diff --git a/.gitignore b/.gitignore index da470e1..34464f6 100644 --- a/.gitignore +++ b/.gitignore @@ -17,6 +17,8 @@ projects/**/slides/s*/*.mkv projects/**/slides/s*/*.wav projects/**/slides/s*/*.mp3 projects/**/slides/s*/*.m4a +projects/**/slides/*.pdf +projects/**/slides/*.pptx projects/**/renders/** projects/**/exports/** projects/**/videos/** diff --git a/AGENTS.md b/AGENTS.md index 3ea8983..5197748 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -158,6 +158,7 @@ Rules: - Visible character identity cannot be generated from text-only prompts when identity matters. - Slide prompts must use the `gpt-image-2` Skill Advisor / host-native workflow. - In `slides/sNN/`, keep Markdown control/script artifacts in Git, but treat generated images, audio, and video as asset-layer files that are ignored by default and recorded by path/hash/status in control files. +- Assembled `.pptx` / `.pdf` files under project `slides/` are generated deliverables. Do not commit them unless the user explicitly promotes a named file as source-authority material. - Project `archive/` directories are for discarded images and discarded documents by default. Do not add them to Git unless the user explicitly promotes a specific archived item back into `intake/`, `visual-system/`, or another source-authority location. - New slide-task execution must append the next unused `sNN-vN-*` version and must not overwrite existing slide artifacts unless the user explicitly authorizes an overwrite repair for named files. - Review defaults to `none` in production-light and local-only in test/audit or explicit review tasks. Do not call Minimax MCP or other external vision/review services unless the user explicitly authorizes that task. diff --git a/projects/2026-06-29-搭上AI这条船/execution-plan.md b/projects/2026-06-29-搭上AI这条船/execution-plan.md new file mode 100644 index 0000000..040b97f --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/execution-plan.md @@ -0,0 +1,81 @@ +# Execution Plan + +## Current Medium Branch + +- Branch: internal PPT full-page visual image production. +- Format: 16:9 horizontal. +- Page count: 24 main pages, with possible backup pages later only if requested. +- Production mode: full-page images first; final PPT assembly after page images are ready. +- Prompt ownership: Codex owns final image prompts; GPT intake is source specification, not final prompt. +- Image prompt workflow: `gpt-image-2` Advisor / host-native path only unless the user explicitly changes policy. + +## Current Execution Focus + +Active focus: + +1. P01 / `s01` cover and public-style sample passed user confirmation. +2. P02 / `s02` first content-page sample passed user confirmation. +3. Remaining page image production `s03-s24` completed through production-light child sessions. +4. Next focus is optional PPT assembly, user visual sampling, or append-only page repair. + +## Operating Defaults + +| Item | Default | +| --- | --- | +| Line | production-light for remaining pages. | +| Worker profile | pending PPT-page-production design; do not blindly reuse MV shot profile. | +| Running mode now | prompt and generate, full-page image-led. | +| Later likely running mode | same. | +| Review mode later | none, unless user asks for sample review / repair. | +| Write policy | append-only; overwrite allowed: no. | +| Source authority | P1-P24 single-page design skeleton. | + +## Visual-System Alignment Scope + +The visual-system stage must settle: + +1. Global palette and atmosphere. +2. Page family taxonomy. +3. Motif rules: ship ticket, route, radar, compass, deck, port, double track, funnel / gate, ladder, training card. +4. Text-in-image tolerance and simplification rules. +5. Which pages should act as visual anchors for the whole deck. + +## Sample-Gate Plan + +The user approved this process: + +| Page | Why | +| --- | --- | +| P01 | Cover and public-style sample: tests the unified dark AI route-map base, ship ticket, route glow, title treatment, and meeting atmosphere. | +| P02 | First content-page sample: tests whether the same base can carry ordinary page structure and meeting-positioning content. | + +Decision rule: + +- If P01 exposes a common base-style issue, revise `visual-system/`. +- If P01 exposes a cover-only issue, revise P01 only. +- If P02 exposes a content-page readability / structure issue that affects later pages, revise `visual-system/` and the style master. +- If P02 exposes only a page-specific issue, revise P02 only. +- After P01 and P02 pass, enter production for the remaining pages. + +## Current Round + +- R0: project files initialized. +- R1: visual-system base accepted. +- R2: P01 cover / public-style sample generated and user-confirmed pass. +- R3: P02 content-page sample generated and user-confirmed pass. +- R4: remaining pages formal production completed for `s03-s24`. + +## Open Decisions + +| Decision | Current Default | +| --- | --- | +| Final deck style | Full-page visual-image-led PPT. | +| Base visual style | Unified deep blue-black AI route operation-map base across all pages; page families vary motifs lightly only. | +| Text treatment | Text may be embedded in images; minor text defects acceptable. | +| People / portraits | Avoid concrete people unless later explicitly needed. Use abstract business-route metaphors. | +| Source charter | Fact-check backup only; not a main compression source. | +| Public visual duplicates | Merge stage 3 / 4 / 5 visual guidance; treat repeats as reinforcement, not conflict. | + +## Next Decision + +If requested, assemble the completed full-page images into a PPT or run targeted append-only repair for any page the user marks unusable. diff --git a/projects/2026-06-29-搭上AI这条船/handoff/2026-06-29-ai-ship-formal-production-handoff.md b/projects/2026-06-29-搭上AI这条船/handoff/2026-06-29-ai-ship-formal-production-handoff.md new file mode 100644 index 0000000..91584e5 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/handoff/2026-06-29-ai-ship-formal-production-handoff.md @@ -0,0 +1,205 @@ +# 2026-06-29 搭上 AI 这条船 Formal Production Handoff + +## Status + +- Project: `2026-06-29-搭上AI这条船` +- Handoff purpose: next clean session starts formal production. +- Current lifecycle phase: formal production setup. +- Current workflow line: production-light for remaining pages. +- Running mode: prompt and generate. +- Review mode: none by default. +- Write policy: append-only; overwrite allowed: no. + +User decision evidence: + +- user_decision: 2026-06-29 user confirmed `slides/s01/s01-v1-image.png` and `slides/s02/s02-v1-image.png` both passed. +- user_decision: 2026-06-29 user requested this handoff and stated the next new session will start formal production. + +## Next-Session Load Order + +Load these files in order: + +1. `AGENTS.md` +2. `projects/2026-06-29-搭上AI这条船/handoff/2026-06-29-ai-ship-formal-production-handoff.md` +3. `projects/2026-06-29-搭上AI这条船/project.md` +4. `projects/2026-06-29-搭上AI这条船/execution-plan.md` +5. `projects/2026-06-29-搭上AI这条船/slides/slides.md` +6. `projects/2026-06-29-搭上AI这条船/visual-system/visual-system.md` +7. `projects/2026-06-29-搭上AI这条船/visual-system/style/style-prompt-master.md` +8. `projects/2026-06-29-搭上AI这条船/visual-system/motifs/motif-registry.md` +9. `projects/2026-06-29-搭上AI这条船/intake/阶段5：P1-P24 单页设计骨架.md` + +Read narrower intake files only if needed: + +- `intake/阶段5：页面清单骨架.md` +- `intake/阶段5：全局页面规则.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段3：搭上 AI 这条船PPT总纲.md` + +Backup fact-check source only: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\AI智能化客户经营团队启动会议章程.md +``` + +Do not re-compress the charter into the main PPT. Use it only to verify a factual claim when needed. + +## Production Basis + +The user selected: + +> 整页视觉图为主。 + +User-confirmed common visual base: + +> 每页底板风格完全统一；统一深蓝黑 AI 航线作战图底盘，按页面家族只做轻微母题变化。 + +User-confirmed samples: + +| Unit | Page | Image | Status | +| --- | --- | --- | --- | +| `s01` | P01 / 搭上 AI 这条船 | `slides/s01/s01-v1-image.png` | user-confirmed pass | +| `s02` | P02 / 今天这场会，不是再动员一次 | `slides/s02/s02-v1-image.png` | user-confirmed pass | + +When helpful, use these two images as visual calibration samples. If a future generation prompt needs actual image-reference behavior, load the local sample image into visible context before generation; a path written inside a prompt is traceability only. + +## Remaining Scope + +Remaining pages: + +```text +s03-s24 +``` + +Source authority: + +```text +intake/阶段5：P1-P24 单页设计骨架.md +``` + +Do not reorder pages, rename page titles, or replace the core conclusion unless the user explicitly changes the deck. + +## Recommended First Production Package + +Default next package: + +```text +s03-s08 +``` + +Reason: + +- These are the next six pages in source order. +- PPT pages are text/layout-heavy, so six pages is a conservative first formal package. +- If the next session judges context and generation flow to be stable, later packages can broaden up to 8 pages. + +Suggested package sequence: + +1. `s03-s08` +2. `s09-s16` +3. `s17-s24` + +Adjust only if the user requests a different scope. + +## Production Rules For Next Session + +Use the lightweight route unless the user changes it: + +- main/new session may directly produce the package; +- no routine review file; +- no child session required for this project unless the next session chooses to use project-default batching; +- no full completeness gate; +- no external vision review; +- no Minimax MCP or other external review services; +- no source-charter expansion; +- no prompt review pause unless the user asks. + +For each page in scope: + +1. Resolve next unused `sNN-vN` by scanning the page folder. +2. Write `sNN-vN-brief.md`. +3. Write `sNN-vN-prompt.md`. +4. Generate `sNN-vN-image.png`. +5. Update `slides/slides.md`. + +Review mode stays: + +```text +none +``` + +Do not write `sNN-vN-review.md` unless the user explicitly asks for review, repair, or diagnosis. + +## Prompt / Generation Route + +Use `gpt-image-2` Skill Advisor / host-native flow. + +Mode result in this session: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false +} +``` + +Expected route: + +```text +brief -> prompt -> host image generation -> copy image into slides/sNN/ -> update slides.md +``` + +Do not use Garden/API paths unless the user explicitly changes policy. + +## Text Policy + +The user accepts minor text, font-size, and typo defects because this is an internal time-constrained meeting deck. + +Still follow these defaults: + +- one title; +- one core judgment; +- short labels; +- reduce long lists before image generation; +- preserve page title and core conclusion from P1-P24 skeleton. + +If a page's generated Chinese text is imperfect but the image direction is good, treat that as a possible PPT-layer repair later, not an automatic image failure. + +## File State At Handoff + +Created / active control files: + +- `project.md` +- `execution-plan.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `slides/slides.md` +- `tasks/2026-06-29-visual-system-alignment/task-log.md` + +Created sample artifacts: + +- `slides/s01/s01-v1-design.md` +- `slides/s01/s01-v1-brief.md` +- `slides/s01/s01-v1-prompt.md` +- `slides/s01/s01-v1-image.png` +- `slides/s02/s02-v1-design.md` +- `slides/s02/s02-v1-brief.md` +- `slides/s02/s02-v1-prompt.md` +- `slides/s02/s02-v1-image.png` + +No review files were written for the sample run. + +## Stop / Escalation Conditions + +Stop and ask the user if: + +- generated pages drift away from the accepted P01/P02 style; +- text becomes too broken for internal meeting use; +- a page requires a public-style change rather than a page-local repair; +- generation output suggests the deck is becoming customer proposal / government report / SaaS dashboard / cyberpunk tech poster; +- there is an artifact collision because a target `sNN-vN-*` path already exists. + +Otherwise continue production under the approved lightweight rules. diff --git a/projects/2026-06-29-搭上AI这条船/intake/阶段3：搭上 AI 这条船PPT总纲.md b/projects/2026-06-29-搭上AI这条船/intake/阶段3：搭上 AI 这条船PPT总纲.md new file mode 100644 index 0000000..28e6692 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/intake/阶段3：搭上 AI 这条船PPT总纲.md @@ -0,0 +1,66 @@ +# 《搭上 AI 这条船：AI 智能化客户经营团队启动会》PPT 总纲 v1 + +## 0. 总定位 + +这套 PPT 不是销售动员，不是制度宣贯，也不是培训课件。 + +它的定位是： + +> **把一份内部章程，转成一次“兄弟一起开新局”的共识会议。** + +会议要达成的不是“大家听我安排”，而是： + +> **我把完整方案摊出来，大家一起补充、校准、升级，然后立刻进入第一周训练。** + +原始章程的核心目的，是建立一支不是传统卖课、卖软件、卖项目的新型团队，而是围绕企业智能化，建立客户经营、认知升级、场景发现、商务推进和项目落地之间的协同体系。 + +--- + +## 1. PPT 核心主线 + +这套 PPT 的主线建议定为： + +> **船票有了，航线有了，人也找对了。 +> 现在先上船，边学边打。** + +展开链路： + +```text +为什么现在必须变 +↓ +为什么我不能再一个人顶全部 +↓ +为什么这次要找你们 +↓ +为什么 AI 时代给了外行上船机会 +↓ +我们卖的不是 AI 产品，而是一条企业智能化路径 +↓ +客户怎么判断，不能乱推系统 +↓ +团队怎么分工，你们怎么成长 +↓ +先记住三条边界 +↓ +进入一个月培训 +↓ +第一周先形成自己的 AI 训练目标 +``` + +--- + +## 2. 45 分钟会议节奏 + +| 模块 | 时间 | 作用 | +| --------- | ----: | ------------------------------ | +| 开场定调 | 3 分钟 | 说明今天不是动员，是共识会 | +| 为什么必须变 | 7 分钟 | 讲清行业焦虑、AI机会、我的角色变化 | +| 为什么找你们 | 10 分钟 | 重点建立信心：Agentic 技术平权，老销售经验变成新优势 | +| 我们到底卖什么 | 8 分钟 | 讲三级服务路径：培训、顾问、系统 | +| 客户怎么筛 | 5 分钟 | 讲客户适配判断模型 | +| 团队怎么协作 | 6 分钟 | 讲团队结构、五个角色、魏征机制 | +| 怎么成长、怎么训练 | 6 分钟 | 讲 L0-L4、一个月培训、第一周目标 | + +现场可以随时打断交流，所以 PPT 本身不要做成“密集讲稿”，而要做成**每页一个判断，每页一个停留点**。 + +--- diff --git a/projects/2026-06-29-搭上AI这条船/intake/阶段4：通用表达与视觉系统.md b/projects/2026-06-29-搭上AI这条船/intake/阶段4：通用表达与视觉系统.md new file mode 100644 index 0000000..edf5d07 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/intake/阶段4：通用表达与视觉系统.md @@ -0,0 +1,92 @@ +# 阶段4：通用表达与视觉系统 + +## 1. 表达任务 + +这套 PPT 要让参会者形成四个感觉： + +1. **兴奋感**：AI 这条船不是口号，已经有船票了。 +2. **信心感**：他们不是因为懂技术才被需要，而是因为懂人、懂局、懂客户。 +3. **秩序感**：兄弟一起开新局，但未来必须公司化、流程化。 +4. **行动感**：会后不空谈，马上进入第一周训练。 + +--- + +## 2. 语言风格 + +建议使用： + +> **自己人口吻 + 公司化骨架 + 战斗前夜的兴奋感。** + +语言特点： + +* 用“我”和“我们”，不要过度组织化。 +* 判断要直接，不绕。 +* 少讲抽象概念，多讲“为什么是你们”。 +* 规则轻讲，训练重讲。 +* 技术判断可以保留原文锐度。 + +关键句式： + +> **先上船，再学怎么开船。** +> **第一阶段不要求懂 AI，要求会带着 AI 工作。** +> **老销售的能力没有过时，只是换了发动机。** +> **技术平权，不是人人都当程序员，而是外行也能参与探索。** + +--- + +## 3. 统摄性隐喻 + +核心隐喻： + +> **搭上 AI 这条船。** + +隐喻展开： + +| 隐喻 | 对应内容 | +| ---- | -------------------- | +| 船票 | AI 时代的新机会已经出现 | +| 上船 | 有意愿的人先进入训练和协作 | +| 航线 | 培训 → 顾问 → 系统 | +| 船员分工 | 专家、客户经营、AI业务工程师、工程底座 | +| 雷达 | 客户判断、风险识别、机会发现 | +| 罗盘 | 方法论、客户适配模型、承诺边界 | +| 训练营 | 一个月培训，第一周 AI 习惯训练 | + +--- + +## 4. 视觉基调 + +不做人像，不做复杂插画。 + +建议风格： + +> **深蓝黑商务底 + 航线图 + 雷达光效 + 金色/青色重点词 + 大模型图。** + +视觉关键词： + +* 深海蓝 +* 航线 +* 雷达扫描 +* 罗盘 +* 船票 +* 甲板 +* 港口 +* 路线图 +* 作战地图 +* 分层阶梯 + +页面文字可以直接进入图中，因为这是内部会议使用，主要是替代长文阅读。 + +--- + +## 5. 固定页面模板 + +建议固定 5 类页面： + +1. **封面页**：大标题 + 航线背景。 +2. **判断页**：一句大判断 + 3 个支撑点。 +3. **模型页**：三级路径、客户适配、L0-L4 等。 +4. **对比页**：传统销售 vs AI客户经营，传统工程师 vs Agentic工程师。 +5. **行动页**：第一周训练目标、会后作业。 + +--- diff --git a/projects/2026-06-29-搭上AI这条船/intake/阶段5：P1-P24 单页设计骨架.md b/projects/2026-06-29-搭上AI这条船/intake/阶段5：P1-P24 单页设计骨架.md new file mode 100644 index 0000000..3b60c83 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/intake/阶段5：P1-P24 单页设计骨架.md @@ -0,0 +1,1574 @@ +# P1-P24 单页设计骨架 + +--- + +## P01：搭上 AI 这条船 + +### 1. 本页功能 + +封面定调。 +让大家一进来就知道：今天不是随便聊聊，而是正式开局。 + +### 2. 页面核心结论 + +> **船票已经有了，今天我们正式上船。** + +### 3. 页面文字方向 + +主标题： + +> **搭上 AI 这条船** + +副标题： + +> **AI 智能化客户经营团队启动会** + +角标小字： + +> 内部共识会议 / 启动培训前置会 + +底部短句： + +> 先上船，再学怎么开船。 + +### 4. 页面结构 / Layout + +全屏封面。 + +中间大标题。 +背景是深蓝色海面或数字航线图。 +画面中有一条发光航线，从暗处延伸到远方。 + +### 5. 视觉资产设计 + +不要出现具体人物。 + +可用： + +* 数字海面； +* 航线光轨； +* AI 雷达； +* 远处港口灯光； +* 一张抽象船票。 + +### 6. 讲述关键词 + +* 今天不是动员； +* 动员已经做过； +* 今天是正式摊开方案； +* 大家一起补充、校准、升级； +* 会后立刻进入培训。 + +### 7. 承上启下 + +从标题进入会议定位： + +> 今天这场会，不是再动员一次。 + +### 8. 验收关注点 + +封面要有兴奋感，不要做成政府汇报风。 +“AI 船票”这个隐喻要一眼成立。 + +--- + +## P02：今天这场会，不是再动员一次 + +### 1. 本页功能 + +明确会议性质。 +防止大家误以为今天是继续画饼、喊口号。 + +### 2. 页面核心结论 + +> **大家已经有意愿，今天要形成共同方案。** + +### 3. 页面文字方向 + +标题： + +> **今天这场会，不是再动员一次** + +左侧： + +> 不是： +> 再讲一遍 AI 多重要 +> 再劝大家要不要参与 +> 我一个人宣布安排 +> 听完就散 + +右侧： + +> 是： +> 把完整方案摊开 +> 让大家补充不同角度 +> 必要时升级方案 +> 会后立刻进入第一周训练 + +底部金句： + +> **不是“我说你们听”，是“我们一起把这件事定下来”。** + +### 4. 页面结构 / Layout + +左右对比页。 + +左侧灰色“不是”。 +右侧青色/金色“是”。 +中间用一条竖线分开。 + +### 5. 视觉资产设计 + +背景可以是会议桌俯视图的抽象线框。 +右侧可叠加“共识 / 补充 / 升级 / 训练”四个发光节点。 + +### 6. 讲述关键词 + +* 私下都聊过； +* 有意愿的人已经在船边了； +* 今天不是一家之言； +* 今天要把章程变成团队共识。 + +### 7. 承上启下 + +接下来解释：我们到底要建什么团队。 + +### 8. 验收关注点 + +这页要把会议气质立住：不是命令式，而是共识式。 + +--- + +## P03：我们要建的，不是传统销售团队 + +### 1. 本页功能 + +定义团队身份。 +把“销售”从传统卖货语境里拔出来。 + +### 2. 页面核心结论 + +> **我们要建的是 AI 智能化客户经营团队。** + +### 3. 页面文字方向 + +标题： + +> **我们要建的，不是传统销售团队** + +中心大词： + +> **AI 智能化客户经营团队** + +周围五个关键词： + +> 识别客户 +> 经营关系 +> 管理预期 +> 发现机会 +> 推动合作 + +底部短句： + +> **不是卖课、卖软件、卖项目，而是经营客户智能化旅程。** + +### 4. 页面结构 / Layout + +中心圆模型。 + +中间是“AI智能化客户经营团队”。 +外圈五个能力点环绕。 +最外圈是客户、专家、AI业务工程师、工程团队四个协作对象。 + +### 5. 视觉资产设计 + +使用雷达扫描盘。 +团队在雷达中心，客户机会点分布在外圈。 + +### 6. 讲述关键词 + +* 传统销售是卖东西； +* 我们做的是客户经营； +* 客户不知道怎么走，我们要帮他识别路径； +* 不是一单生意，是一条旅程。 + +### 7. 承上启下 + +为什么现在必须建这样的团队？因为形势变了。 + +### 8. 验收关注点 + +页面不要只写“销售升级”，要明确“客户经营”这个新身份。 + +--- + +## P04：为什么现在必须变 + +### 1. 本页功能 + +建立现实压力。 +把大家的焦虑转成上船动力。 + +### 2. 页面核心结论 + +> **旧船越来越难跑，新船已经靠岸。** + +### 3. 页面文字方向 + +标题： + +> **为什么现在必须变** + +三句话： + +> 原来的行业和产业，业绩在下滑。 +> AI 不是远方趋势，而是新的生意入口。 +> 现在不上船，后面会越来越被动。 + +底部金句： + +> **焦虑不是坏事，焦虑说明我们已经看见了水位变化。** + +### 4. 页面结构 / Layout + +左右对比。 + +左侧：旧行业下滑曲线。 +右侧：AI 新航线打开。 +中间：一个“转向点”。 + +### 5. 视觉资产设计 + +左边可用暗色下降曲线、旧码头。 +右边用亮色航线、远方灯塔。 +整体不要悲观，要有转机感。 + +### 6. 讲述关键词 + +* 大家不是没有能力； +* 是旧赛道变难； +* AI 不是概念，是新入口； +* 这次我们不是看热闹，是要上船做事。 + +### 7. 承上启下 + +接下来讲：这不是临时起意，我这半年已经打通了很多东西。 + +### 8. 验收关注点 + +不要讲成宏观趋势报告，要贴近他们的现实焦虑。 + +--- + +## P05：我这半年打通了什么 + +### 1. 本页功能 + +建立强哥的准备度。 +让大家相信这不是临时凑局，而是方法论已经基本成型。 + +### 2. 页面核心结论 + +> **产品力、方法论、训练路径，已经准备到可以开局。** + +### 3. 页面文字方向 + +标题： + +> **我这半年打通了什么** + +三列： + +> 产品力 +> 有了培训、顾问、系统的三级路径 + +> 方法论 +> 有了企业智能化转型的判断框架 + +> 训练路径 +> 有了把销售老兵训练成 AI 增强型商务人员的方法 + +底部短句： + +> **不是因为 AI 热才做，而是因为路径终于想清楚了。** + +### 4. 页面结构 / Layout + +三段式能力底座。 + +底部是一条船的甲板。 +甲板上立起三根桅杆：产品力、方法论、训练路径。 + +### 5. 视觉资产设计 + +可用“船体结构图”隐喻。 +船体代表团队开局能力，三根桅杆代表三大准备。 + +### 6. 讲述关键词 + +* 我想了半年； +* 以前有些思路还不清晰； +* 现在基本打通了； +* 今天就是把这个清晰方案拿出来。 + +### 7. 承上启下 + +为什么必须从我一个人推动，变成团队推动？ + +### 8. 验收关注点 + +这页不要变成个人履历炫耀，要强调“我准备好了，可以带大家开局”。 + +--- + +## P06：我的角色已经变了 + +### 1. 本页功能 + +讲清强哥身份转型。 +这是组织调整的根本原因之一。 + +### 2. 页面核心结论 + +> **我不能再长期同时承担所有角色。** + +### 3. 页面文字方向 + +标题： + +> **我的角色已经变了** + +左侧旧角色： + +> 全能型老板 +> 专家 +> 商务 +> 销售 +> 方案 +> 谈判 +> 客户维护 +> 项目把关 + +右侧新角色： + +> 学者型实践专家 +> 方法论构建者 +> 认知引导者 +> 场景判断者 +> 方案质量把关者 +> 专家督导 + +底部短句： + +> **我不是退出前线，而是换到更该站的位置。** + +### 4. 页面结构 / Layout + +左右转型箭头。 + +左侧是一个人扛很多标签。 +右侧是一个专家节点连接多个团队节点。 + +### 5. 视觉资产设计 + +避免人物肖像。 +用抽象图标：一个高压中心节点 → 多节点协作网络。 + +### 6. 讲述关键词 + +* 过去两年其实已经这样配合； +* 只是以前不成文； +* 今天正式说清楚； +* 我以后主要站在方法论和专家判断位置。 + +### 7. 承上启下 + +过去靠我个人推，未来要靠团队、流程、工具和方法论推。 + +### 8. 验收关注点 + +要让大家感觉这是“体系升级”，不是“强哥甩锅”。 + +--- + +## P07：过去靠我一个人顶，未来靠体系一起跑 + +### 1. 本页功能 + +从个人转型过渡到团队建设。 +让“建团队”变成必然。 + +### 2. 页面核心结论 + +> **个人驱动必须升级为团队驱动。** + +### 3. 页面文字方向 + +标题： + +> **过去靠我一个人顶，未来靠体系一起跑** + +上半部分： + +> 过去： +> 线索靠我判断 +> 方案靠我讲 +> 商务靠我谈 +> 风险靠我兜 +> 客户关系也往我身上集中 + +下半部分： + +> 未来： +> 团队分工 +> AI 工具 +> 客户经营 +> 培训路径 +> 流程机制 +> 方法论支撑 + +底部金句： + +> **一个人能冲得快，体系才能跑得远。** + +### 4. 页面结构 / Layout + +上：单引擎小船。 +下：多引擎船队。 + +### 5. 视觉资产设计 + +单点发动机 vs 多节点协同网络。 +从“中心压力”转成“分布式推进”。 + +### 6. 讲述关键词 + +* 我成为瓶颈； +* 客户也容易把所有问题都压到我身上； +* 这不利于做大； +* 接下来要公司化正规化。 + +### 7. 承上启下 + +那未来大家不是传统销售，是什么？ + +### 8. 验收关注点 + +页面要有组织升级感，不要像抱怨自己太累。 + +--- + +## P08：为什么不是传统销售 + +### 1. 本页功能 + +重定义销售工作。 +让大家知道自己不是来“卖 AI 概念”的。 + +### 2. 页面核心结论 + +> **这件事不是把 AI 卖出去，而是把客户带上正确路径。** + +### 3. 页面文字方向 + +标题： + +> **为什么不是传统销售** + +左侧： + +> 传统销售 +> 找客户 +> 讲产品 +> 谈价格 +> 促成交 +> 追回款 + +右侧： + +> AI 客户经营 +> 看懂客户 +> 判断基础 +> 识别场景 +> 管理预期 +> 推进路径 +> 保护边界 + +底部短句： + +> **不是卖东西，是经营客户的智能化旅程。** + +### 4. 页面结构 / Layout + +左右对比表。 + +不要做成贬低传统销售。 +要体现“老能力升级为新打法”。 + +### 5. 视觉资产设计 + +左侧是“成交漏斗”。 +右侧是“客户旅程航线”。 + +### 6. 讲述关键词 + +* 你们都是老销售； +* 传统销售能力仍然有用； +* 但 AI 项目不能靠老套路硬推； +* 要看客户能不能走、适合走到哪一步。 + +### 7. 承上启下 + +为什么这次偏偏要找你们？因为你们的老经验在新阶段反而重要。 + +### 8. 验收关注点 + +不要把老销售说成过时，而是说“发动机换了”。 + +--- + +## P09：为什么这次找你们 + +### 1. 本页功能 + +建立参会者信心。 +让他们知道自己不是因为懂技术被找来，而是因为懂人、懂局、懂客户。 + +### 2. 页面核心结论 + +> **AI 客户经营第一阶段，最重要的是识人、识局、识势。** + +### 3. 页面文字方向 + +标题： + +> **为什么这次找你们** + +三个大词： + +> 识人 +> 看谁是真决策者，谁只是旁观者 + +> 识局 +> 看客户组织里谁推动，谁阻力，谁买单，谁验收 + +> 识势 +> 看客户是真要做，还是只想听热闹 + +底部金句： + +> **老销售的能力没有过时，只是换了发动机。** + +### 4. 页面结构 / Layout + +三角模型。 + +底部是“多年社会经验 / 客户经验 / 谈判经验”。 +上面托起三个能力：识人、识局、识势。 + +### 5. 视觉资产设计 + +可以用雷达扫描客户组织。 +雷达上出现不同颜色的客户角色点：决策者、推动者、阻力者、旁观者。 + +### 6. 讲述关键词 + +* 你们懂人情； +* 你们懂饭局、关系、组织里的微妙变化； +* 这些不是 AI 能直接替代的； +* AI 可以增强你们，但不能替你们做人。 + +### 7. 承上启下 + +更关键的是，Agentic 时代让外行也有了进场机会。 + +### 8. 验收关注点 + +这页要让他们“抬头”，不是让他们觉得自己被培训。 + +--- + +## P10：Agentic 技术平权：外行也能上船 + +### 1. 本页功能 + +本套 PPT 的信心核心之一。 +解释为什么信息化时代他们在外围，AI Agentic 时代可以进前场。 + +### 2. 页面核心结论 + +> **技术平权，不是人人都当程序员，而是外行也能参与探索。** + +### 3. 页面文字方向 + +标题： + +> **Agentic 技术平权：外行也能上船** + +三句话： + +> 信息化时代，门槛在代码、系统、数据库。 +> Agentic 时代，入口变成业务理解、自然语言、任务拆解。 +> 所以，低技术包袱的人，反而更容易进入探索轨。 + +底部金句： + +> **不懂代码，不等于不能做 AI。** + +### 4. 页面结构 / Layout + +交叉图。 + +横轴：技术门槛。 +纵轴：业务理解。 +信息化时代高技术门槛。 +Agentic 时代业务理解权重上升。 + +### 5. 视觉资产设计 + +一张“登船坡道”图。 +过去是高墙，需要程序员钥匙；现在是坡道，懂业务的人可以先上船。 + +### 6. 讲述关键词 + +* 不是说技术不重要； +* 是第一阶段不是写大系统； +* 第一阶段是发现问题、拆任务、试原型； +* 这些事你们可以学。 + +### 7. 承上启下 + +为什么我说传统软件工程师和 Agentic 工程师是两个物种？ + +### 8. 验收关注点 + +这页一定要讲成“给销售信心”，不要讲成技术判断课。 + +--- + +## P11：传统软件工程师和 Agentic 工程师，是两个物种 + +### 1. 本页功能 + +强化反直觉判断。 +这是解释“为什么找你们”的关键页，而不是系统分工页。 + +### 2. 页面核心结论 + +> **这不是技术栈升级，而是能力系统变化。** + +### 3. 页面文字方向 + +标题： + +> **传统软件工程师和 Agentic 工程师，是两个物种** + +左侧： + +> 传统软件工程师 +> 接需求 +> 写代码 +> 调接口 +> 做数据库 +> 做权限 +> 做测试 +> 解决确定性问题 + +右侧： + +> Agentic 工程师 +> 理解含混目标 +> 拆解业务任务 +> 用自然语言组织流程 +> 验证 AI 输出 +> 设计智能体任务链 +> 处理不确定性问题 + +底部短句： + +> **一个擅长把确定需求做稳，一个擅长把模糊问题探索出来。** + +### 4. 页面结构 / Layout + +左右对比。 + +中间用一句话隔开： + +> **不是谁高级谁低级，是两种不同能力系统。** + +### 5. 视觉资产设计 + +左侧是工程蓝图、管线、接口。 +右侧是探索地图、任务网络、智能体链路。 + +可以保留你原文里的锐度： + +> 传统工程师更像 API 水管工。 +> Agentic 工程师更像问题的业主。 + +但这句话建议放小一点，作为讲述用，不一定做成页面最大字。 + +### 6. 讲述关键词 + +* 这页不是贬低技术团队； +* 技术团队负责稳定系统，很重要； +* 但探索客户 AI 价值，不是他们天然擅长； +* 所以你们有机会进前场。 + +### 7. 承上启下 + +既然第一阶段不是写代码，那第一阶段要求是什么？ + +### 8. 验收关注点 + +这一页要服务“拉他们上船”，不能提前陷入工程分工细节。 + +--- + +## P12：第一阶段要求：不是懂 AI，而是会带着 AI 工作 + +### 1. 本页功能 + +降低进入门槛。 +把“我要学 AI”降维成“我要开始用 AI 工作”。 + +### 2. 页面核心结论 + +> **先会用，再会卖，再会带客户用。** + +### 3. 页面文字方向 + +标题： + +> **第一阶段要求：不是懂 AI，而是会带着 AI 工作** + +中心循环： + +> 事前问 AI +> 会中观察人 +> 会后用 AI 复盘 +> 下一次调整打法 + +页面短句： + +> 不要求一开始懂原理。 +> 不要求一开始懂技术。 +> 先要求形成 AI 工作习惯。 + +底部金句： + +> **把 AI 用到自己身上，才有资格带客户上船。** + +### 4. 页面结构 / Layout + +闭环图。 + +四个节点组成循环： + +1. 会前准备； +2. 现场观察； +3. 会后复盘； +4. 下一步行动。 + +### 5. 视觉资产设计 + +使用 AI 工作流闭环。 +背景可以是雷达扫描后的客户画像卡片。 + +### 6. 讲述关键词 + +* 不要怕 AI； +* 不懂就问； +* 每天用起来； +* 会前用 AI，和会后用 AI，是第一阶段最重要的训练。 + +### 7. 承上启下 + +有了人和训练入口，接下来讲我们到底卖什么。 + +### 8. 验收关注点 + +这页要让他们觉得“我今天晚上就能开始”，不是“我要先学半年”。 + +--- + +## P13：我们卖的不是 AI 产品，是一条企业智能化路径 + +### 1. 本页功能 + +定义商业产品。 +避免他们理解成出去卖课、卖软件、卖系统。 + +### 2. 页面核心结论 + +> **客户真正需要的，是从想用 AI 到用好 AI 的路径。** + +### 3. 页面文字方向 + +标题： + +> **我们卖的不是 AI 产品，是一条企业智能化路径** + +主路径： + +> 想用 AI +> ↓ +> 看懂 AI +> ↓ +> 找到场景 +> ↓ +> 形成方案 +> ↓ +> 试点验证 +> ↓ +> 系统落地 +> ↓ +> 真正用好 + +底部短句： + +> **产品是入口，路径才是价值。** + +### 4. 页面结构 / Layout + +航线图。 + +从“想用 AI”的港口，沿航线经过多个节点，最后到“用好 AI”的港口。 + +### 5. 视觉资产设计 + +使用航线节点地图。 +每个节点是一盏灯塔或浮标。 + +### 6. 讲述关键词 + +* 客户不是缺一个工具； +* 客户缺的是判断； +* 不知道该不该做、先做什么、怎么做； +* 我们卖的是路径感和确定性。 + +### 7. 承上启下 + +这条路径在产品上分成三级：培训、顾问、系统。 + +### 8. 验收关注点 + +这页要把“路径”讲透，不要停留在口号。 + +--- + +## P14：三级服务路径：培训 → 顾问 → 系统 + +### 1. 本页功能 + +展示核心商业路径。 +这是必须讲清楚的主模型之一。 + +### 2. 页面核心结论 + +> **培训是入口，顾问是筛选，系统是重服务。** + +### 3. 页面文字方向 + +标题： + +> **三级服务路径：培训 → 顾问 → 系统** + +三层： + +> 第一级：培训 +> 建立认知，打开入口，发现意愿 + +> 第二级：顾问 +> 梳理场景，判断基础，设计路径 + +> 第三级：系统 +> 重服务、重交付、重验收，只适合少数成熟客户 + +底部金句： + +> **不是所有客户都直接上系统。** + +### 4. 页面结构 / Layout + +三段航线或三层阶梯。 + +每一层标明： + +* 目标； +* 销售角色； +* 客户状态； +* 下一步动作。 + +### 5. 视觉资产设计 + +三段式航线： + +1. 近海训练区：培训； +2. 航道判断区：顾问； +3. 深水建设区：系统。 + +### 6. 讲述关键词 + +* 培训不是陪跑； +* 顾问不是陪聊； +* 系统不是乱卖； +* 三级路径是我们未来最重要的产品逻辑。 + +### 7. 承上启下 + +那什么客户能进系统？要先筛。 + +### 8. 验收关注点 + +这页要成为“他们出去讲业务”的最基础模型。 + +--- + +## P15：培训可以宽，顾问要筛，系统必须严 + +### 1. 本页功能 + +建立客户推进原则。 +防止销售见客户就想推系统。 + +### 2. 页面核心结论 + +> **做错项目，比少做项目更伤。** + +### 3. 页面文字方向 + +标题： + +> **培训可以宽，顾问要筛，系统必须严** + +三句话： + +> 培训：可以宽，适合打开入口。 +> 顾问：必须筛，适合判断路径。 +> 系统：必须严，适合成熟客户。 + +底部金句： + +> **宁可少做项目，也不能做错项目。** + +### 4. 页面结构 / Layout + +漏斗图。 + +上层大口：培训。 +中层收窄：顾问。 +底层小口：系统。 + +旁边加风险提示： + +> 错客户 = 消耗团队 + 消耗客户 + 消耗信用。 + +### 5. 视觉资产设计 + +航道闸门隐喻。 +越往系统阶段，闸门越窄，检查越严格。 + +### 6. 讲述关键词 + +* 培训是入口； +* 系统是重服务； +* 系统一旦做错，后面全是麻烦； +* 销售的价值也包括筛掉不合适客户。 + +### 7. 承上启下 + +筛客户不能凭感觉，至少要看四个方面。 + +### 8. 验收关注点 + +这页一定要把“宽入口、严系统”讲成纪律感，但不要吓人。 + +--- + +## P16：客户适配判断模型 + +### 1. 本页功能 + +给销售一个初步判断框架。 +这是他们未来看客户的罗盘。 + +### 2. 页面核心结论 + +> **客户能不能做 AI，至少看四件事。** + +### 3. 页面文字方向 + +标题： + +> **客户适配判断模型** + +四个判断维度： + +> 基础建设 +> 有没有系统、数据、资料、流程和知识沉淀 + +> 组织认知 +> 老板、高层、中层、员工怎么看 AI + +> 业务场景价值 +> 是否高频、重复、高成本、高风险、高知识密度 + +> 项目权力结构 +> 谁决策、谁付款、谁使用、谁验收、谁推动、谁阻力 + +底部短句： + +> **客户想不想做，不等于客户能不能做。** + +### 4. 页面结构 / Layout + +四象限罗盘。 + +中心是“客户是否适合智能化”。 +四个方向分别是基础、认知、场景、权力。 + +### 5. 视觉资产设计 + +罗盘 + 雷达结合。 +每个方向有 3-4 个关键词标签。 + +### 6. 讲述关键词 + +* 老销售有直觉； +* 但 AI 项目要把直觉结构化； +* 以后会训练大家用 AI 做客户分析； +* 先记住这四个维度。 + +### 7. 承上启下 + +判断完客户，未来项目会进入两条轨道，但眼下重点是先上探索轨。 + +### 8. 验收关注点 + +这页信息可能多，要控制关键词，不要变成表格堆砌。 + +--- + +## P17：双轨体系：先探索价值，再工程兑现 + +### 1. 本页功能 + +讲双轨体系，但不提前展开系统建设。 +重点是告诉大家：你们现在先进入探索轨。 + +### 2. 页面核心结论 + +> **眼下重点不是系统建设分工，而是先把探索轨跑起来。** + +### 3. 页面文字方向 + +标题： + +> **双轨体系：先探索价值，再工程兑现** + +两条轨： + +> 探索轨：发现价值 +> 客户访谈、培训、场景梳理、智能体原型、试点验证 + +> 工程轨：兑现价值 +> 正式系统、数据库、权限、接口、部署、测试、维护 + +中间大字： + +> **先拉上船，再说怎么造大船。** + +底部短句： + +> **我们现在要先学会发现价值。** + +### 4. 页面结构 / Layout + +双轨图。 + +探索轨在上方，用亮色。 +工程轨在下方，用深色。 +探索轨前置，工程轨后接。 + +### 5. 视觉资产设计 + +两条铁路 / 航道并行。 +探索轨是雷达船，工程轨是工程船。 +雷达船先出去探水深，工程船后面跟进。 + +### 6. 讲述关键词 + +* 今天不是重点讲系统建设； +* 未来系统还有几个月准备期； +* 现在先学习、准备工具、规划潜在客户、做培训顾问； +* 真到系统建设，再细化分工。 + +### 7. 承上启下 + +既然是探索轨，团队结构就不是老板+销售+技术，而是新的协作结构。 + +### 8. 验收关注点 + +这页要避免跑偏到工程管理。 +核心是：销售老兵先进入探索轨。 + +--- + +## P18：新团队协作结构 + +### 1. 本页功能 + +讲团队结构。 +让他们看见未来不是单点作战，而是协同体系。 + +### 2. 页面核心结论 + +> **未来不是老板 + 销售 + 技术，而是四类角色协同。** + +### 3. 页面文字方向 + +标题： + +> **新团队协作结构** + +中心结构： + +> 学者型首席专家 +> 负责方法论、认知引导、场景判断、方案把关 + +> 客户经营负责人 +> 负责客户关系、初筛、商务推进、预期管理、魏征反馈 + +> AI 业务工程师 +> 负责业务问题转译、智能体原型、轻量部署、客户训练 + +> 确定性工程底座 +> 负责正式系统、数据库、权限、接口、部署运维 + +底部短句： + +> **各就各位，才能打大仗。** + +### 4. 页面结构 / Layout + +四节点协作图。 + +中间放“客户智能化旅程”。 +四类角色围绕旅程协作。 + +### 5. 视觉资产设计 + +作战地图式结构图。 +每个角色是一个功能舱位： + +* 专家舱； +* 客户经营舱； +* AI业务工程舱； +* 工程底座舱。 + +### 6. 讲述关键词 + +* 现在不要求大家一步到位； +* 但要知道未来结构； +* 我的位置变了； +* 你们不是外围，而是客户前端。 + +### 7. 承上启下 + +那客户经营团队在客户面前到底做什么？就是帮客户上船。 + +### 8. 验收关注点 + +这页距离他们稍远，要讲得务实，不要组织架构化太重。 + +--- + +## P19：我们是帮客户上船的人 + +### 1. 本页功能 + +精神锚点页。 +用低阻抗语言解释“入口、雷达、翻译器、推进器、防火墙”。 + +### 2. 页面核心结论 + +> **客户不知道怎么上 AI 这条船，我们就是带路的人。** + +### 3. 页面文字方向 + +标题： + +> **我们是帮客户上船的人** + +主金句： + +> **客户不知道怎么上 AI 这条船，我们就是那个带路的人。** + +五个角色： + +> 入口：把客户带进来 +> 雷达：看见机会和风险 +> 翻译器：把客户的话翻译成业务问题 +> 推进器：推动合作往前走 +> 防火墙：守住承诺和边界 + +底部短句： + +> **找到客户，听懂客户，判断客户，推动客户，守住边界。** + +### 4. 页面结构 / Layout + +中心一艘船 / 一条登船通道。 + +五个角色围绕登船路径排布。 +每个词配一个简单图标。 + +### 5. 视觉资产设计 + +不要做复杂插画。 +用简洁信息图： + +* 入口 = 船票； +* 雷达 = 雷达盘； +* 翻译器 = 双向箭头； +* 推进器 = 发动机； +* 防火墙 = 护盾。 + +### 6. 讲述关键词 + +* 原话比较抽象； +* 换成大白话就是帮客户上船； +* 客户不懂 AI，不知道该问什么； +* 我们要在前面带路，也在后面守边界。 + +### 7. 承上启下 + +带路的人还要能提醒我，这就是魏征机制。 + +### 8. 验收关注点 + +这一页要成为全场最容易记住的一页。 + +--- + +## P20：魏征机制：你们也是我的现实校准器 + +### 1. 本页功能 + +建立内部协作机制。 +让大家知道他们不只是销售，也要帮助强哥控制会议节奏和现实反馈。 + +### 2. 页面核心结论 + +> **你们不是打断我，是帮我保护会议节奏。** + +### 3. 页面文字方向 + +标题： + +> **魏征机制：你们也是我的现实校准器** + +三段： + +> 会前提醒 +> 这次会议目标是什么，哪些该讲，哪些点到为止 + +> 会中拉回 +> 老师，这部分我们后面结合资料再展开 + +> 会后复盘 +> 今天有没有讲太多，有没有形成误解，客户真正关心什么 + +底部金句： + +> **AI 能提醒我，但现实里的魏征更管用。** + +### 4. 页面结构 / Layout + +三段流程。 + +会前 → 会中 → 会后。 +每段配一个“校准动作”。 + +### 5. 视觉资产设计 + +可以用罗盘校准 / 航向修正隐喻。 +一艘船偏航，旁边有人调整罗盘。 + +### 6. 讲述关键词 + +* 你们都了解我； +* 我一讲容易讲深、讲散； +* 你们要帮我收回来； +* 复盘时客户经营负责人先说，我后说。 + +### 7. 承上启下 + +不同人参与程度不同，所以需要 L0-L4 成长路径。 + +### 8. 验收关注点 + +这页要有兄弟之间的信任感，不要做成管理制度页。 + +--- + +## P21：L0-L4 成长路径 + +### 1. 本页功能 + +给每个人一条现实成长路线。 +避免一上来就封头衔，也避免大家不知道自己从哪里开始。 + +### 2. 页面核心结论 + +> **头衔不是先给的，是训练和行为拿到的。** + +### 3. 页面文字方向 + +标题： + +> **L0-L4 成长路径** + +阶梯： + +> L0 渠道伙伴 +> 只能引荐客户，不能独立承诺 + +> L1 AI 商务助理 +> 参与会前准备、会后复盘 + +> L2 客户经营负责人 +> 独立做客户初筛和客户跟进 + +> L3 商务负责人 +> 在授权范围内谈报价、合同、回款 + +> L4 AI 前端部署顾问 +> 做工具配置、知识库整理、轻量原型和客户培训 + +底部金句： + +> **不是所有人一步到位，但每个人都有上升通道。** + +### 4. 页面结构 / Layout + +五级阶梯图。 + +左低右高。 +每一级只保留角色名、核心权限、进入条件关键词。 + +### 5. 视觉资产设计 + +阶梯 / 船舱等级 / 航海执照隐喻。 +L0-L4 像不同航行资格。 + +### 6. 讲述关键词 + +* 今天不是马上定死； +* 现在只是有个成长框架； +* 将来分级标准会细化； +* 先从第一周训练开始看。 + +### 7. 承上启下 + +成长可以慢慢来，但底线今天先钉住三条。 + +### 8. 验收关注点 + +这页要给希望，不要给压力。 +“L0”不能让人觉得低人一等。 + +--- + +## P22：今天先记住三条 + +### 1. 本页功能 + +轻规则页。 +不展开完整商务防火墙，只钉住三条底线。 + +### 2. 页面核心结论 + +> **规则可以慢慢细化，但底线今天先钉住。** + +### 3. 页面文字方向 + +标题： + +> **今天先记住三条** + +三张大卡片： + +> **不装专家** +> 不懂可以学，不懂不能装懂。 + +> **不乱承诺** +> 可以谈方向，不能承诺结果。 + +> **不把不成熟客户直接推系统** +> 培训可以宽，顾问要筛，系统必须严。 + +底部短句： + +> **老江湖也要适应新边界。** + +### 4. 页面结构 / Layout + +三卡片并列。 + +每张卡片只放一句解释。 +不要做成纪律清单。 + +### 5. 视觉资产设计 + +三枚“航行底线”印章。 +或者三道安全闸门。 + +### 6. 讲述关键词 + +* 你们都是老销售，这些不是教常识； +* 但 AI 项目风险不一样； +* 今天不讲太多规则； +* 后面培训会逐步细化。 + +### 7. 承上启下 + +规则后面慢慢来，现在马上进入一个月训练。 + +### 8. 验收关注点 + +这页要轻，但要稳。 +不要把氛围从兴奋拉成纪律教育。 + +--- + +## P23：一个月训练：成为 AI 增强型客户经营人员 + +### 1. 本页功能 + +交代培训路径。 +让大家知道启动会后马上进入训练，不是听完就散。 + +### 2. 页面核心结论 + +> **一个月后，大家至少要会用 AI 做准备、复盘和客户判断。** + +### 3. 页面文字方向 + +标题： + +> **一个月训练：成为 AI 增强型客户经营人员** + +四周路线： + +> 第一周：和 AI 交朋友 +> 形成自己的 AI 工作习惯 + +> 第二周：客户沟通与业务理解 +> 学会用 AI 辅助客户分析，学会问对问题 + +> 第三周：产品边界与承诺规则 +> 知道什么能说，什么不能说 + +> 第四周：模拟拜访、陪访与认证 +> 把前三周用于真实或模拟场景 + +底部金句： + +> **不是培养技术专家，是培养 AI 增强型商务人员。** + +### 4. 页面结构 / Layout + +四周时间线。 + +每周一个节点。 +节点下只写目标，不写细节。 + +### 5. 视觉资产设计 + +训练营路线图。 +从“新船员训练”到“前端客户经营”。 + +### 6. 讲述关键词 + +* 启动会后立刻培训； +* 第一周不是学理论； +* 是让大家真正用起来； +* 一个月后至少具备基础客户经营能力。 + +### 7. 承上启下 + +先不要想一个月，今天先落到第一周目标。 + +### 8. 验收关注点 + +这页不要展开成课程大纲，保持总览感。 + +--- + +## P24：第一周目标：写出自己的 AI 训练目标 + +### 1. 本页功能 + +行动收束。 +把会议落到每个人的第一步。 + +### 2. 页面核心结论 + +> **会后第一件事：每个人形成自己的第一周 AI 训练目标。** + +### 3. 页面文字方向 + +标题： + +> **第一周目标：写出自己的 AI 训练目标** + +页面问题： + +> 1. 我准备用 AI 解决哪个工作问题？ +> 2. 我每天准备什么时候用 AI？ +> 3. 我会前准备用 AI 做什么准备？ +> 4. 我会后准备用 AI 做什么复盘？ +> 5. 一周后，我希望自己拿出什么成果？ + +底部升级方向： + +> 后续升级为： +> **《我的 AI 工作流说明书》** + +收束金句： + +> **先从自己开始，把 AI 用起来。** + +### 4. 页面结构 / Layout + +作业卡片页。 + +左侧是“第一周 AI 训练目标”。 +右侧是五个问题。 +底部是“提交成果”。 + +### 5. 视觉资产设计 + +一张“船员第一周训练卡”。 +可以做成表单式视觉，但不需要太正式。 + +### 6. 讲述关键词 + +* 每个人情况不同； +* 不要求统一答案； +* 关键是自己先用； +* 先形成第一周目标，再检查第一周成果。 + +### 7. 承上启下 + +这一页就是会议结束动作。 +讲完后可以进入现场交流、补充意见和第一次培训。 + +### 8. 验收关注点 + +这页必须能直接变成会后行动。 +不要做成口号页。 + +--- diff --git a/projects/2026-06-29-搭上AI这条船/intake/阶段5：全局页面规则.md b/projects/2026-06-29-搭上AI这条船/intake/阶段5：全局页面规则.md new file mode 100644 index 0000000..6d2e136 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/intake/阶段5：全局页面规则.md @@ -0,0 +1,60 @@ +# 一、全局页面规则 + +## 1. 页面气质 + +这套 PPT 的气质是： + +> **兄弟一起开新局，但要按公司化打法打仗。** + +不是客户汇报，不是正式课件，不是制度宣贯。 + +它应该像一张**上船前的作战地图**。 + +--- + +## 2. 统一视觉系统 + +建议统一采用： + +> **深蓝黑商务底 + AI 航线图 + 雷达光效 + 青色/金色高亮关键词 + 大模型图。** + +视觉元素： + +* 船票； +* 航线； +* 罗盘； +* 雷达； +* 甲板； +* 港口； +* 双轨； +* 阶梯； +* 作战地图； +* 客户旅程。 + +--- + +## 3. 页面文字策略 + +因为这是内部交流，且你明确说 PPT 本质上是替代看文本，所以： + +* 页面可以直接承载文字； +* 不用过度追求留白； +* 但每页必须有一个大判断； +* 每页最多一个主模型； +* 不要把原文整段复制进页面。 + +执行时，每页建议采用： + +> **一句大标题 + 一句核心判断 + 一个模型 / 三个要点 / 一张关系图。** + +--- + +## 4. 讲述备注策略 + +你自己讲，不需要完整备注。 + +每页只给： + +> **讲述关键词 / 过渡句 / 容易讲散的提醒。** + +--- diff --git a/projects/2026-06-29-搭上AI这条船/intake/阶段5：页面清单骨架.md b/projects/2026-06-29-搭上AI这条船/intake/阶段5：页面清单骨架.md new file mode 100644 index 0000000..a9b8b31 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/intake/阶段5：页面清单骨架.md @@ -0,0 +1,140 @@ + +# 阶段5：页面清单骨架 v1 + +## 主 PPT：24 页 + +| 页码 | 页面标题 | 页面功能 | 核心结论 | 页面结构 / 视觉方向 | 讲述关键词 | +| --: | -------------------------- | ------- | ------------------------------------- | ---------------------------------------------------------- | ------------------------ | +| P01 | 搭上 AI 这条船 | 封面定调 | 船票已经有了，今天我们正式上船 | 深蓝航线背景 + 大标题 + 副标题“AI智能化客户经营团队启动会” | 不是动员，是开局 | +| P02 | 今天这场会，不是再动员一次 | 会议定位 | 大家已经有意愿，今天是把方案摊开形成共识 | 左侧“不是”，右侧“是” | 共识、补充、升级 | +| P03 | 我们要建的，不是传统销售团队 | 核心定义 | 我们要建的是 AI 智能化客户经营团队 | 中心大词“客户经营团队”，四周围绕：客户、认知、场景、商务、落地 | 不卖话术，不卖热闹 | +| P04 | 为什么现在必须变 | 现实压力 | 旧行业下滑，AI 新船靠岸，不能再观望 | 一边是下滑曲线，一边是航船靠岸 | 焦虑不是坏事，是上船动力 | +| P05 | 我这半年打通了什么 | 强哥方法论背书 | 产品力、方法论、培训路径已经准备到可以带队开局 | 三段式：产品力 / 方法论 / 培训体系 | 不是临时起意 | +| P06 | 我的角色已经变了 | 角色转型 | 我不能再长期同时承担专家、商务、销售、方案和客户维护 | “全能型老板”到“学者型实践专家”的箭头 | 过去靠我顶，未来靠体系打 | +| P07 | 过去是我一个人往前推，未来要靠团队一起跑 | 组织升级 | 个人驱动要升级为团队、流程、工具、方法论驱动 | 单点发动机 → 多引擎船队 | 我不是退出，是换位置 | +| P08 | 为什么不是传统销售 | 销售身份重定义 | 这件事不是把 AI 卖出去，而是把客户带上正确路径 | 传统销售 vs 客户经营负责人对比 | 不是卖东西，是经营客户旅程 | +| P09 | 为什么这次找你们 | 信心建立 | AI 客户经营第一阶段，最重要的是懂人、懂局、懂客户 | 三个大词：识人 / 识局 / 识势 | 你们的老经验没有过时 | +| P10 | Agentic 技术平权：外行也能上船 | 核心信心页 | AI 时代，低技术包袱的人反而更容易参与探索 | “技术门槛下降，业务理解上升”的交叉图 | 不懂代码，不等于不能做 AI | +| P11 | 传统软件工程师和 Agentic 工程师，是两个物种 | 反直觉判断 | 这不是技术栈升级，而是能力系统变化 | 左右对比：确定性工程 vs 不确定性探索 | 这页是给大家信心，不是贬低技术 | +| P12 | 第一阶段要求：不是懂 AI，而是会带着 AI 工作 | 学习门槛降维 | 先养成 AI 工作习惯，再谈客户经营能力升级 | “事前问 AI / 事后用 AI 复盘”循环图 | 先会用，再会卖，再会带客户 | +| P13 | 我们卖的不是 AI 产品，是一条企业智能化路径 | 产品定义 | 客户真正需要的是从想用 AI 到用好 AI 的路径 | 航线图：想用 AI → 能用 AI → 用好 AI | 产品不是单点，是路径 | +| P14 | 三级服务路径：培训 → 顾问 → 系统 | 必讲模型 1 | 培训是入口，顾问是筛选，系统是重服务 | 三段航线 / 三层阶梯 | 不是所有客户都直接上系统 | +| P15 | 培训可以宽，顾问要筛，系统必须严 | 客户推进原则 | 宽入口、严系统，避免做错客户 | 漏斗图：培训大口径 → 顾问筛选 → 系统少数 | 做错项目比少做项目更伤 | +| P16 | 客户适配判断模型 | 必讲模型 2 | 判断客户至少看四件事：基础、认知、场景、权力 | 四象限罗盘：基础建设 / 组织认知 / 业务场景 / 权力结构 | 客户能不能做，比想不想做更重要 | +| P17 | 双轨体系：先探索价值，再工程兑现 | 必讲模型 3 | 探索轨负责发现价值，工程轨负责兑现价值 | 两条轨道图：探索轨在前，工程轨在后 | 眼下先拉上船，系统建设后面再细化 | +| P18 | 新团队协作结构 | 必讲模型 4 | 未来不是老板+销售+技术，而是专家、客户经营、AI业务工程师、工程底座协作 | 中心结构图：强哥 / 客户经营 / AI业务工程师 / 工程底座 | 每个人不是什么都干，而是各就各位 | +| P19 | 我们是帮客户上船的人 | 精神锚点降维 | 客户不知道怎么上 AI 这条船，我们就是带路的人 | 五个角色围绕一艘船：入口、雷达、翻译器、推进器、防火墙 | 找到客户、听懂客户、判断客户、推动客户、守住边界 | +| P20 | 魏征机制：你们也是我的现实校准器 | 关系机制 | 你们不只是销售，也要提醒我、校准我、保护会议节奏 | “会前提醒 / 会中拉回 / 会后复盘”三段图 | 不是打断我，是保护节奏 | +| P21 | L0-L4 成长路径 | 必讲模型 5 | 头衔不是先给的，是通过训练和行为拿到的 | 阶梯图：L0渠道伙伴 → L1 AI商务助理 → L2客户经营负责人 → L3商务负责人 → L4 AI前端部署顾问 | 先定位，再成长 | +| P22 | 今天先记住三条 | 轻规则页 | 不装专家，不乱承诺，不把不成熟客户直接推系统 | 三张大卡片 | 规则以后慢慢细化，今天先钉住底线 | +| P23 | 一个月训练：先成为 AI 增强型客户经营人员 | 培训总览 | 一个月后，大家至少会用 AI 做准备、复盘和客户判断 | 四周训练路线：交朋友 / 懂客户 / 知边界 / 模拟拜访 | 不是培养技术专家，是培养 AI 增强型商务 | +| P24 | 第一周目标：写出自己的 AI 训练目标 | 行动收束 | 会后第一件事：每个人形成自己的第一周 AI 训练目标 | 作业页：我准备用 AI 解决什么、每天何时用、会前会后怎么用、一周后交什么 | 先从自己开始，把 AI 用起来 | + +--- + +## 3. 重点页面处理建议 + +### P10-P12 是本次 PPT 的信心核心 + +这里不要讲成技术课。 + +核心不是解释 Agentic，而是让他们明白： + +> **信息化时代，他们只能在外围。 +> Agentic 时代，他们可以进入前场。** + +这一组页面要打出气势： + +> 不是你们不懂技术，所以不适合。 +> 恰恰是因为这件事一开始不是写代码，而是理解人、理解业务、理解场景，所以你们适合先上船。 + +原文章程中也明确指出，销售第一阶段的要求不是懂 AI，而是会带着 AI 工作；同时，Agentic 工程面对的是目标不清晰、路径不确定、业务上下文复杂的问题，这正是传统确定性工程之外的新能力空间。 + +--- + +### P14-P16 是业务路径核心 + +这三页负责把“我们到底卖什么”讲清楚。 + +一句话： + +> **我们不是见客户就卖系统。 +> 我们先用培训打开入口，用顾问筛出价值，最后才谈系统。** + +原文章程中对客户分层已经有清晰判断，尤其是“培训可以宽，顾问要筛，系统必须严”这句话，应该保留为主视觉金句。 + +--- + +### P18-P21 是团队关系核心 + +这四页要让他们明白： + +> **不是今天给大家封官，而是给大家一条成长路径。** + +重点讲两个模型： + +1. **团队协作结构**：强哥不再什么都亲自扛，客户经营团队要站到前台。 +2. **L0-L4 成长路径**：每个人从自己的现实条件出发，不必一步到位。 + +原文章程里，启动会议要达成的共识包括：不是传统销售团队、销售要成为 AI 增强型商务人员、强哥从全能型老板转为学者型首席专家、客户经营负责人要做读人识局和“魏征”等。 + +--- + +## 4. 主金句库 + +可分散放到页面标题、副标题或结束页： + +1. **船票现在有了，先上船。** +2. **我们卖的不是 AI 产品，而是一条企业智能化路径。** +3. **第一阶段不要求懂 AI，要求会带着 AI 工作。** +4. **老销售的能力没有过时，只是换了发动机。** +5. **技术平权，不是人人当程序员，而是外行也能参与探索。** +6. **培训可以宽，顾问要筛，系统必须严。** +7. **客户不知道怎么上 AI 这条船，我们就是带路的人。** +8. **头衔不是先给的，是训练和行为拿到的。** +9. **规则可以慢慢细化，但底线今天先钉住。** +10. **先把 AI 用到自己身上，再带客户上 AI 这条船。** + +--- + +## 5. 不建议进入主 PPT 的内容 + +这些内容不是不重要，而是不适合这次启动会展开： + +* 佣金分成； +* 报价规则； +* 详细权限； +* 四级承诺矩阵细则； +* 禁止话术大全； +* 红线考试； +* 销售工具模板； +* 项目交接模板； +* 智能体清单明细； +* 培训结业标准。 + +它们适合后续变成： + +> **培训材料 / 章程附录 / 流程模板 / 工作手册。** + +--- + +## 6. 备份页建议 + +可放 4 页备份，不主动讲，现场有人问再打开： + +1. 章程原文目录； +2. 一个月培训详细安排； +3. 客户分层表； +4. 四级承诺矩阵简版。 + +--- + +## 7. 导演审查 + +这一版最重要的调整是： + +> **把“传统软件工程师和 Agentic 工程师是两个物种”前置为信心建立页，而不是后置为双轨分工页。** + +因为这次启动会的第一任务不是讲未来系统建设，而是让这些销售老兵意识到： + +> **AI 时代不是把他们挡在门外，而是给了他们重新进场的机会。** diff --git a/projects/2026-06-29-搭上AI这条船/project.md b/projects/2026-06-29-搭上AI这条船/project.md new file mode 100644 index 0000000..e05fbb1 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/project.md @@ -0,0 +1,103 @@ +# 2026-06-29-搭上AI这条船 + +## Status + +- Status: P01-P24 full-page image production completed via production-light child sessions. +- Medium type: 16:9 internal kickoff meeting PPT. +- Output direction: full-page visual-image-led deck. +- Lifecycle phase: page image production complete. +- Workflow phase: production-light run completed for remaining pages. +- Review default for later production: none, unless the user requests sampling or repair. +- Current execution focus: optional PPT assembly, user visual sampling, or append-only repairs if requested. + +## Meeting Positioning + +This deck is for an internal kickoff speech. It is not an archive version of the charter, not a customer proposal, and not a formal training courseware package. + +The deck should create shared confidence, make the team feel they can board the AI route now, and move directly into first-week AI training goals. + +Core sentence: + +> 船票有了，航线有了，人也找对了。现在先上船，边学边打。 + +## Output Format Decision + +The user selected: + +> 整页视觉图为主。 + +Execution meaning: + +- Each PPT page may be treated as a 16:9 full-page visual image. +- Page text may appear directly inside the generated image. +- Minor typography, font-size, and typo imperfections are acceptable because this is a time-constrained internal meeting deck. +- The deck should prioritize atmosphere, momentum, page-level judgment, and visual memory over fine editable text polish. +- If a page has too much text for reliable image rendering, the working default is to simplify visible text to title, core judgment, and short labels. + +## Source Hierarchy + +Main PPT authority: + +1. `intake/阶段5：P1-P24 单页设计骨架.md` +2. `intake/阶段5：页面清单骨架.md` +3. `intake/阶段5：全局页面规则.md` +4. `intake/阶段4：通用表达与视觉系统.md` +5. `intake/阶段3：搭上 AI 这条船PPT总纲.md` + +Backup fact-check source only: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\AI智能化客户经营团队启动会议章程.md +``` + +The charter must not be re-compressed into the main PPT. Use it only if a factual claim in the intake files needs verification. + +## Accepted Intake + +| File | Role | Use | +| --- | --- | --- | +| `intake/阶段3：搭上 AI 这条船PPT总纲.md` | meeting story | Main emotional arc, timing, and core story chain. | +| `intake/阶段4：通用表达与视觉系统.md` | expression / visual system | Tone, language, visual motifs, page family guidance. | +| `intake/阶段5：P1-P24 单页设计骨架.md` | page-level authority | Canonical page order, page titles, conclusions, and per-page visual direction. | +| `intake/阶段5：全局页面规则.md` | global page rules | Deck tone, text strategy, and shared visual elements. | +| `intake/阶段5：页面清单骨架.md` | page table | Compact page list and key-page treatment notes. | + +## Current Visual Direction + +> 深蓝黑商务底 + AI 航线图 + 雷达光效 + 青色/金色高亮关键词 + 船票 / 罗盘 / 路线图 / 作战地图视觉母题。 + +The feel should be: + +> 兄弟一起开新局，但要按公司化打法打仗。 + +Accepted base direction: + +> 每页底板风格完全统一；统一深蓝黑 AI 航线作战图底盘，按页面家族只做轻微母题变化。 + +## Key Local Execution Files + +| File | Purpose | +| --- | --- | +| `execution-plan.md` | Current execution control and next decision. | +| `visual-system/visual-system.md` | Merged shared visual system. | +| `visual-system/style/style-prompt-master.md` | Reusable style and prompt-language master for later page prompts. | +| `visual-system/motifs/motif-registry.md` | Motif-to-page-family registry. | +| `slides/slides.md` | P01-P24 page execution status table. | +| `tasks/2026-06-29-visual-system-alignment/task-plan.md` | Current setup and visual-system alignment task. | + +## Production Handoff + +Current handoff for the next clean session: + +```text +handoff/2026-06-29-ai-ship-formal-production-handoff.md +``` + +User decision evidence: + +- 2026-06-29: user confirmed both generated sample images passed: `slides/s01/s01-v1-image.png` and `slides/s02/s02-v1-image.png`. +- 2026-06-29: formal production completed for `s03-s24` across three direct child sessions; review mode `none`. + +## Next Action + +Use the completed page images as the production-pass source for optional PPT assembly. If the user finds a page unusable, repair it append-only as a new `sNN-vN` version. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-brief.md new file mode 100644 index 0000000..b68793a --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-brief.md @@ -0,0 +1,126 @@ +# S-01 Slide Brief V1 + +## Status + +- Status: ready for prompt. +- Source page: P01. +- Output type: 16:9 full-page visual image. +- Running mode: prompt and generate. +- Review mode: none. +- Write policy: append-only; overwrite allowed: no. + +## Source Basis + +- `../../intake/阶段5：P1-P24 单页设计骨架.md` +- `../../visual-system/visual-system.md` +- `../../visual-system/style/style-prompt-master.md` +- `../../visual-system/motifs/motif-registry.md` +- `s01-v1-design.md` + +Backup fact-check source recorded but not used: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\AI智能化客户经营团队启动会议章程.md +``` + +## Slide Function + +封面定调，同时作为整套 PPT 的公共视觉样片。它要让参会者第一眼明白：这不是随便聊聊，而是正式开局。 + +## First Read + +第一眼应该读到： + +> 搭上 AI 这条船。 + +第二眼读到： + +> 船票已经有了，今天我们正式上船。 + +第三眼读到深蓝黑 AI 航线作战图、发光航线、抽象船票、远方港口灯光。 + +## Risk Class + +- Risk class: core motif / title-safe cover. +- Public-style risk: high, because this page tests the common deck base. +- Page-specific risk: medium, because title and ship-ticket placement can be adjusted locally. + +## Reference Plan + +- Actual visual reference image: none. +- Style source: `visual-system/style/style-prompt-master.md` +- Motif source: `visual-system/motifs/motif-registry.md` +- Active style module: Module A, Opening / Consensus. +- Core motifs: AI 航线, 船票, 港口 / 灯塔, 雷达. +- Generation path: host-native image generation; Garden/API expected: no. + +## Visual Requirements + +- 16:9 horizontal full-page cover image. +- Deep navy-black AI maritime route-map base. +- Cyan glowing route from lower-left / dark origin toward upper-right / far port. +- Abstract AI boarding ticket as a foreground signal, gold edge and cyan data marks. +- Far port / lighthouse warm-gold signal light. +- Subtle radar scan, compass marks, coordinate grid, and navigation lines. +- No real people, no real meeting room, no literal large ship. + +## Character Handling + +No visible character. Do not add faces, silhouettes of attendees, speakers, or crew. + +## Composition / Scale + +- Main title: central-left or mid-upper area, dominant. +- Route line: lower-left to upper-right, behind title but readable. +- Ticket: lower-right preferred, 12%-18% of frame, secondary to title. +- Port light: upper-right / far-depth, small but legible. +- Radar / compass: background layer only. + +## Light / Color / Texture + +- Base: deep blue-black, dark navy, cold slate gray. +- Signal: cyan for route / AI / radar, restrained gold for ticket / opportunity / port. +- Title: white or pale-blue, with subtle cyan/gold accent on `AI` if stable. +- Texture: cinematic business, map glass, subtle scan lines, no cyberpunk excess. + +## Text Plan + +Use in-image text. Minor text defects are acceptable, but keep text short. + +Required text priority: + +1. `搭上 AI 这条船` +2. `AI 智能化客户经营团队启动会` +3. `先上船，再学怎么开船。` + +Optional small label: + +- `内部共识会议 / 启动培训前置会` + +If text rendering is unstable, keep the main title and subtitle; bottom and corner text can be repaired later in PPT. + +## Forbidden Drift + +Avoid: + +- government meeting cover; +- customer proposal cover; +- generic tech summit poster; +- cyberpunk neon city; +- cute cartoon ship / pirate ship / fantasy ship; +- literal cruise ship hero; +- humanoid robots or AI faces; +- dense dashboard UI; +- text too small or paragraph-like. + +## Acceptance Checklist + +- The cover feels like a formal internal kickoff, not a customer-facing deck. +- The AI route / boarding ticket metaphor is clear. +- The unified deep navy-black operation-map base is usable for later pages. +- The title is the first visual read. +- The image has excitement and order at the same time. + +## Prompt Handoff + +Create a host-native image prompt using the active Module A language and this brief. Do not use external reference images. Record `mode: B-or-C / host-or-advisor`. Generate directly in the main session after prompt creation, with no review file and no child session. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-design.md new file mode 100644 index 0000000..82fcdbd --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-design.md @@ -0,0 +1,169 @@ +# S-01 Slide Design V1 + +## Status + +- Status: draft for user review. +- Source page: P01. +- Page title: 搭上 AI 这条船. +- Role: cover page and public-style sample. +- Line: test/audit sample. +- Write policy: append-only; overwrite allowed: no. +- Next gate: user confirms design before brief / prompt / image generation. + +## Design Purpose + +本页既是封面，也是整套 PPT 的公共视觉样片。它要一次性验证三件事： + +1. 统一深蓝黑 AI 航线作战图底板是否成立； +2. “AI 船票 / 上船 / 航线”这个核心隐喻是否一眼能看懂； +3. 封面是否有内部启动会的兴奋感，而不是政府汇报、客户方案或培训课件。 + +如果本页失败，需要先区分原因：公共底板问题回改 `visual-system/`；封面局部构图问题只改 P01。 + +## Discussion Summary + +用户已确认整套 PPT 采用“整页视觉图为主”，每页底板风格完全统一。公共方向为： + +> 统一深蓝黑 AI 航线作战图底盘 + 按页面家族轻微变化母题。 + +P01 作为第一张样片，优先测试公共底板、标题字、青色 / 金色高亮、航线、雷达、船票与港口远光的组合。 + +## Visual Concept + +画面是一张“上船前的 AI 作战航线图”。 + +底层是深蓝黑的数字海面 / 航海地图，带有非常克制的网格、坐标线、罗盘刻度和雷达扫描光。画面中有一条青色发光航线从左下或底部暗处出发，穿过画面中心，延伸到右上远方的港口灯光。航线不是旅游路线，而像一条被正式批准的行动路径。 + +前景需要出现一张抽象“AI 船票”：不做真实纸票，不做复古票据，而是一张带金色边缘、青色数据线、登船编号感的半透明发光卡片。它可以位于画面右下或左下，与主标题错开，不遮挡文字。船票的作用是让“船票已经有了”这个隐喻成立。 + +整体第一感觉应该是：正式开局、准备上船、路线已经亮起来。 + +## Image Base Requirements + +生成图应该包含： + +- 16:9 横版全屏封面。 +- 深蓝黑商务底，带 AI 航线作战图质感。 +- 一条明确的青色发光航线，从暗处延伸到远处。 +- 远处港口 / 灯塔 / 航线终点的微弱暖金光。 +- 抽象 AI 船票，金色边缘 + 青色数据纹理。 +- 低调雷达扫描圈、罗盘刻度、坐标网格作为背景层。 + +生成图不需要包含： + +- 具体人物。 +- 真实船只特写。 +- 会议室照片。 +- 复杂仪表盘 UI。 +- 可交互按钮、卡片堆、SaaS dashboard。 + +允许少量文字直接进入图中。文字应尽量大、短、清晰。 + +## Text / Typography Plan + +页面文字建议直接进入图中： + +主标题： + +> 搭上 AI 这条船 + +副标题： + +> AI 智能化客户经营团队启动会 + +角标小字： + +> 内部共识会议 / 启动培训前置会 + +底部短句： + +> 先上船，再学怎么开船。 + +标题层级： + +- 主标题为全页最大文字，放在画面中部偏左或中部偏上。 +- `AI` 可以用青色或淡金色强调，但不要做霓虹 cyberpunk。 +- 副标题放在主标题下方，字号明显小一档。 +- 角标小字放在左上或右上，像内部资料标记。 +- 底部短句放在底部安全区，作为收束金句。 + +如果图像模型中文不够稳定，后续可接受小字轻微错漏；但主标题必须尽量清楚，不能被装饰压住。 + +## Layout / Safe Areas + +建议构图： + +- 主标题区域：画面中部偏左，宽度约 55%-65%。 +- 航线主方向：从左下 / 下中出发，向右上远方延伸。 +- 船票：右下或左下前景，面积约画面 12%-18%，不能抢主标题。 +- 港口 / 灯塔远光：右上远方或画面深处，面积小，但要形成“目的地已亮”的感觉。 +- 雷达 / 罗盘图层：铺在背景，不要比标题更亮。 +- 四周保留边缘安全区，避免标题、角标、底句贴边。 + +视觉重心顺序： + +1. 主标题； +2. 发光航线； +3. 抽象船票； +4. 远方港口光； +5. 雷达 / 罗盘 / 网格细节。 + +## Color Guidance + +基础色： + +- 深蓝黑； +- 暗海军蓝； +- 冷灰蓝； +- 近黑。 + +信号色： + +- 青色用于航线、雷达、AI 信号； +- 金色用于船票边缘、机会感、启动感； +- 白色 / 淡蓝白用于标题。 + +色彩边界： + +- 不要大面积紫色渐变。 +- 不要亮红金政府风。 +- 不要高饱和赛博霓虹。 +- 金色只能作为信号和重点，不要让画面变成奢华黑金海报。 + +## Post-Production Notes + +本项目默认接受文字直接烘在图里。若 P01 图像整体气质很好，但文字轻微不稳，后续可以保留图像作为封面底图，再用 PPT 文字层覆盖主标题 / 副标题。此动作属于封面局部修正，不必回改公共视觉系统。 + +如果出现以下情况，则属于公共视觉问题，需要回改 `visual-system/`： + +- 底板像 SaaS dashboard，而不是 AI 航线作战图； +- 过度 cyberpunk； +- 像政府汇报或客户方案； +- 船票 / 航线隐喻不成立； +- 深蓝黑底板压抑但没有开局感。 + +## Constraints / Avoid + +必须避免： + +- 具体人物、群体、领导发言照； +- 具象大船、邮轮、海盗船、童话船； +- 可爱卡通船票； +- 旅游广告海面； +- 政府会议封面； +- 客户提案封面； +- 普通科技峰会海报； +- 机器人头像、AI 大脑、芯片脸； +- 文字太多、标题被挤压； +- 大面积纯渐变背景，没有航线 / 雷达 / 罗盘逻辑。 + +## Confirmation Gate + +请检查： + +1. 这个封面方向能否作为整套 PPT 的公共视觉样片； +2. “AI 船票 / 正式上船 / 航线已亮”是否一眼成立； +3. 主标题与副标题文案是否按现版本保留； +4. 船票应放右下、左下，还是更靠中心。 + +确认后再进入 `s01-v1-brief.md`、`s01-v1-prompt.md` 和封面图生成。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-prompt.md new file mode 100644 index 0000000..e814c0c --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-prompt.md @@ -0,0 +1,79 @@ +# S-01 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s01-v1-brief.md` +- Review mode: none. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P01 / S-01. +- Page family: A / Opening / Consensus. +- Active style module: `visual-system/style/style-prompt-master.md`, Module A. +- Core motifs: AI 航线, 船票, 港口 / 灯塔, 雷达. +- Actual image references: none. +- Reference note: no public visual reference image exists for this project yet; use the accepted text visual-system as the style authority. +- Main title: `搭上 AI 这条船` +- Core judgment: `船票已经有了，今天我们正式上船。` +- Text complexity: low. +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Use built-in host image generation directly. +- No child session, no review file, no completeness gate. + +## Advisor / Host-Native Record + +Mode: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false +} +``` + +## Final Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page cover image for an internal PowerPoint kickoff meeting + +Create a 16:9 full-page visual slide image, cinematic executive business style. This is the cover page for an internal kickoff meeting titled "搭上 AI 这条船". The page should feel like a deep navy-black AI maritime operation map: a formal "boarding route" for a company team opening a new AI business line. + +Scene/backdrop: deep blue-black digital sea and maritime route-map background, subtle coordinate grid, compass markings, faint radar scan rings, restrained navigation-map texture. It should feel like an "AI航线作战图", not a software dashboard. + +Primary visual structure: a clear cyan glowing route line starts from a dark lower-left / lower-center origin and travels toward the upper-right distance. At the far destination, show small warm-gold port lights or a lighthouse-like signal, suggesting the route is now open. Add an abstract AI boarding ticket in the lower-right foreground: semi-transparent dark glass card, restrained gold edge, cyan data marks, no logo, no QR code focus. The ticket should be a supporting motif, not the main subject. + +Text (verbatim Chinese, keep large and readable): +- Main title, largest: "搭上 AI 这条船" +- Subtitle below: "AI 智能化客户经营团队启动会" +- Bottom line: "先上船，再学怎么开船。" +- Optional small corner label: "内部共识会议 / 启动培训前置会" + +Typography: bold modern Chinese sans-serif, high contrast, white or pale-blue title with very subtle cyan/gold accent on "AI". Keep text short and spacious. Main title must be the first read. Do not use decorative calligraphy. + +Composition/framing: title in the middle-left or mid-upper area, route line behind and around it without interfering with readability. Ticket in lower-right, about 12-18% of frame. Radar/compass/grid elements stay in the background. Keep safe margins around all text. + +Lighting/mood: energetic but disciplined, formal internal kickoff, "the route is ready, we are boarding now." Cinematic dark business atmosphere, not gloomy. + +Color palette: deep navy-black, dark slate blue, cyan AI signal light, restrained warm gold, pale-blue/white title. + +Constraints: no real people, no meeting room photo, no literal big ship, no cartoon ship, no pirate or fantasy ship, no humanoid robot, no AI face, no generic tech conference poster, no government-report red-gold style, no customer proposal style, no dense dashboard UI, no pure gradient background, no watermark, no logo. + +## Negative / Avoid + +Avoid unreadable small Chinese text, over-dense paragraphs, cyberpunk neon overload, luxury black-gold poster tone, cute illustration, stock-photo realism, cruise ship imagery, and UI cards. + +## Output Intent + +Generate `s01-v1-image.png` as the cover and public-style sample candidate. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-brief.md new file mode 100644 index 0000000..80e2985 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-brief.md @@ -0,0 +1,151 @@ +# S-02 Slide Brief V1 + +## Status + +- Status: ready for prompt. +- Source page: P02. +- Output type: 16:9 full-page visual image. +- Running mode: prompt and generate. +- Review mode: none. +- Write policy: append-only; overwrite allowed: no. + +## Source Basis + +- `../../intake/阶段5：P1-P24 单页设计骨架.md` +- `../../visual-system/visual-system.md` +- `../../visual-system/style/style-prompt-master.md` +- `../../visual-system/motifs/motif-registry.md` +- `s02-v1-design.md` + +Backup fact-check source recorded but not used: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\AI智能化客户经营团队启动会议章程.md +``` + +## Slide Function + +明确会议性质，作为第一张内容页样片。它要说明：今天不是继续动员，而是把方案摊开形成共同方案。 + +## First Read + +第一眼应该读到： + +> 今天这场会，不是再动员一次。 + +第二眼读到左右对比： + +> 不是旧式动员；是共同定方案。 + +第三眼读到右侧的行动节点： + +> 共识 / 补充 / 升级 / 训练。 + +## Risk Class + +- Risk class: content-page readability / comparison infographic. +- Public-style risk: medium, because this tests whether the common base supports normal content pages. +- Page-specific risk: medium, because text density and left-right balance may need adjustment. + +## Reference Plan + +- Actual visual reference image: none. +- Style source: `visual-system/style/style-prompt-master.md` +- Motif source: `visual-system/motifs/motif-registry.md` +- Active style module: Module A, Opening / Consensus. +- Core motifs: AI 航线, route split, radar / operation-map grid, activated nodes. +- Generation path: host-native image generation; Garden/API expected: no. + +## Visual Requirements + +- 16:9 horizontal full-page content slide image. +- Same deep navy-black AI route operation-map base as P01. +- Clear left-right comparison layout. +- Left side: dark gray-blue, deactivated / closed route, marked `不是`. +- Right side: active cyan/gold route, marked `是`. +- Middle: thin glowing vertical route divider / checkpoint / routing gate. +- Right side: four glowing action nodes: 共识, 补充, 升级, 训练. +- Optional subtle top-down abstract meeting table linework in the background, very faint. + +## Character Handling + +No visible character. Do not add real people, meeting photos, speakers, or audience. + +## Composition / Scale + +- Header zone: top 15%-18%, title and core judgment. +- Main comparison zone: middle 65%-70%. +- Footer quote zone: bottom 10%-12%. +- Left block: 42%-45%, low-light gray-blue. +- Right block: 45%-48%, brighter cyan/gold. +- Divider: 4%-6% center zone. + +## Light / Color / Texture + +- Base: same deep navy-black AI route operation-map base as S-01. +- Left: muted slate gray / low-light blue-gray. +- Right: active cyan route and restrained gold highlights. +- Footer quote: small gold or pale-blue emphasis. +- Texture: business operation map, not SaaS dashboard. + +## Text Plan + +Use in-image text. Minor text defects are acceptable, but the prompt must keep text compact. + +Required text priority: + +1. `今天这场会，不是再动员一次` +2. `不是` +3. `是` +4. `共识` +5. `补充` +6. `升级` +7. `训练` + +Secondary text if space and rendering stability allow: + +Left: + +- `再讲 AI 多重要` +- `再劝要不要参与` +- `我一个人宣布安排` +- `听完就散` + +Right: + +- `摊开完整方案` +- `补充不同角度` +- `必要时升级方案` +- `进入第一周训练` + +Footer: + +> 不是“我说你们听”，是“我们一起把这件事定下来”。 + +If the generator cannot reliably handle all text, prioritize title, `不是 / 是`, and four right-side nodes. Secondary item text can be repaired later in PPT. + +## Forbidden Drift + +Avoid: + +- white consulting table; +- ordinary dashboard UI; +- real meeting-room photograph; +- command-style policy page; +- overly negative or accusatory `不是` side; +- too much text; +- separated style from S-01; +- cyberpunk split line; +- software project-management board. + +## Acceptance Checklist + +- The page remains visibly in the same deck style as S-01. +- The `不是 / 是` contrast reads quickly. +- The right-side path feels active and collaborative. +- It feels like consensus formation, not orders from above. +- Content is usable for an internal meeting even if minor text defects appear. + +## Prompt Handoff + +Create a host-native image prompt using Module A language and this brief. Do not use external reference images. Record `mode: B-or-C / host-or-advisor`. Generate directly in the main session after prompt creation, with no review file and no child session. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-design.md new file mode 100644 index 0000000..116692e --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-design.md @@ -0,0 +1,207 @@ +# S-02 Slide Design V1 + +## Status + +- Status: draft for user review. +- Source page: P02. +- Page title: 今天这场会，不是再动员一次. +- Role: first content-page sample. +- Line: test/audit sample. +- Write policy: append-only; overwrite allowed: no. +- Next gate: user confirms design before brief / prompt / image generation. + +## Design Purpose + +本页用于验证：在 P01 的统一深蓝黑 AI 航线作战图底板上，普通内容页是否能读、能讲、能保持会议气质。 + +它不是公共底板的重新设计，而是同一底板下的第一张内容页样片。它要解决的核心问题是： + +> 这场会不是继续动员，而是把方案摊开，形成共同方案。 + +如果 P02 读不清、信息承载不稳、左右对比难成立，可能需要回改内容页规则；如果只是本页文案太多或左右布局比例不对，则只改 P02。 + +## Discussion Summary + +P02 承接 P01 的封面，进入会议定位。用户希望内部会议 PPT 不追求精细排版，但每页必须形成判断、建立气氛。P02 作为内容页样片，应测试“同一视觉底板 + 一页一个判断 + 少量文字模型”的可行性。 + +公共风格仍然不变： + +> 深蓝黑 AI 航线作战图底板，青色 / 金色高亮，雷达、航线、船票、罗盘等母题轻量变化。 + +## Visual Concept + +画面是同一张 AI 航线作战图底板上的“会议定位分岔图”。 + +顶部放主标题： + +> 今天这场会，不是再动员一次 + +画面主体是左右对比： + +- 左侧是暗灰、降噪、低亮度的“不是”区域，像旧航线 / 无效循环 / 已关闭任务； +- 右侧是青色与金色高亮的“是”区域，像当前被激活的行动路线； +- 中间不是普通竖线，而是一条类似航线分界 / 闸门 / 作战地图分割线的发光细线，让它仍然属于统一视觉系统。 + +右侧可以叠加四个发光节点：共识、补充、升级、训练。它们是本页的行动路径。 + +整体第一感觉应该是：今天不是喊口号，而是进入正式协作。 + +## Image Base Requirements + +生成图应该包含： + +- 16:9 横版内容页。 +- 与 P01 同一底板气质：深蓝黑、AI 航线作战图、雷达 / 坐标 / 路线。 +- 左右对比结构。 +- 左侧“不是”低亮度灰色，像被关闭的旧路线。 +- 右侧“是”青色 / 金色高亮，像被激活的新路线。 +- 中间有一条发光分界线或航线闸门。 +- 右侧有“共识 / 补充 / 升级 / 训练”四个发光节点。 +- 背景可以有抽象会议桌俯视线框，但必须很淡，不能变成会议室照片。 + +生成图不需要包含： + +- 真实参会人物； +- 会议桌照片； +- 卡通插画； +- 传统 PPT 白底左右表格； +- 笨重 UI 卡片堆。 + +## Text / Typography Plan + +页面文字建议直接进入图中，但要控制长度。 + +主标题： + +> 今天这场会，不是再动员一次 + +核心判断： + +> 大家已经有意愿，今天要形成共同方案。 + +左侧标题： + +> 不是 + +左侧 4 个短项： + +- 再讲 AI 多重要 +- 再劝要不要参与 +- 我一个人宣布安排 +- 听完就散 + +右侧标题： + +> 是 + +右侧 4 个短项： + +- 摊开完整方案 +- 补充不同角度 +- 必要时升级方案 +- 进入第一周训练 + +底部金句： + +> 不是“我说你们听”，是“我们一起把这件事定下来”。 + +文字优先级： + +1. 主标题； +2. 左右大字“不是 / 是”； +3. 右侧四个行动节点； +4. 核心判断； +5. 底部金句； +6. 左右细项。 + +如果图像模型难以稳定生成全部文字，优先保留：主标题、不是、是、共识、补充、升级、训练。细项可在后续 PPT 层补充或压缩。 + +## Layout / Safe Areas + +建议构图： + +- 顶部 15%-18% 放主标题和一句核心判断。 +- 主体 65%-70% 做左右对比。 +- 底部 10%-12% 放金句。 +- 左侧占 42%-45%，低亮度灰蓝。 +- 右侧占 45%-48%，青色 / 金色更亮。 +- 中间留 4%-6% 给发光分界线、航线闸门或路由分叉。 + +左侧视觉： + +- 灰色旧任务列表； +- 轻微斜线 / 断开的路线； +- 不要出现失败、否定、崩塌的强烈灾难感。 + +右侧视觉： + +- 四个发光节点按从上到下或从左下到右上的路径排列； +- 节点文字为：共识、补充、升级、训练； +- 路线最终指向“第一周训练”。 + +安全区： + +- 左右文字不要贴边； +- 底部金句不要靠近最下缘； +- 中间分界线不要穿过标题； +- 背景雷达线不能干扰正文。 + +## Color Guidance + +整体延续 P01： + +- 深蓝黑底； +- 冷灰蓝结构线； +- 青色路线和节点； +- 金色用于“是”侧的关键节点和底部金句； +- 左侧“不是”使用灰色 / 低饱和蓝灰。 + +对比关系： + +- 左侧不是要“死黑”，而是“已关闭 / 不再走”的低亮状态； +- 右侧是当前激活路线，要更有能量； +- 不要把左侧做得太负面，会议气质应是共识式，不是批判式。 + +## Post-Production Notes + +本页是内容页样片，允许出现轻微文字错漏。但如果左右结构和主判断成立，可以通过后续 PPT 文字层修正细项。 + +如果出现以下情况，属于公共 / 内容系统问题，需要回改 `visual-system` 或 `style-prompt-master`： + +- 同一底板无法承载内容页，文字区域被背景干扰严重； +- 内容页变成普通 UI dashboard； +- 左右对比页与封面风格断裂； +- “共识式会议”气质消失，变成命令式制度页。 + +如果出现以下情况，只改 P02： + +- 左右比例不舒服； +- 细项文字太多； +- 底部金句位置压迫； +- “不是 / 是”的亮度对比不够。 + +## Constraints / Avoid + +必须避免： + +- 白底咨询公司左右表格； +- 大量卡片堆叠； +- 真实会议室照片； +- 领导讲话台； +- 命令式制度宣贯； +- 错把“不是”做成攻击或批判； +- 右侧节点像项目管理软件； +- 文字密度过高导致全页不可读； +- 过亮 cyberpunk 分割线破坏商务感。 + +## Confirmation Gate + +请检查： + +1. P02 是否能作为内容页样片； +2. “不是 / 是”的左右对比是否符合你的会议气质； +3. 右侧是否保留“共识 / 补充 / 升级 / 训练”四个节点； +4. 底部金句是否保留，还是压缩为更短版本； +5. 如果 P01 通过后，P02 是否可以直接进入 brief / prompt / 生成。 + +确认后再进入 `s02-v1-brief.md`、`s02-v1-prompt.md` 和内容页样片生成。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-prompt.md new file mode 100644 index 0000000..69daa86 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s02/s02-v1-prompt.md @@ -0,0 +1,86 @@ +# S-02 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s02-v1-brief.md` +- Review mode: none. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P02 / S-02. +- Page family: A / Opening / Consensus. +- Active style module: `visual-system/style/style-prompt-master.md`, Module A. +- Core motifs: AI 航线, route split, activated nodes, operation-map grid. +- Actual image references: none. +- Reference note: no public visual reference image exists for this project yet; use the accepted text visual-system as the style authority. +- Main title: `今天这场会，不是再动员一次` +- Core judgment: `大家已经有意愿，今天要形成共同方案。` +- Text complexity: medium. +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Use built-in host image generation directly. +- No child session, no review file, no completeness gate. + +## Advisor / Host-Native Record + +Mode: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false +} +``` + +## Final Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page content slide image for an internal PowerPoint kickoff meeting + +Create a 16:9 full-page visual slide image in the same unified style as a deep navy-black AI maritime operation map. This is the first content page after the cover. It should explain meeting positioning: this meeting is not another mobilization; it is a collaborative session to form a shared plan. + +Scene/backdrop: deep blue-black executive AI route-map base, subtle coordinate grid, radar scan rings, compass/navigation marks, faint abstract top-down meeting-table linework as background only. Keep the same visual base as the cover: disciplined internal AI route / war-map atmosphere, not a white consulting slide and not a SaaS dashboard. + +Main layout: clear left-right comparison structure. +- Left side: low-light gray-blue deactivated route area labeled "不是". It should feel like a closed old route or inactive task list, not a harsh criticism. +- Right side: active cyan and restrained gold route area labeled "是". It should feel like the chosen active route. +- Center: a thin glowing vertical route divider / checkpoint / routing gate, integrated into the maritime operation map. +- Right side should include four glowing action nodes connected by a subtle route path: "共识", "补充", "升级", "训练". + +Text (verbatim Chinese, prioritize readability): +- Main title at top, large: "今天这场会，不是再动员一次" +- Core judgment near title, smaller: "大家已经有意愿，今天要形成共同方案" +- Left heading: "不是" +- Left short items: "再讲 AI 多重要", "再劝要不要参与", "我一个人宣布安排", "听完就散" +- Right heading: "是" +- Right short items: "摊开完整方案", "补充不同角度", "必要时升级方案", "进入第一周训练" +- Footer quote, optional if space allows: "不是“我说你们听”，是“我们一起把这件事定下来”" + +Typography: modern Chinese sans-serif, high contrast, large title, clear headings. Use short labels and avoid tiny text. If not all text can fit cleanly, prioritize the main title, the headings "不是" and "是", and the four nodes "共识 / 补充 / 升级 / 训练". + +Composition/framing: top 15-18% for title and core judgment, middle 65-70% for comparison, bottom 10-12% for footer quote. Left block about 43% width, right block about 47% width, center divider about 5%. Keep safe margins, avoid text touching edges, and do not let background radar lines interfere with text. + +Lighting/mood: consensus-building, pragmatic, energetic but not loud. The right side should feel active and hopeful; the left side muted but not hostile. + +Color palette: same deep navy-black base, muted slate gray-blue on the left, active cyan route and restrained warm gold highlights on the right, pale-blue/white text. + +Constraints: no real people, no meeting-room photo, no leader podium, no government policy page, no command-style discipline board, no ordinary dashboard UI, no white consulting table, no excessive cards, no cyberpunk neon split line, no cartoon illustration, no humanoid robots, no logo, no watermark. + +## Negative / Avoid + +Avoid making the page look like a project-management app, a customer proposal, a government report, or a dense training manual. Avoid making the "不是" side feel accusatory or negative beyond a muted inactive route. + +## Output Intent + +Generate `s02-v1-image.png` as the first content-page sample candidate. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-brief.md new file mode 100644 index 0000000..3d75078 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-brief.md @@ -0,0 +1,12 @@ +# s03-v1 Brief + +- Slide: s03 / P03 +- Title: 我们要建的，不是传统销售团队 +- Core judgment: 我们要建的是 AI 智能化客户经营团队。 +- Visual model: radar-centered team identity map. +- Required text: title, central team name, five short capability labels, one bottom sentence. +- Style base: accepted deep navy-black AI route operation map with cyan radar signals and gold emphasis. +- Motifs: radar, route map, collaboration nodes. +- Avoid: traditional sales proposal look, customer-facing SaaS dashboard, cartoon ship, humanoid robots, concrete attendee portraits. +- Output target: `projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-image.png` +- Review mode: none. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-design.md new file mode 100644 index 0000000..5f1d946 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-design.md @@ -0,0 +1,28 @@ +# s03-v1 Design + +## 页面 + +P03：我们要建的，不是传统销售团队 + +## 设计目标 + +把团队身份从“传统销售”切换成“AI 智能化客户经营团队”。画面要让观众一眼看到：中心不是卖货岗位，而是一个在雷达中心识别客户、经营关系、管理预期、发现机会、推动合作的新型前端团队。 + +## 画面概念 + +使用统一深蓝黑 AI 航线作战图底板。中心是发光雷达盘，核心文字为“AI 智能化客户经营团队”。外圈五个能力点围成雷达环：识别客户、经营关系、管理预期、发现机会、推动合作。最外圈用四个较小协作节点表示客户、专家、AI 业务工程师、工程团队。 + +## 文案布局 + +- 顶部大标题：我们要建的，不是传统销售团队 +- 中央主词：AI 智能化客户经营团队 +- 外圈短标签：识别客户 / 经营关系 / 管理预期 / 发现机会 / 推动合作 +- 底部短句：不是卖课、卖软件、卖项目，而是经营客户智能化旅程 + +## 视觉要求 + +延续 s01/s02 的深海航线地图、青色雷达线、金色重点标签、白色大标题。页面保持信息图感，不画真实人物，不做 SaaS 仪表盘，不做可爱船插画。 + +## 后期提示 + +如果生成文字有轻微瑕疵，可在 PPT 中覆盖标题和底部短句；核心视觉必须保留“雷达中心团队身份”。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-prompt.md new file mode 100644 index 0000000..2579287 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-prompt.md @@ -0,0 +1,40 @@ +# s03-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: + - `AGENTS.md` + - `projects/2026-06-29-搭上AI这条船/handoff/2026-06-29-ai-ship-formal-production-handoff.md` + - `projects/2026-06-29-搭上AI这条船/project.md` + - `projects/2026-06-29-搭上AI这条船/execution-plan.md` + - `projects/2026-06-29-搭上AI这条船/slides/slides.md` + - `projects/2026-06-29-搭上AI这条船/visual-system/visual-system.md` + - `projects/2026-06-29-搭上AI这条船/visual-system/style/style-prompt-master.md` + - `projects/2026-06-29-搭上AI这条船/visual-system/motifs/motif-registry.md` + - `projects/2026-06-29-搭上AI这条船/intake/阶段5：P1-P24 单页设计骨架.md` + - `projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/task-plan.md` + - `projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/production-run-status.md` +- Visual calibration references loaded: + - Image 1: accepted cover style sample, `slides/s01/s01-v1-image.png` + - Image 2: accepted content-page style sample, `slides/s02/s02-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual, matching the accepted samples: deep navy-black AI route operation map, subtle ocean/chart texture, thin grid lines, compass/radar overlays, cyan route glow, gold accent points, crisp white Chinese title typography. Use Image 1 for the overall deep route-map atmosphere and Image 2 for the content-page layout density and text hierarchy. + +Page title at top: “我们要建的，不是传统销售团队”. + +Centerpiece: a large glowing cyan radar disk in the middle of the slide. In the radar center, place the main phrase in bold readable Chinese: “AI 智能化客户经营团队”. Around the radar ring, place five short capability labels as compact chips or orbit nodes: “识别客户”, “经营关系”, “管理预期”, “发现机会”, “推动合作”. On the outer ring, add four smaller collaboration nodes labeled “客户”, “专家”, “AI业务工程师”, “工程团队”, connected by fine cyan lines. + +Bottom sentence, smaller but readable: “不是卖课、卖软件、卖项目，而是经营客户智能化旅程”. + +Visual mood: confident, operational, internal route-map briefing. Keep it elegant and cinematic, not a government report, not a customer proposal, not a SaaS dashboard. No humanoid robots, no cartoon ship, no real people or portraits. Use only one title, one central judgment, short labels, and clean information hierarchy. Minor Chinese text imperfections are acceptable, but make the text as legible as possible. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-brief.md new file mode 100644 index 0000000..b5d5756 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-brief.md @@ -0,0 +1,12 @@ +# s04-v1 Brief + +- Slide: s04 / P04 +- Title: 为什么现在必须变 +- Core judgment: 旧船越来越难跑，新船已经靠岸。 +- Visual model: old route pressure versus new AI route. +- Required text: title, three short labels, one bottom judgment. +- Style base: accepted deep navy-black AI route operation map with cyan/gold signals. +- Motifs: old dock, new route, lighthouse, turning point. +- Avoid: macroeconomic report, gloomy disaster page, customer proposal, cyberpunk poster, cartoon ship. +- Output target: `projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-image.png` +- Review mode: none. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-design.md new file mode 100644 index 0000000..e63cf31 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-design.md @@ -0,0 +1,29 @@ +# s04-v1 Design + +## 页面 + +P04：为什么现在必须变 + +## 设计目标 + +建立现实压力，但不制造悲观。画面要表达“旧船越来越难跑，新船已经靠岸”：左侧旧行业航线变暗、下降，右侧 AI 新航线被点亮，中间出现必须转向的节点。 + +## 画面概念 + +统一深蓝黑航线作战图底板。左右对比结构：左侧是暗色旧码头、下降曲线、灰蓝航道；右侧是亮起的 AI 航线、远方灯塔、金色靠岸信号。中间用一个“转向点 / 航向切换”符号连接两侧。 + +## 文案布局 + +- 顶部大标题：为什么现在必须变 +- 左侧短句：旧行业下滑 +- 中间短句：转向点 +- 右侧短句：AI 新入口 +- 底部金句：旧船越来越难跑，新船已经靠岸 + +## 视觉要求 + +整体有压力与转机，不做宏观趋势报告。左侧低亮度但不脏，右侧青色路径和金色灯塔作为希望点。保留航线图、雷达和指南针语言。 + +## 后期提示 + +底部金句是本页核心；若图中文字不稳，优先覆盖底部金句和右侧“AI 新入口”。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-prompt.md new file mode 100644 index 0000000..85934ac --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-prompt.md @@ -0,0 +1,29 @@ +# s04-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P04 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted cover style sample, `slides/s01/s01-v1-image.png` + - Image 2: accepted content-page style sample, `slides/s02/s02-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual in the same style as the accepted samples: deep navy-black maritime AI operation chart, subtle ocean route map, compass grid, radar sweeps, cyan route glow, restrained gold emphasis, large crisp white Chinese typography. + +Page title at top: “为什么现在必须变”. + +Layout: left-right contrast with a central turning point. Left side: dim old dock / old route zone, a muted downward line, low blue-gray signal, label “旧行业下滑”. Right side: bright cyan AI route opening toward a warm gold lighthouse, label “AI 新入口”. Center: a clear navigation pivot marker labeled “转向点”, with route line bending from old path to new path. + +Bottom core judgment in one strong line: “旧船越来越难跑，新船已经靠岸”. + +Tone: pressure plus opportunity, grounded in real business anxiety but not pessimistic. It should feel like an internal route-map briefing, not a macro trend report. Avoid government report style, customer proposal style, SaaS dashboard UI, cyberpunk poster, cute ship cartoon, robots, and real people. Keep text short and legible. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-brief.md new file mode 100644 index 0000000..e8852c3 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-brief.md @@ -0,0 +1,12 @@ +# s05-v1 Brief + +- Slide: s05 / P05 +- Title: 我这半年打通了什么 +- Core judgment: 产品力、方法论、训练路径，已经准备到可以开局。 +- Visual model: ship deck capability base with three pillars. +- Required text: title, three labels, one bottom sentence. +- Style base: deep navy-black AI route operation map, cyan/gold signal hierarchy. +- Motifs: route map, ship deck structure, capability pillars. +- Avoid: personal resume, trophy wall, customer proposal, cartoon ship, humanoid robots. +- Output target: `projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-image.png` +- Review mode: none. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-design.md new file mode 100644 index 0000000..e224034 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-design.md @@ -0,0 +1,31 @@ +# s05-v1 Design + +## 页面 + +P05：我这半年打通了什么 + +## 设计目标 + +建立“强哥已经准备好带大家开局”的可信度，但避免个人履历炫耀。画面表达三项底座已经成型：产品力、方法论、训练路径。 + +## 画面概念 + +统一深蓝黑航线作战图底板。底部是一条抽象船体 / 甲板结构图，不画卡通船。甲板上竖起三根发光桅杆或三座能力塔，分别标注“产品力”“方法论”“训练路径”。三根桅杆向上连接到同一条 AI 航线，表示已经可以开局。 + +## 文案布局 + +- 顶部大标题：我这半年打通了什么 +- 三列主标签：产品力 / 方法论 / 训练路径 +- 每列一句短解释： + - 三级路径 + - 判断框架 + - 销售老兵训练法 +- 底部短句：路径终于想清楚了 + +## 视觉要求 + +金色用于“已经准备好”的可信节点，青色用于连接航线和结构线。整页要像能力底座图，不像个人荣誉墙。 + +## 后期提示 + +保留三列结构即可；详细解释可在 PPT 层补字。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-prompt.md new file mode 100644 index 0000000..efc6fbb --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-prompt.md @@ -0,0 +1,29 @@ +# s05-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P05 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted cover style sample, `slides/s01/s01-v1-image.png` + - Image 2: accepted content-page style sample, `slides/s02/s02-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT visual. Match the accepted samples: deep navy-black AI maritime operation chart, subtle ocean map texture, compass/radar overlays, cyan glowing route lines, restrained gold accents, crisp white Chinese type, cinematic but businesslike. + +Page title at top: “我这半年打通了什么”. + +Main visual: an abstract ship deck / structural base diagram along the lower third, not a cartoon ship. On the deck stand three luminous capability pillars or mast-like towers, evenly spaced, connected upward into one cyan AI route line. Label the three pillars clearly: “产品力”, “方法论”, “训练路径”. Under each, use one short small label: “三级路径”, “判断框架”, “训练方法”. + +Bottom sentence: “路径终于想清楚了，可以开局”. + +Make the page feel like readiness and structured preparation, not personal bragging. Use gold highlights for readiness nodes and cyan for route/connection lines. Avoid resume-like visuals, trophy imagery, government report style, SaaS dashboard UI, cute ship cartoon, robots, and real people. Keep text short and legible. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-brief.md new file mode 100644 index 0000000..e05ae68 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-brief.md @@ -0,0 +1,12 @@ +# s06-v1 Brief + +- Slide: s06 / P06 +- Title: 我的角色已经变了 +- Core judgment: 我不能再长期同时承担所有角色。 +- Visual model: overloaded center node to expert network node. +- Required text: title, left old role, right new role, four short expert functions, bottom sentence. +- Style base: deep navy-black AI route operation map with cyan/gold signals. +- Motifs: pressure node, network map, role transition arrow. +- Avoid: real portrait, boss biography, blame-shifting tone, customer proposal, SaaS dashboard, robots. +- Output target: `projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-image.png` +- Review mode: none. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-design.md new file mode 100644 index 0000000..89e1c2d --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-design.md @@ -0,0 +1,29 @@ +# s06-v1 Design + +## 页面 + +P06：我的角色已经变了 + +## 设计目标 + +说明强哥角色从“全能型老板”转向“学者型实践专家 / 方法论与判断节点”。观众应理解这是体系升级，不是退出前线或甩锅。 + +## 画面概念 + +统一深蓝黑作战图底板。左右转型结构：左侧是一个高压中心节点，周围堆叠多个旧标签；右侧是一个更稳的专家节点，连接客户经营团队、AI 业务工程师、工程底座等多个节点。中间用青色箭头表示角色换位。 + +## 文案布局 + +- 顶部大标题：我的角色已经变了 +- 左侧标签：全能型老板 +- 右侧标签：学者型实践专家 +- 右侧短标签：方法论 / 认知引导 / 场景判断 / 质量把关 +- 底部短句：我不是退出前线，而是换到更该站的位置 + +## 视觉要求 + +不使用人物肖像。用节点、网络、压力环和航线表达角色变化。左侧压力感，右侧秩序感。 + +## 后期提示 + +如果需要 PPT 层补充旧角色长列表，放在左侧灰色标签区；生成图只保留短标签。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-prompt.md new file mode 100644 index 0000000..ab80150 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-prompt.md @@ -0,0 +1,29 @@ +# s06-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P06 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted cover style sample, `slides/s01/s01-v1-image.png` + - Image 2: accepted content-page style sample, `slides/s02/s02-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual, matching the accepted samples: deep navy-black AI route operation map, compass grid, radar sweep lines, cyan route glow, gold emphasis, crisp white Chinese typography. + +Page title at top: “我的角色已经变了”. + +Layout: left-to-right transformation. Left side: a single overloaded glowing node under pressure rings, labeled “全能型老板”, surrounded by small muted tags like “专家”, “商务”, “销售”, “方案”, “谈判”, “把关”. Right side: a stable expert node connected to several team nodes, labeled “学者型实践专家”. Around it place four short function labels: “方法论”, “认知引导”, “场景判断”, “质量把关”. Center: a clean cyan transition arrow or route switch from left to right. + +Bottom sentence: “我不是退出前线，而是换到更该站的位置”. + +Mood: system upgrade, calm authority, clear role repositioning. No human portraits, no realistic boss figure, no blame tone. Avoid customer proposal style, SaaS dashboard UI, government report, robots, cyberpunk poster, cartoon ship. Keep all Chinese text short and as legible as possible. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-brief.md new file mode 100644 index 0000000..90670b0 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-brief.md @@ -0,0 +1,12 @@ +# s07-v1 Brief + +- Slide: s07 / P07 +- Title: 过去靠我一个人顶，未来靠体系一起跑 +- Core judgment: 个人驱动必须升级为团队驱动。 +- Visual model: single engine to multi-engine system. +- Required text: title, past/future labels, four future keywords, bottom judgment. +- Style base: deep navy-black AI route operation map, cyan/gold signal hierarchy. +- Motifs: route map, single engine, multi-node fleet, distributed propulsion. +- Avoid: complaint tone, cute ship, real people, customer proposal, SaaS dashboard, robots. +- Output target: `projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-image.png` +- Review mode: none. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-design.md new file mode 100644 index 0000000..549dfc0 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-design.md @@ -0,0 +1,29 @@ +# s07-v1 Design + +## 页面 + +P07：过去靠我一个人顶，未来靠体系一起跑 + +## 设计目标 + +从个人角色变化自然过渡到团队建设。画面要表达个人驱动升级为团队驱动：过去一个中心发动机承压，未来多节点协同推进。 + +## 画面概念 + +统一深蓝黑航线作战图底板。上下结构：上半部分是单引擎小船 / 单中心推进节点，周围有风险和压力标记；下半部分是多引擎船队或多节点协同网络，几条青色航线一起向前。整体像作战路线升级图，不画可爱船。 + +## 文案布局 + +- 顶部大标题：过去靠我一个人顶，未来靠体系一起跑 +- 上半标签：过去：个人驱动 +- 下半标签：未来：团队驱动 +- 下方关键词：团队分工 / AI 工具 / 客户经营 / 流程机制 +- 底部金句：个人驱动必须升级为团队驱动 + +## 视觉要求 + +上半压力低亮，下半协同高亮。表达“体系才能跑得远”，不是抱怨个人太累。 + +## 后期提示 + +长列表不进入生成图；必要时在 PPT 旁白讲。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-prompt.md new file mode 100644 index 0000000..9c17f94 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-prompt.md @@ -0,0 +1,29 @@ +# s07-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P07 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted cover style sample, `slides/s01/s01-v1-image.png` + - Image 2: accepted content-page style sample, `slides/s02/s02-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT visual. Match the accepted samples: deep navy-black AI route operation chart, subtle maritime map texture, compass/radar overlays, cyan glowing route paths, gold key nodes, large white Chinese title, crisp diagram labels. + +Page title at top: “过去靠我一个人顶，未来靠体系一起跑”. + +Layout: upper half and lower half. Upper half: a single overloaded propulsion node / small abstract vessel icon, muted blue-gray, labeled “过去：个人驱动”, with pressure rings and several small dim tags. Lower half: a brighter distributed system, multiple engine nodes / small fleet route nodes connected by cyan lines, labeled “未来：团队驱动”. Add four compact labels near the future network: “团队分工”, “AI工具”, “客户经营”, “流程机制”. + +Bottom core judgment: “个人驱动必须升级为团队驱动”. + +Mood: organizational upgrade, confidence, not exhaustion or complaint. It should feel like an internal operation map. Avoid customer proposal style, SaaS dashboard, government report, cute cartoon ship, humanoid robots, real people. Keep text short and legible. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-brief.md new file mode 100644 index 0000000..834a9c7 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-brief.md @@ -0,0 +1,12 @@ +# s08-v1 Brief + +- Slide: s08 / P08 +- Title: 为什么不是传统销售 +- Core judgment: 这件事不是把 AI 卖出去，而是把客户带上正确路径。 +- Visual model: traditional sales funnel versus AI customer journey route. +- Required text: title, two side headers, short labels, bottom sentence. +- Style base: deep navy-black AI route operation map with cyan/gold signals. +- Motifs: funnel, route line, lighthouse, boundary markers. +- Avoid: insulting traditional sales, SaaS dashboard, customer proposal, cartoon ship, robots, portraits. +- Output target: `projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-image.png` +- Review mode: none. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-design.md new file mode 100644 index 0000000..e5307da --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-design.md @@ -0,0 +1,28 @@ +# s08-v1 Design + +## 页面 + +P08：为什么不是传统销售 + +## 设计目标 + +重定义销售工作：传统销售能力仍然有用，但 AI 项目要升级为客户经营和路径推进。画面不能贬低传统销售，而是表达“发动机换了”。 + +## 画面概念 + +统一深蓝黑航线作战图底板。左右对比：左侧是传统成交漏斗，短标签为找客户、讲产品、谈价格、促成交、追回款；右侧是客户旅程航线，短标签为看懂客户、判断基础、识别场景、管理预期、推进路径、保护边界。右侧航线更亮，连接到远方 AI 灯塔。 + +## 文案布局 + +- 顶部大标题：为什么不是传统销售 +- 左侧标题：传统销售 +- 右侧标题：AI 客户经营 +- 底部短句：不是卖东西，是经营客户的智能化旅程 + +## 视觉要求 + +左侧不要做成失败或落后，只是“旧打法”；右侧体现升级后的路径感。青色用于新旅程，金色用于边界与关键判断。 + +## 后期提示 + +如果生成图左右文字不够稳定，可在 PPT 中重做标签；关键是漏斗 vs 航线结构。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-prompt.md new file mode 100644 index 0000000..a62f29c --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-prompt.md @@ -0,0 +1,29 @@ +# s08-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P08 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted cover style sample, `slides/s01/s01-v1-image.png` + - Image 2: accepted content-page style sample, `slides/s02/s02-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual, same accepted style: deep navy-black AI operation route map, subtle ocean chart texture, compass/radar elements, cyan route glow, gold accent nodes, crisp white Chinese headings. + +Page title at top: “为什么不是传统销售”. + +Layout: respectful left-right comparison. Left side: a muted but clean sales funnel labeled “传统销售”, with short stacked labels: “找客户”, “讲产品”, “谈价格”, “促成交”, “追回款”. Right side: a brighter customer journey route map labeled “AI 客户经营”, with route nodes labeled: “看懂客户”, “判断基础”, “识别场景”, “管理预期”, “推进路径”, “保护边界”. The right route leads toward a small gold lighthouse / AI route marker. + +Bottom sentence: “不是卖东西，是经营客户的智能化旅程”. + +The page must say “upgrade”, not “old sales are useless”. Keep the left side dignified, right side more future-facing. Avoid customer proposal style, SaaS dashboard UI, government report, cartoon ship, robots, real people. Use short readable Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-brief.md new file mode 100644 index 0000000..5eb0e78 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-brief.md @@ -0,0 +1,12 @@ +# s09-v1 Brief + +- Slide: s09 / P09 +- Title: 为什么这次找你们 +- Core judgment: AI 客户经营第一阶段，最重要的是识人、识局、识势。 +- Visual model: radar-scanned customer organization plus three-ability triangle. +- Required text: title, three large words, short labels, bottom sentence. +- Style base: deep navy-black AI route operation map with cyan/gold signals. +- Motifs: radar, customer organization nodes, boarding opportunity signal. +- Avoid: training lecture page, portraits, cartoon ship, robots, customer proposal, SaaS dashboard. +- Output target: `projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-image.png` +- Review mode: none. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-design.md new file mode 100644 index 0000000..34706ba --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-design.md @@ -0,0 +1,31 @@ +# s09-v1 Design + +## 页面 + +P09：为什么这次找你们 + +## 设计目标 + +建立参会者信心。观众要感到自己被需要，不是因为懂技术，而是因为懂人、懂局、懂客户。核心三词：识人、识局、识势。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。中心是客户组织雷达扫描盘，雷达上有不同颜色的小节点表示决策者、推动者、阻力者、旁观者。三角模型托起三项能力：识人、识局、识势。底座写“多年客户经验 / 社会经验 / 谈判经验”。 + +## 文案布局 + +- 顶部大标题：为什么这次找你们 +- 三个大词：识人 / 识局 / 识势 +- 每个词一句短解释： + - 真决策者 + - 推动与阻力 + - 真需求与看热闹 +- 底部金句：老销售的能力没有过时，只是换了发动机 + +## 视觉要求 + +这页要让人抬头，有尊重感。不要做培训说教页，不要把人画成头像。用雷达和组织节点表示经验的价值。 + +## 后期提示 + +如文字不稳，优先保留三个大词和底部金句。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-prompt.md new file mode 100644 index 0000000..92372be --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-prompt.md @@ -0,0 +1,29 @@ +# s09-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P09 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted cover style sample, `slides/s01/s01-v1-image.png` + - Image 2: accepted content-page style sample, `slides/s02/s02-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual. Match the accepted samples: deep navy-black AI maritime route operation map, compass/radar grid, subtle ocean chart, cyan signal lines, gold highlights, large readable white Chinese title. + +Page title at top: “为什么这次找你们”. + +Main visual: a customer-organization radar scan. Center or middle-right contains a glowing radar disk with small colored nodes representing roles in a customer organization: “决策者”, “推动者”, “阻力者”, “旁观者”. Over or beside the radar, build a clear three-point triangle model with three large gold/cyan words: “识人”, “识局”, “识势”. Under each word add a very short label: “真决策者”, “推动与阻力”, “真需求”. + +Bottom sentence: “老销售的能力没有过时，只是换了发动机”. + +Mood: respect, confidence, invitation into the AI era. It should make experienced salespeople feel newly valuable. Avoid training lecture look, government report, customer proposal, SaaS dashboard, cute ship cartoon, robots, real portraits or attendee faces. Use short, legible Chinese labels; one title, one core judgment, no long paragraphs. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-brief.md new file mode 100644 index 0000000..6577439 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-brief.md @@ -0,0 +1,32 @@ +# s10-v1 Brief + +## Page + +- Unit: s10 +- Source page: P10 +- Title: Agentic 技术平权：外行也能上船 +- Page family: Confidence / Agentic Entry +- Version: v1 + +## Core Conclusion + +技术平权，不是人人都当程序员，而是外行也能参与探索。 + +## Objective + +让参会者相信，AI Agentic 阶段的第一步不是写代码，而是用业务理解、自然语言和任务拆解进入探索轨。 + +## Visual Model + +登船坡道替代信息化高墙。左侧高墙代表代码、系统、数据库门槛；右侧坡道代表业务理解、自然语言、任务拆解。坡道连接船票和 AI 航线。 + +## Text Strategy + +- One title. +- One central judgment. +- Three short labels. +- Avoid long explanatory sentences. + +## Continuity + +Use the accepted deep navy-black AI route operation-map base with cyan route glow and restrained gold highlights. Motif: 登船坡道 + 船票. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-design.md new file mode 100644 index 0000000..022f6e5 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-design.md @@ -0,0 +1,28 @@ +# s10-v1 Design + +## 页面 + +P10：Agentic 技术平权：外行也能上船 + +## 设计目标 + +建立信心核心：这不是要求销售老兵变成程序员，而是让他们相信自己可以先进入 AI 探索轨。页面要把“技术门槛下降、业务理解上升”讲清楚。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。左侧是过去的信息化高墙，墙上有代码、系统、数据库的冷色符号；右侧是一条发光登船坡道，业务理解、自然语言、任务拆解三个节点沿坡道上船。坡道通向金色船票和远方 AI 航线。 + +## 文案布局 + +- 顶部标题：Agentic 技术平权：外行也能上船 +- 中心判断：不懂代码，不等于不能做 AI +- 三个短标签：业务理解 / 自然语言 / 任务拆解 +- 轻量对比：过去高墙 / 现在坡道 + +## 视觉要求 + +要给销售信心，不要讲成技术判断课。避免代码崇拜、程序员英雄、机器人老师。画面重点是“坡道降低门槛”，不是“技术不重要”。 + +## 后期提示 + +如果文字不稳，优先保留标题、中心判断和三个坡道标签。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-prompt.md new file mode 100644 index 0000000..c3c7c72 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-prompt.md @@ -0,0 +1,30 @@ +# s10-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P10 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted previous package radar/style sample, `slides/s09/s09-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual. Match the accepted samples: deep navy-black AI maritime route operation map, subtle ocean chart texture, compass/radar geometry, cyan signal lines, restrained gold highlights, large readable white Chinese title. + +Page title at top: “Agentic 技术平权：外行也能上船”. + +Main visual: left side shows an old high technical wall labeled “过去高墙”, with small muted symbols for “代码”, “系统”, “数据库”. Right side shows a bright cyan-gold boarding ramp replacing the wall, leading toward a glowing abstract AI route and a gold-edged boarding ticket. On the ramp place three clear labels: “业务理解”, “自然语言”, “任务拆解”. + +Center judgment in large readable text: “不懂代码，不等于不能做 AI”. + +Mood: confidence for experienced business people entering AI exploration. The page must communicate lowered entry barrier, not anti-technology. Avoid programmer worship, code walls as hero, robot teacher, customer proposal style, SaaS dashboard UI, government report, cartoon ship, real people or portraits. Use short, legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-brief.md new file mode 100644 index 0000000..5889966 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-brief.md @@ -0,0 +1,32 @@ +# s11-v1 Brief + +## Page + +- Unit: s11 +- Source page: P11 +- Title: 传统软件工程师和 Agentic 工程师，是两个物种 +- Page family: Confidence / Agentic Entry +- Version: v1 + +## Core Conclusion + +这不是技术栈升级，而是能力系统变化。 + +## Objective + +解释为什么客户 AI 价值探索不只是传统软件工程问题，并继续把销售老兵拉进探索前场。 + +## Visual Model + +左右对比：确定性工程蓝图 vs 不确定性探索地图。中间是“能力系统变化”的分界线。 + +## Text Strategy + +- One long title. +- Two side labels. +- One fairness sentence. +- One bottom judgment. + +## Continuity + +Use the accepted deep navy-black AI route operation-map base with cyan and gold signal accents. Motif: capability-system contrast inside the Agentic entry family. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-design.md new file mode 100644 index 0000000..33a92f1 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-design.md @@ -0,0 +1,29 @@ +# s11-v1 Design + +## 页面 + +P11：传统软件工程师和 Agentic 工程师，是两个物种 + +## 设计目标 + +强化反直觉判断：这不是技术栈升级，而是能力系统变化。页面必须服务“你们有机会进入前场”，不能变成贬低技术团队。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。左右对比：左侧是稳定工程管线、接口、数据库和蓝图；右侧是探索地图、任务网络、智能体链路。中间用一道发光分界线写“能力系统变化”。 + +## 文案布局 + +- 顶部标题：传统软件工程师和 Agentic 工程师，是两个物种 +- 左侧标题：传统软件工程师 +- 右侧标题：Agentic 工程师 +- 中心短句：不是谁高级谁低级，是两种不同能力系统 +- 底部判断：一个做稳确定需求，一个探索模糊问题 + +## 视觉要求 + +左右都要专业、克制、有价值感。左侧稳定，右侧探索。不要做成人物对立、职业嘲讽或工程架构课。 + +## 后期提示 + +如文字不稳，保留左右标题、中心短句和底部判断。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-prompt.md new file mode 100644 index 0000000..e104519 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-prompt.md @@ -0,0 +1,32 @@ +# s11-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P11 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted previous package radar/style sample, `slides/s09/s09-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual in the accepted style: deep navy-black AI maritime operation map, compass grid, cyan signal glow, restrained gold accents, crisp large Chinese typography. + +Page title at top: “传统软件工程师和 Agentic 工程师，是两个物种”. + +Layout: professional left-right contrast, not hostile. Left side label: “传统软件工程师”, visualized as stable engineering blueprint, pipes, API nodes, database blocks, test checkmarks, with short labels “确定需求”, “写代码”, “做系统”. Right side label: “Agentic 工程师”, visualized as exploration map, fuzzy target becoming task chain, AI agent nodes, validation loops, with short labels “理解目标”, “拆任务”, “验输出”. + +Center divider phrase in gold/cyan: “不是谁高级谁低级，是两种不同能力系统”. + +Bottom sentence: “一个做稳确定需求，一个探索模糊问题”. + +Keep both sides credible and useful. Avoid mocking programmers, dense architecture lecture, SaaS dashboard, customer proposal, government report, robots, real portraits, cartoon style. Use short readable Chinese only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-brief.md new file mode 100644 index 0000000..004a6b4 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-brief.md @@ -0,0 +1,32 @@ +# s12-v1 Brief + +## Page + +- Unit: s12 +- Source page: P12 +- Title: 第一阶段要求：不是懂 AI，而是会带着 AI 工作 +- Page family: Confidence / Agentic Entry +- Version: v1 + +## Core Conclusion + +先会用，再会卖，再会带客户用。 + +## Objective + +把“学 AI”的压力转成“带着 AI 工作”的第一阶段行动习惯。 + +## Visual Model + +四节点 AI 工作闭环：会前准备 -> 现场观察 -> 会后复盘 -> 下一步行动。 + +## Text Strategy + +- One title. +- One central judgment. +- Four loop labels. +- One bottom action sentence. + +## Continuity + +Use the accepted deep navy-black AI route operation-map base with radar glow, route lines, cyan loop, and gold central judgment. Motif: 登船坡道 / AI work-loop route. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-design.md new file mode 100644 index 0000000..acd296d --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-design.md @@ -0,0 +1,28 @@ +# s12-v1 Design + +## 页面 + +P12：第一阶段要求：不是懂 AI，而是会带着 AI 工作 + +## 设计目标 + +降低进入门槛，让观众觉得今天晚上就能开始。核心是形成 AI 工作习惯，而不是先学半年原理。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。中心是一个发光闭环：会前准备、现场观察、会后复盘、下一步行动。闭环外层有雷达扫描和客户画像卡片，表示 AI 帮助销售在真实客户经营中形成循环。 + +## 文案布局 + +- 顶部标题：第一阶段要求：不是懂 AI，而是会带着 AI 工作 +- 中心金句：先会用，再会卖，再会带客户用 +- 四个闭环节点：会前准备 / 现场观察 / 会后复盘 / 下一步行动 +- 底部短句：把 AI 用到自己身上，才有资格带客户上船 + +## 视觉要求 + +要有行动感和可开始感，不要像课程大纲。节点必须清楚，文本少。 + +## 后期提示 + +如文字不稳，优先保留四个闭环节点和中心金句。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-prompt.md new file mode 100644 index 0000000..ce27d22 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-prompt.md @@ -0,0 +1,32 @@ +# s12-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P12 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted previous package radar/style sample, `slides/s09/s09-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual. Keep the same accepted deep navy-black AI route operation-map base, ocean chart lines, compass marks, cyan signal light, restrained gold emphasis, readable Chinese text. + +Page title at top: “第一阶段要求：不是懂 AI，而是会带着 AI 工作”. + +Main visual: a clean glowing circular work-loop diagram over a radar-map background. Four nodes around the loop: “会前准备”, “现场观察”, “会后复盘”, “下一步行动”. Add subtle customer-profile cards and radar scan marks around the loop, not as a SaaS dashboard but as maritime operation-map annotations. + +Center judgment: “先会用，再会卖，再会带客户用”. + +Bottom sentence: “把 AI 用到自己身上，才有资格带客户上船”. + +Mood: immediately actionable, low entry barrier, confident. Avoid course syllabus, training manual, dense text, robot teacher, generic software UI, customer proposal, government report, real people or portraits. Use short, legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-brief.md new file mode 100644 index 0000000..0204f50 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-brief.md @@ -0,0 +1,31 @@ +# s13-v1 Brief + +## Page + +- Unit: s13 +- Source page: P13 +- Title: 我们卖的不是 AI 产品，是一条企业智能化路径 +- Page family: Business Path / Customer Judgment +- Version: v1 + +## Core Conclusion + +客户真正需要的，是从想用 AI 到用好 AI 的路径。 + +## Objective + +把团队要卖的东西从“课程 / 软件 / 系统”重新定义为企业智能化路径。 + +## Visual Model + +航线节点地图：想用 AI -> 看懂 AI -> 找到场景 -> 形成方案 -> 试点验证 -> 系统落地 -> 用好 AI。 + +## Text Strategy + +- One title. +- Route node labels. +- One bottom value sentence. + +## Continuity + +Use the accepted deep navy-black AI route operation-map base with cyan route and gold destination markers. Motif: AI 航线 / 港口 / 灯塔. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-design.md new file mode 100644 index 0000000..9164e39 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-design.md @@ -0,0 +1,27 @@ +# s13-v1 Design + +## 页面 + +P13：我们卖的不是 AI 产品，是一条企业智能化路径 + +## 设计目标 + +定义商业产品：客户真正需要的是从想用 AI 到用好 AI 的路径。页面要从信心段落转入业务路径段落。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。一条明亮航线从左侧“想用 AI”港口出发，经过看懂 AI、找到场景、形成方案、试点验证、系统落地，最终抵达右侧“用好 AI”港口。每个节点像灯塔或浮标。 + +## 文案布局 + +- 顶部标题：我们卖的不是 AI 产品，是一条企业智能化路径 +- 航线节点：想用 AI / 看懂 AI / 找到场景 / 形成方案 / 试点验证 / 系统落地 / 用好 AI +- 底部短句：产品是入口，路径才是价值 + +## 视觉要求 + +路径要一眼成立，不要做成产品清单或客户方案页。整体保持内训启动会的作战地图感。 + +## 后期提示 + +如节点文字过多，优先保留“想用 AI -> 用好 AI”和底部短句。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-prompt.md new file mode 100644 index 0000000..9255df1 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-prompt.md @@ -0,0 +1,30 @@ +# s13-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P13 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted previous package radar/style sample, `slides/s09/s09-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual in the same accepted style: deep navy-black AI maritime route operation map, ocean chart texture, subtle compass geometry, cyan glowing route, restrained gold action nodes, large readable Chinese typography. + +Page title at top: “我们卖的不是 AI 产品，是一条企业智能化路径”. + +Main visual: a clear maritime route map from left to right. Start port label: “想用 AI”. Route nodes as glowing buoys or small lighthouses: “看懂 AI”, “找到场景”, “形成方案”, “试点验证”, “系统落地”. Final destination port label: “用好 AI”. The route should feel practical and guided, not like a software product roadmap. + +Bottom sentence: “产品是入口，路径才是价值”. + +Mood: practical navigation model for clients. Avoid product catalog, sales proposal, SaaS dashboard, government report, dense process chart, cartoon ship, robots, real people. Use short, legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-brief.md new file mode 100644 index 0000000..cba212c --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-brief.md @@ -0,0 +1,32 @@ +# s14-v1 Brief + +## Page + +- Unit: s14 +- Source page: P14 +- Title: 三级服务路径：培训 → 顾问 → 系统 +- Page family: Business Path / Customer Judgment +- Version: v1 + +## Core Conclusion + +培训是入口，顾问是筛选，系统是重服务。 + +## Objective + +把三级服务路径可视化为团队可复述的业务基础模型。 + +## Visual Model + +三段航线：近海训练区 -> 航道判断区 -> 深水建设区，对应培训、顾问、系统。 + +## Text Strategy + +- One title. +- Three large stage labels. +- One short label per stage. +- One bottom warning sentence. + +## Continuity + +Use the accepted deep navy-black AI route operation-map base. Motif: AI 航线 + service-stage nodes. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-design.md new file mode 100644 index 0000000..9a31edb --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-design.md @@ -0,0 +1,30 @@ +# s14-v1 Design + +## 页面 + +P14：三级服务路径：培训 → 顾问 → 系统 + +## 设计目标 + +展示核心商业路径，让这页成为团队未来出去讲业务的基础模型。核心是培训入口、顾问筛选、系统重服务。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。三段式航线从近海训练区进入航道判断区，再到深水建设区。每段有一个醒目节点：培训、顾问、系统，并配短标签说明角色。 + +## 文案布局 + +- 顶部标题：三级服务路径：培训 → 顾问 → 系统 +- 三段节点： + - 培训：建立认知 + - 顾问：判断路径 + - 系统：重服务交付 +- 底部金句：不是所有客户都直接上系统 + +## 视觉要求 + +要像核心业务模型，不要像课程表。系统段要显得更重、更严，但不要压抑。 + +## 后期提示 + +如文字不稳，保留三个大节点和底部金句。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-prompt.md new file mode 100644 index 0000000..7e57076 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-prompt.md @@ -0,0 +1,30 @@ +# s14-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P14 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted previous package radar/style sample, `slides/s09/s09-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual, matching the accepted deep navy-black AI maritime operation-map style, with cyan route glow, gold stage markers, compass lines, and readable Chinese typography. + +Page title at top: “三级服务路径：培训 → 顾问 → 系统”. + +Main visual: a three-stage maritime route from left to right or rising diagonally. Stage 1 nearshore training zone: large label “培训”, sublabel “建立认知”. Stage 2 channel judgment zone: large label “顾问”, sublabel “判断路径”. Stage 3 deep-water construction zone: large label “系统”, sublabel “重服务交付”. Use route nodes, depth zones, and subtle lock/channel geometry, not a generic staircase clipart. + +Bottom sentence: “不是所有客户都直接上系统”. + +Mood: core business model, practical and memorable. Avoid course timetable, customer proposal, government report, SaaS dashboard, dense table, cartoon ship, robots, real people. Use short, legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-brief.md new file mode 100644 index 0000000..17fa3aa --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-brief.md @@ -0,0 +1,32 @@ +# s15-v1 Brief + +## Page + +- Unit: s15 +- Source page: P15 +- Title: 培训可以宽，顾问要筛，系统必须严 +- Page family: Business Path / Customer Judgment +- Version: v1 + +## Core Conclusion + +做错项目，比少做项目更伤。 + +## Objective + +让销售明白客户推进要分层筛选，尤其不能把不成熟客户直接推系统。 + +## Visual Model + +航道闸门 / 漏斗：培训宽入口，顾问筛选，系统严闸门。 + +## Text Strategy + +- One title. +- Three strict short labels. +- One central judgment. +- One bottom discipline sentence. + +## Continuity + +Use the accepted deep navy-black AI route operation-map base. Motif: 航道闸门 / funnel gate. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-design.md new file mode 100644 index 0000000..fb2db71 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-design.md @@ -0,0 +1,28 @@ +# s15-v1 Design + +## 页面 + +P15：培训可以宽，顾问要筛，系统必须严 + +## 设计目标 + +建立客户推进纪律：宽入口、严系统。页面要稳，但不能把兴奋感拉成纪律教育。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。画面中心是三段航道闸门 / 漏斗：培训入口较宽，顾问通道收窄，系统闸门最窄、最亮、最严格。旁边有风险提示，不做错项目。 + +## 文案布局 + +- 顶部标题：培训可以宽，顾问要筛，系统必须严 +- 三段标签：培训：宽入口 / 顾问：要筛选 / 系统：必须严 +- 中心判断：做错项目，比少做项目更伤 +- 底部金句：宁可少做项目，也不能做错项目 + +## 视觉要求 + +闸门要有纪律感，但不要恐吓。要体现筛选客户也是销售价值。 + +## 后期提示 + +如文字不稳，保留三段标签和底部金句。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-prompt.md new file mode 100644 index 0000000..4c906a0 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-prompt.md @@ -0,0 +1,30 @@ +# s15-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P15 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted previous package radar/style sample, `slides/s09/s09-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual in the accepted deep navy-black AI maritime route-map style, with cyan signal lines, restrained gold warning/action accents, compass grid, and bold readable Chinese typography. + +Page title at top: “培训可以宽，顾问要筛，系统必须严”. + +Main visual: a maritime lock-gate funnel. Top wide gate labeled “培训：宽入口”. Middle narrower gate labeled “顾问：要筛选”. Bottom strict narrow gate labeled “系统：必须严”. The gate geometry should feel like a channel checkpoint on an AI route map, not a generic sales funnel. Add a concise central judgment plaque: “做错项目，比少做项目更伤”. + +Bottom sentence: “宁可少做项目，也不能做错项目”. + +Mood: disciplined but not scary, practical customer filtering. Avoid punishment board, compliance training, government report, customer proposal, spreadsheet funnel, SaaS dashboard, cartoon ship, robots, real people. Use short, legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-brief.md new file mode 100644 index 0000000..6e6809c --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-brief.md @@ -0,0 +1,32 @@ +# s16-v1 Brief + +## Page + +- Unit: s16 +- Source page: P16 +- Title: 客户适配判断模型 +- Page family: Business Path / Customer Judgment +- Version: v1 + +## Core Conclusion + +客户能不能做 AI，至少看四件事。 + +## Objective + +给销售一个初步判断客户是否适合智能化的四方向罗盘。 + +## Visual Model + +四象限罗盘 + 雷达：基础建设、组织认知、场景价值、权力结构。 + +## Text Strategy + +- One title. +- One central judgment. +- Four short direction labels. +- One bottom caution sentence. + +## Continuity + +Use the accepted deep navy-black AI route operation-map base. Motif: 罗盘 + 雷达. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-design.md new file mode 100644 index 0000000..4a78174 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-design.md @@ -0,0 +1,28 @@ +# s16-v1 Design + +## 页面 + +P16：客户适配判断模型 + +## 设计目标 + +给销售一个初步判断客户的罗盘。页面信息可能多，必须把关键词压缩成四个方向。 + +## 画面概念 + +统一深蓝黑 AI 航线作战图底板。中心是“客户是否适合智能化”的罗盘 / 雷达盘，四个方向分别是基础建设、组织认知、场景价值、权力结构。每个方向只放少量关键词。 + +## 文案布局 + +- 顶部标题：客户适配判断模型 +- 中心判断：客户能不能做 AI，至少看四件事 +- 四向罗盘：基础建设 / 组织认知 / 场景价值 / 权力结构 +- 底部短句：客户想不想做，不等于客户能不能做 + +## 视觉要求 + +像销售未来可用的判断工具，不要像表格堆砌。罗盘和雷达结合，四个方向清楚。 + +## 后期提示 + +如文字不稳，优先保留四个方向和底部短句。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-prompt.md new file mode 100644 index 0000000..ee659a3 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-prompt.md @@ -0,0 +1,32 @@ +# s16-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: required project load order plus P16 skeleton, visual system, style master, motif registry, task plan, production status. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted previous package radar/style sample, `slides/s09/s09-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual in the accepted style: deep navy-black AI maritime operation map, radar scan, compass rose, subtle ocean chart, cyan signal glow, restrained gold highlights, crisp readable Chinese typography. + +Page title at top: “客户适配判断模型”. + +Main visual: a large four-direction compass combined with radar. Center label: “客户是否适合智能化”. Four compass directions with clear labels: “基础建设”, “组织认知”, “场景价值”, “权力结构”. Add tiny supporting keywords around each direction, very short only: “系统/数据”, “老板/员工”, “高频/高成本”, “决策/付款”. Keep the compass clean and usable, not a crowded table. + +Central or upper judgment: “客户能不能做 AI，至少看四件事”. + +Bottom sentence: “客户想不想做，不等于客户能不能做”. + +Mood: practical judgment tool for experienced salespeople. Avoid dense table, government report, customer proposal, SaaS dashboard, technical architecture lecture, cartoon ship, robots, real portraits. Use short, legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-brief.md new file mode 100644 index 0000000..f85c887 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-brief.md @@ -0,0 +1,33 @@ +# s17-v1 Brief + +## Execution Card + +- Unit: s17 +- Source page: P17 +- Title: 双轨体系：先探索价值，再工程兑现 +- Family: Business Path / Customer Judgment +- Motif: 双轨 / 双航道 +- Running mode: prompt and generate +- Review mode: none +- Version: s17-v1 +- Overwrite allowed: no + +## Source Judgment + +眼下重点不是系统建设分工，而是先把探索轨跑起来。 + +## Visual Direction + +Use the accepted deep navy-black AI maritime route operation-map base. Show two coordinated channels: a bright exploration track above and a steadier engineering track below. The exploration vessel goes first to identify value; the engineering vessel follows only after value is confirmed. + +## Text To Keep Short + +- 双轨体系：先探索价值，再工程兑现 +- 探索轨：发现价值 +- 工程轨：兑现价值 +- 先拉上船，再说怎么造大船 +- 我们现在要先学会发现价值 + +## Avoid + +Do not drift into engineering management, system architecture, SaaS dashboard, customer proposal, cartoon ship, humanoid robots, or concrete people. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-design.md new file mode 100644 index 0000000..60f47dd --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-design.md @@ -0,0 +1,27 @@ +# s17-v1 Design + +## 页面定位 + +- 页面：P17 / s17 +- 标题：双轨体系：先探索价值，再工程兑现 +- 页面家族：Business Path / Customer Judgment +- 核心结论：眼下重点不是系统建设分工，而是先把探索轨跑起来。 +- 核心母题：双轨 / 双航道 + +## 视觉概念 + +在统一的深蓝黑 AI 航线作战图底盘上，画面横向展开两条并行航道。上方“探索轨”用更亮的青色航线表现，像一艘雷达探测船先行探水深；下方“工程轨”用更深、更稳的蓝灰航道表现，像工程船队在后方等待兑现价值。 + +两条轨道不是并列抢戏，而是有先后关系：探索轨前置、工程轨后接。中间用金色转接节点强调“价值确认后再工程兑现”。 + +## 文字与布局 + +- 顶部主标题：双轨体系：先探索价值，再工程兑现 +- 中央大判断：先拉上船，再说怎么造大船 +- 上轨标签：探索轨 / 发现价值 +- 下轨标签：工程轨 / 兑现价值 +- 底部短句：我们现在要先学会发现价值 + +## 风格约束 + +沿用 s02 / s16 的深蓝黑航海作战图、雷达、罗盘线、青色信号和克制金色强调。不要做成工程管理架构图、铁路交通图、SaaS 流程图或客户方案页。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-prompt.md new file mode 100644 index 0000000..066e18e --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-prompt.md @@ -0,0 +1,33 @@ +# s17-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, subtle ocean chart grid, radar glow, compass lines, cyan signal routes, restrained gold decision highlights, crisp readable Chinese typography. + +Page title at top: “双轨体系：先探索价值，再工程兑现”. + +Main visual: two parallel maritime channels across the slide. Upper channel is bright cyan and labeled “探索轨：发现价值”, with a radar scout vessel moving first through customer interview, training, scenario sorting, agent prototype, pilot validation nodes shown as tiny route lights. Lower channel is darker, steadier blue-gray and labeled “工程轨：兑现价值”, with an engineering vessel following later through system, database, permission, interface, deployment, testing nodes as subdued markers. Add one gold transfer node between tracks labeled “价值确认”. + +Central large judgment plaque: “先拉上船，再说怎么造大船”. + +Bottom sentence: “我们现在要先学会发现价值”. + +Mood: practical navigation model, sales veterans enter the exploration track first. Avoid engineering management chart, system architecture lecture, SaaS dashboard, customer proposal, government report, cyberpunk poster, cartoon ship, robots, stock people, concrete portraits. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-brief.md new file mode 100644 index 0000000..78466a2 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-brief.md @@ -0,0 +1,35 @@ +# s18-v1 Brief + +## Execution Card + +- Unit: s18 +- Source page: P18 +- Title: 新团队协作结构 +- Family: Team Structure / Boundaries +- Motif: 船舱 / 作战地图 +- Running mode: prompt and generate +- Review mode: none +- Version: s18-v1 +- Overwrite allowed: no + +## Source Judgment + +未来不是老板 + 销售 + 技术，而是四类角色协同。 + +## Visual Direction + +Use a ship-compartment operation map. Put “客户智能化旅程” in the center and four functional compartments around it: chief expert, customer operations, AI business engineer, deterministic engineering foundation. + +## Text To Keep Short + +- 新团队协作结构 +- 客户智能化旅程 +- 首席专家 +- 客户经营 +- AI业务工程 +- 工程底座 +- 各就各位，才能打大仗 + +## Avoid + +No HR org chart, no portrait wall, no policy page, no customer proposal, no generic SaaS dashboard. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-design.md new file mode 100644 index 0000000..36276cc --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-design.md @@ -0,0 +1,26 @@ +# s18-v1 Design + +## 页面定位 + +- 页面：P18 / s18 +- 标题：新团队协作结构 +- 页面家族：Team Structure / Boundaries +- 核心结论：未来不是老板 + 销售 + 技术，而是四类角色协同。 +- 核心母题：船舱 / 作战地图 + +## 视觉概念 + +统一底盘上呈现一张“船舱式作战地图”。中心不是老板，而是“客户智能化旅程”；四个功能舱位环绕中心：学者型首席专家、客户经营负责人、AI 业务工程师、确定性工程底座。 + +每个舱位使用抽象图标和短标签，连接线汇入中心航线，表达“各就各位，才能打大仗”。画面要有组织感但不僵硬，像启动会的作战分工图，不像 HR 组织架构。 + +## 文字与布局 + +- 顶部主标题：新团队协作结构 +- 中心：客户智能化旅程 +- 四舱位：首席专家 / 客户经营 / AI业务工程 / 工程底座 +- 底部短句：各就各位，才能打大仗 + +## 风格约束 + +保持深蓝黑、青色航线、金色角色节点。避免正式组织架构图、职级汇报页、团队头像墙和政府报告风。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-prompt.md new file mode 100644 index 0000000..44f41ed --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-prompt.md @@ -0,0 +1,35 @@ +# s18-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, cyan route glow, radar and compass geometry, restrained gold role highlights, crisp readable Chinese typography. + +Page title at top: “新团队协作结构”. + +Main visual: a ship-compartment operation map, not a stiff org chart. Center glowing route node labeled “客户智能化旅程”. Four surrounding compartments connected to the center: +1. “首席专家” sublabel “方法论 / 判断” +2. “客户经营” sublabel “关系 / 初筛” +3. “AI业务工程” sublabel “转译 / 原型” +4. “工程底座” sublabel “系统 / 交付” + +Use compartment panels, route lines, subtle deck blueprint geometry, and gold-cyan node links. Add bottom sentence: “各就各位，才能打大仗”. + +Mood: brotherly trust plus company discipline, practical collaboration map. Avoid HR org chart, portrait wall, meeting-room stock photo, customer proposal, government report, SaaS dashboard, cyberpunk poster, robots, cartoon ship. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-brief.md new file mode 100644 index 0000000..5d1fca2 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-brief.md @@ -0,0 +1,32 @@ +# s19-v1 Brief + +## Execution Card + +- Unit: s19 +- Source page: P19 +- Title: 我们是帮客户上船的人 +- Family: Team Structure / Boundaries +- Motif: 角色图标 / 登船路径 +- Running mode: prompt and generate +- Review mode: none +- Version: s19-v1 +- Overwrite allowed: no + +## Source Judgment + +客户不知道怎么上 AI 这条船，我们就是带路的人。 + +## Visual Direction + +Create an easy-to-remember role map around an abstract boarding path. Five icons: entrance, radar, translator, propeller, firewall. Keep it simple and iconic. + +## Text To Keep Short + +- 我们是帮客户上船的人 +- 客户不知道怎么上 AI 这条船，我们就是那个带路的人 +- 入口 / 雷达 / 翻译器 / 推进器 / 防火墙 +- 找到客户，听懂客户，判断客户，推动客户，守住边界 + +## Avoid + +No real people, no cartoon mascot, no customer brochure, no motivational poster, no humanoid robots. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-design.md new file mode 100644 index 0000000..99bb55b --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-design.md @@ -0,0 +1,26 @@ +# s19-v1 Design + +## 页面定位 + +- 页面：P19 / s19 +- 标题：我们是帮客户上船的人 +- 页面家族：Team Structure / Boundaries +- 核心结论：客户不知道怎么上 AI 这条船，我们就是带路的人。 +- 核心母题：五个角色图标围绕登船路径 + +## 视觉概念 + +这页要成为容易记住的精神锚点。画面中心是一条抽象登船路径，从客户侧通向 AI 航线。五个角色图标围绕路径排列：入口、雷达、翻译器、推进器、防火墙。 + +视觉语言要简洁、有力量，不做复杂插画。每个角色用一个金色或青色图标表示，整体像一张“客户上船行动图”。 + +## 文字与布局 + +- 顶部主标题：我们是帮客户上船的人 +- 中央金句：客户不知道怎么上 AI 这条船，我们就是那个带路的人 +- 五角色：入口 / 雷达 / 翻译器 / 推进器 / 防火墙 +- 底部短句：找到客户，听懂客户，判断客户，推动客户，守住边界 + +## 风格约束 + +避免人物肖像、卡通船、吉祥物和励志海报。必须像内部作战图中的角色地图。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-prompt.md new file mode 100644 index 0000000..4d07bb9 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-prompt.md @@ -0,0 +1,38 @@ +# s19-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, cyan route glow, radar scan, compass grid, restrained gold highlights, crisp readable Chinese typography. + +Page title at top: “我们是帮客户上船的人”. + +Main visual: an abstract boarding path across a dark AI route map, leading from “客户” toward a glowing AI route. Around the path place five clean role icons with short labels: +1. “入口” with a boarding-ticket icon +2. “雷达” with a radar-scan icon +3. “翻译器” with two-way arrows +4. “推进器” with a propulsion engine symbol +5. “防火墙” with a shield gate + +Central large quote: “客户不知道怎么上 AI 这条船，我们就是那个带路的人”. + +Bottom sentence: “找到客户，听懂客户，判断客户，推动客户，守住边界”. + +Mood: memorable spiritual anchor, simple role map, internal route-operation energy. Avoid real people, portraits, cute cartoon ship, mascot, customer brochure, government report, SaaS dashboard, cyberpunk poster, robots, dense text. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-brief.md new file mode 100644 index 0000000..6d8496f --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-brief.md @@ -0,0 +1,34 @@ +# s20-v1 Brief + +## Execution Card + +- Unit: s20 +- Source page: P20 +- Title: 魏征机制：你们也是我的现实校准器 +- Family: Team Structure / Boundaries +- Motif: 校准罗盘 +- Running mode: prompt and generate +- Review mode: none +- Version: s20-v1 +- Overwrite allowed: no + +## Source Judgment + +你们不是打断我，是帮我保护会议节奏。 + +## Visual Direction + +Use a compass correction metaphor. A route drifts off course, then three calibration actions return it to the main route: before meeting reminder, during meeting pullback, after meeting debrief. + +## Text To Keep Short + +- 魏征机制：你们也是我的现实校准器 +- 会前提醒 +- 会中拉回 +- 会后复盘 +- 你们不是打断我，是帮我保护会议节奏 +- AI 能提醒我，但现实里的魏征更管用 + +## Avoid + +No historical portrait, no ancient costume style, no rules board, no HR process, no government report. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-design.md new file mode 100644 index 0000000..c0c6c02 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-design.md @@ -0,0 +1,26 @@ +# s20-v1 Design + +## 页面定位 + +- 页面：P20 / s20 +- 标题：魏征机制：你们也是我的现实校准器 +- 页面家族：Team Structure / Boundaries +- 核心结论：你们不是打断我，是帮我保护会议节奏。 +- 核心母题：校准罗盘 / 航向修正 + +## 视觉概念 + +画面以一个正在被校准的罗盘为中心。偏航的航线从左侧进入，经过“会前提醒 / 会中拉回 / 会后复盘”三个校准动作后，重新回到主航线。 + +这页要有人情味但不能出现具体人物。用“现实校准器”这个隐喻来表达兄弟间的提醒和协作，不做成管理制度页。 + +## 文字与布局 + +- 顶部主标题：魏征机制：你们也是我的现实校准器 +- 中央判断：你们不是打断我，是帮我保护会议节奏 +- 三段：会前提醒 / 会中拉回 / 会后复盘 +- 底部金句：AI 能提醒我，但现实里的魏征更管用 + +## 风格约束 + +保持航线图与罗盘感。避免历史人物画像、古风海报、制度板、会议管理流程图。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-prompt.md new file mode 100644 index 0000000..51881ca --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-prompt.md @@ -0,0 +1,33 @@ +# s20-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, compass geometry, radar glow, cyan route lines, restrained gold correction markers, crisp readable Chinese typography. + +Page title at top: “魏征机制：你们也是我的现实校准器”. + +Main visual: a compass calibration and route-correction map. A cyan route line begins slightly off course, passes through three gold-cyan calibration nodes, then returns to the main route. The three nodes are labeled “会前提醒”, “会中拉回”, “会后复盘”. Center compass label: “现实校准器”. + +Large central judgment: “你们不是打断我，是帮我保护会议节奏”. + +Bottom sentence: “AI 能提醒我，但现实里的魏征更管用”. + +Mood: trusted internal feedback mechanism, brotherly but disciplined. Avoid historical portraits, ancient Chinese costume style, rules board, HR process page, government report, customer proposal, SaaS dashboard, cyberpunk poster, robots, real people. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-brief.md new file mode 100644 index 0000000..08f512d --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-brief.md @@ -0,0 +1,35 @@ +# s21-v1 Brief + +## Execution Card + +- Unit: s21 +- Source page: P21 +- Title: L0-L4 成长路径 +- Family: Team Structure / Boundaries +- Motif: L0-L4 阶梯 / 航行资格 +- Running mode: prompt and generate +- Review mode: none +- Version: s21-v1 +- Overwrite allowed: no + +## Source Judgment + +头衔不是先给的，是训练和行为拿到的。 + +## Visual Direction + +Use an upward navigation-license ladder, from L0 to L4. Each step is a clear growth station, not a ranking wall. + +## Text To Keep Short + +- L0-L4 成长路径 +- L0 渠道伙伴 +- L1 AI商务助理 +- L2 客户经营负责人 +- L3 商务负责人 +- L4 AI前端部署顾问 +- 不是所有人一步到位，但每个人都有上升通道 + +## Avoid + +No school grading, no pressure ranking, no HR promotion chart, no stiff policy page. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-design.md new file mode 100644 index 0000000..f4d53f1 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-design.md @@ -0,0 +1,26 @@ +# s21-v1 Design + +## 页面定位 + +- 页面：P21 / s21 +- 标题：L0-L4 成长路径 +- 页面家族：Team Structure / Boundaries +- 核心结论：头衔不是先给的，是训练和行为拿到的。 +- 核心母题：L0-L4 阶梯 / 航行资格 + +## 视觉概念 + +画面用左低右高的航行资格阶梯。每一级像一张航海许可或训练等级牌，而不是等级压迫。L0 到 L4 沿着青色路线逐步点亮，最终通向前端部署顾问。 + +整体要给希望，不给压力。L0 不显得低人一等，而是“起点清楚”。 + +## 文字与布局 + +- 顶部主标题：L0-L4 成长路径 +- 中央判断：头衔不是先给的，是训练和行为拿到的 +- 五级：L0 渠道伙伴 / L1 AI商务助理 / L2 客户经营负责人 / L3 商务负责人 / L4 AI前端部署顾问 +- 底部短句：不是所有人一步到位，但每个人都有上升通道 + +## 风格约束 + +保持深蓝黑航线和金色资格节点。避免学校成绩单、KPI 压迫榜、HR 晋升制度页。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-prompt.md new file mode 100644 index 0000000..97ab312 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-prompt.md @@ -0,0 +1,38 @@ +# s21-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, subtle compass grid, cyan route glow, restrained gold milestone nodes, crisp readable Chinese typography. + +Page title at top: “L0-L4 成长路径”. + +Main visual: an upward navigation-license ladder from left-low to right-high across the dark route map. Five illuminated stations, each like a clean maritime qualification plate: +L0 “渠道伙伴” +L1 “AI商务助理” +L2 “客户经营负责人” +L3 “商务负责人” +L4 “AI前端部署顾问” + +Add a large central judgment: “头衔不是先给的，是训练和行为拿到的”. + +Bottom sentence: “不是所有人一步到位，但每个人都有上升通道”. + +Mood: hopeful growth path, disciplined but not pressure-heavy. Avoid school grading chart, HR promotion chart, pressure ranking, compliance policy page, customer proposal, government report, SaaS dashboard, cartoon ship, robots, real people. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-brief.md new file mode 100644 index 0000000..07c7f32 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-brief.md @@ -0,0 +1,33 @@ +# s22-v1 Brief + +## Execution Card + +- Unit: s22 +- Source page: P22 +- Title: 今天先记住三条 +- Family: Team Structure / Boundaries +- Motif: 三道安全闸 +- Running mode: prompt and generate +- Review mode: none +- Version: s22-v1 +- Overwrite allowed: no + +## Source Judgment + +规则可以慢慢细化，但底线今天先钉住。 + +## Visual Direction + +Use three safety gates / seals in the accepted maritime operation-map style. The page should feel firm and lightweight, not punitive. + +## Text To Keep Short + +- 今天先记住三条 +- 不装专家 +- 不乱承诺 +- 不直接推系统 +- 老江湖也要适应新边界 + +## Avoid + +No punishment board, no red compliance warning, no dense rule list, no government report. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-design.md new file mode 100644 index 0000000..4740e1f --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-design.md @@ -0,0 +1,26 @@ +# s22-v1 Design + +## 页面定位 + +- 页面：P22 / s22 +- 标题：今天先记住三条 +- 页面家族：Team Structure / Boundaries +- 核心结论：规则可以慢慢细化，但底线今天先钉住。 +- 核心母题：三道安全闸 + +## 视觉概念 + +画面呈现三道轻量但明确的航行安全闸门。每道闸门像一枚发光印章或检查点，不像纪律处分板。三条底线并列：不装专家、不乱承诺、不把不成熟客户直接推系统。 + +整体氛围要稳，但不能把启动会兴奋感拉成规则教育。 + +## 文字与布局 + +- 顶部主标题：今天先记住三条 +- 中央判断：规则可以慢慢细化，但底线今天先钉住 +- 三卡：不装专家 / 不乱承诺 / 不直接推系统 +- 底部短句：老江湖也要适应新边界 + +## 风格约束 + +用航道闸门和金色底线印章；避免处罚、红色警示、制度墙、密密麻麻清单。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-prompt.md new file mode 100644 index 0000000..1ca3778 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-prompt.md @@ -0,0 +1,36 @@ +# s22-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, cyan route lines, compass grid, restrained gold safety-gate highlights, crisp readable Chinese typography. + +Page title at top: “今天先记住三条”. + +Main visual: three large clean safety gates or gold-cyan seals aligned across an AI route channel. Each gate is firm but not punitive: +1. “不装专家” sublabel “不懂可以学” +2. “不乱承诺” sublabel “不能承诺结果” +3. “不直接推系统” sublabel “成熟客户再进” + +Central judgment: “规则可以慢慢细化，但底线今天先钉住”. + +Bottom sentence: “老江湖也要适应新边界”. + +Mood: lightweight boundary-setting, steady and practical, still part of an exciting kickoff. Avoid punishment board, red compliance warning, dense policy wall, government report, customer proposal, SaaS dashboard, cyberpunk poster, cartoon ship, robots, real people. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-brief.md new file mode 100644 index 0000000..c2753ce --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-brief.md @@ -0,0 +1,34 @@ +# s23-v1 Brief + +## Execution Card + +- Unit: s23 +- Source page: P23 +- Title: 一个月训练：成为 AI 增强型客户经营人员 +- Family: Training / Action +- Motif: 训练路线图 +- Running mode: prompt and generate +- Review mode: none +- Version: s23-v1 +- Overwrite allowed: no + +## Source Judgment + +一个月后，大家至少要会用 AI 做准备、复盘和客户判断。 + +## Visual Direction + +Use a four-week route map across the accepted dark AI maritime operation base. Keep each week as one clear node with a short training target. + +## Text To Keep Short + +- 一个月训练：成为 AI 增强型客户经营人员 +- 第一周：和 AI 交朋友 +- 第二周：客户沟通与业务理解 +- 第三周：产品边界与承诺规则 +- 第四周：模拟拜访与认证 +- 不是培养技术专家，是培养 AI 增强型商务人员 + +## Avoid + +No course syllabus, no school homework look, no formal certificate poster, no dense schedule table. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-design.md new file mode 100644 index 0000000..cb74d9d --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-design.md @@ -0,0 +1,26 @@ +# s23-v1 Design + +## 页面定位 + +- 页面：P23 / s23 +- 标题：一个月训练：成为 AI 增强型客户经营人员 +- 页面家族：Training / Action +- 核心结论：一个月后，大家至少要会用 AI 做准备、复盘和客户判断。 +- 核心母题：训练路线图 + +## 视觉概念 + +画面是一条四周训练航线，从“新船员训练”出发，到“AI 增强型客户经营人员”。四个周节点沿路线排布，节点文字只保留目标，不展开课程大纲。 + +这页从结构页转入行动页，要更明确、更收束，但仍沿用统一航线作战图底盘。 + +## 文字与布局 + +- 顶部主标题：一个月训练：成为 AI 增强型客户经营人员 +- 中央判断：一个月后，大家至少要会用 AI 做准备、复盘和客户判断 +- 四周：和 AI 交朋友 / 客户沟通与业务理解 / 产品边界与承诺规则 / 模拟拜访与认证 +- 底部金句：不是培养技术专家，是培养 AI 增强型商务人员 + +## 风格约束 + +避免课程表、学校培训海报、密集 syllabus。必须是行动路线图。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-prompt.md new file mode 100644 index 0000000..6e11bbe --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-prompt.md @@ -0,0 +1,37 @@ +# s23-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, cyan route glow, compass lines, restrained gold milestone highlights, crisp readable Chinese typography. + +Page title at top: “一个月训练：成为 AI 增强型客户经营人员”. + +Main visual: a four-week training route map across a dark AI sea chart, starting from “新船员训练” and ending at “AI增强型客户经营”. Four glowing route nodes: +1. “第一周：和 AI 交朋友” +2. “第二周：客户沟通” +3. “第三周：边界规则” +4. “第四周：模拟认证” + +Large central judgment: “一个月后，会用 AI 做准备、复盘和客户判断”. + +Bottom sentence: “不是培养技术专家，是培养 AI 增强型商务人员”. + +Mood: immediate action after kickoff, clear training route, confident and practical. Avoid course syllabus, school homework cartoon, formal certificate poster, dense schedule table, customer proposal, government report, SaaS dashboard, cyberpunk poster, robots, real people. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-brief.md b/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-brief.md new file mode 100644 index 0000000..336f081 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-brief.md @@ -0,0 +1,37 @@ +# s24-v1 Brief + +## Execution Card + +- Unit: s24 +- Source page: P24 +- Title: 第一周目标：写出自己的 AI 训练目标 +- Family: Training / Action +- Motif: 船员训练卡 +- Running mode: prompt and generate +- Review mode: none +- Version: s24-v1 +- Overwrite allowed: no + +## Source Judgment + +会后第一件事：每个人形成自己的第一周 AI 训练目标。 + +## Visual Direction + +Use a crew first-week training card, derived from the boarding-ticket motif. It should look actionable and fillable, but not like school homework or an administrative form. + +## Text To Keep Short + +- 第一周目标：写出自己的 AI 训练目标 +- 第一周 AI 训练目标 +- 解决什么问题 +- 每天何时用 +- 会前准备 +- 会后复盘 +- 一周成果 +- 我的 AI 工作流说明书 +- 先从自己开始，把 AI 用起来 + +## Avoid + +No school test paper, no rigid form, no certificate poster, no empty slogan page. diff --git a/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-design.md b/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-design.md new file mode 100644 index 0000000..8733437 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-design.md @@ -0,0 +1,27 @@ +# s24-v1 Design + +## 页面定位 + +- 页面：P24 / s24 +- 标题：第一周目标：写出自己的 AI 训练目标 +- 页面家族：Training / Action +- 核心结论：会后第一件事：每个人形成自己的第一周 AI 训练目标。 +- 核心母题：船员训练卡 + +## 视觉概念 + +最后一页要直接落到行动。画面中心是一张“船员第一周训练卡”，像从船票升级而来的行动卡。卡片上保留五个问题，但压缩成短标签，旁边是提交成果“我的 AI 工作流说明书”。 + +视觉上既像可填写的卡，也像 AI 航线上的第一张行动票。 + +## 文字与布局 + +- 顶部主标题：第一周目标：写出自己的 AI 训练目标 +- 中央卡片：第一周 AI 训练目标 +- 五问短标签：解决什么问题 / 每天何时用 / 会前准备 / 会后复盘 / 一周成果 +- 升级方向：我的 AI 工作流说明书 +- 收束金句：先从自己开始，把 AI 用起来 + +## 风格约束 + +保持启动会收束感，不做口号页。避免作业本、学校考试、行政表单和过度正式的证书。 diff --git a/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-prompt.md b/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-prompt.md new file mode 100644 index 0000000..7bde50b --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-prompt.md @@ -0,0 +1,38 @@ +# s24-v1 Prompt + +## gpt-image-2 Workflow Record + +- Skill mode result: `{"mode":"B-or-C","recommendation":"host-or-advisor","garden_mode_enabled":false,"has_api_key":false,"base_url":"https://api.openai.com/v1","model":"gpt-image-2","env_flag_value":"(unset)"}` +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Reference/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- Source files used: AGENTS.md, formal production handoff, project.md, execution-plan.md, slides.md, visual-system.md, style-prompt-master.md, motif-registry.md, P1-P24 skeleton, task-plan.md, production-run-status.md. +- Visual calibration references loaded: + - Image 1: accepted content-page style sample, `slides/s02/s02-v1-image.png` + - Image 2: accepted customer-judgment style sample, `slides/s16/s16-v1-image.png` + +## Final Image Prompt + +Create a 16:9 internal kickoff PPT full-page visual matching Image 1 and Image 2: deep navy-black AI maritime operation map, boarding-ticket motif, cyan route glow, restrained gold action highlights, compass grid, crisp readable Chinese typography. + +Page title at top: “第一周目标：写出自己的 AI 训练目标”. + +Main visual: a large crew first-week training card, like a boarding pass upgraded into an action worksheet. Card title: “第一周 AI 训练目标”. On the card show five short fill-in prompts as clean rows: +1. “解决什么问题” +2. “每天何时用” +3. “会前准备” +4. “会后复盘” +5. “一周成果” + +Add a gold upgrade tag on the card: “我的 AI 工作流说明书”. + +Bottom closing sentence: “先从自己开始，把 AI 用起来”. + +Mood: final action page, concrete and motivating, immediately usable after the meeting. Avoid school test paper, administrative form, certificate poster, empty slogan page, customer proposal, government report, SaaS dashboard, cyberpunk poster, cartoon ship, robots, real people. Use short legible Chinese labels only. diff --git a/projects/2026-06-29-搭上AI这条船/slides/slides.md b/projects/2026-06-29-搭上AI这条船/slides/slides.md new file mode 100644 index 0000000..2d29f4b --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/slides/slides.md @@ -0,0 +1,51 @@ +# Slides + +## Status + +- Project: `2026-06-29-搭上AI这条船` +- Unit type: PPT page / slide. +- Source page notation: P01-P24. +- Local artifact notation for generated work: `s01`, `s02`, ... +- Current status: P01/P02 samples confirmed by user; s03-s24 production-pass. +- Write policy: append-only; overwrite allowed: no. + +## Source Authority + +Page order, page title, and core conclusion come from: + +```text +../intake/阶段5：P1-P24 单页设计骨架.md +``` + +## Page Status Table + +| Unit | Source Page | Title | Page Family | Status | Design | Prompt | Image | Notes | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | +| s01 | P01 | 搭上 AI 这条船 | Opening / Consensus | user-confirmed pass | `slides/s01/s01-v1-design.md`; `slides/s01/s01-v1-brief.md` | `slides/s01/s01-v1-prompt.md` | `slides/s01/s01-v1-image.png` | Cover and public-style sample / AI 航线 / 船票 | +| s02 | P02 | 今天这场会，不是再动员一次 | Opening / Consensus | user-confirmed pass | `slides/s02/s02-v1-design.md`; `slides/s02/s02-v1-brief.md` | `slides/s02/s02-v1-prompt.md` | `slides/s02/s02-v1-image.png` | First content-page sample / Not-Is consensus page | +| s03 | P03 | 我们要建的，不是传统销售团队 | Opening / Consensus | production-pass | `slides/s03/s03-v1-design.md`; `slides/s03/s03-v1-brief.md` | `slides/s03/s03-v1-prompt.md` | `slides/s03/s03-v1-image.png` | Radar-centered team identity | +| s04 | P04 | 为什么现在必须变 | Pressure / Role Transition | production-pass | `slides/s04/s04-v1-design.md`; `slides/s04/s04-v1-brief.md` | `slides/s04/s04-v1-prompt.md` | `slides/s04/s04-v1-image.png` | Old route pressure / new AI route | +| s05 | P05 | 我这半年打通了什么 | Pressure / Role Transition | production-pass | `slides/s05/s05-v1-design.md`; `slides/s05/s05-v1-brief.md` | `slides/s05/s05-v1-prompt.md` | `slides/s05/s05-v1-image.png` | Product / method / training base | +| s06 | P06 | 我的角色已经变了 | Pressure / Role Transition | production-pass | `slides/s06/s06-v1-design.md`; `slides/s06/s06-v1-brief.md` | `slides/s06/s06-v1-prompt.md` | `slides/s06/s06-v1-image.png` | Overloaded center to expert node | +| s07 | P07 | 过去靠我一个人顶，未来靠体系一起跑 | Pressure / Role Transition | production-pass | `slides/s07/s07-v1-design.md`; `slides/s07/s07-v1-brief.md` | `slides/s07/s07-v1-prompt.md` | `slides/s07/s07-v1-image.png` | Single engine to multi-engine system | +| s08 | P08 | 为什么不是传统销售 | Confidence / Agentic Entry | production-pass | `slides/s08/s08-v1-design.md`; `slides/s08/s08-v1-brief.md` | `slides/s08/s08-v1-prompt.md` | `slides/s08/s08-v1-image.png` | Traditional sales vs customer journey | +| s09 | P09 | 为什么这次找你们 | Confidence / Agentic Entry | production-pass | `slides/s09/s09-v1-design.md`; `slides/s09/s09-v1-brief.md` | `slides/s09/s09-v1-prompt.md` | `slides/s09/s09-v1-image.png` | 识人 / 识局 / 识势 | +| s10 | P10 | Agentic 技术平权：外行也能上船 | Confidence / Agentic Entry | production-pass | `slides/s10/s10-v1-design.md`; `slides/s10/s10-v1-brief.md` | `slides/s10/s10-v1-prompt.md` | `slides/s10/s10-v1-image.png` | Boarding ramp / lowered technical wall | +| s11 | P11 | 传统软件工程师和 Agentic 工程师，是两个物种 | Confidence / Agentic Entry | production-pass | `slides/s11/s11-v1-design.md`; `slides/s11/s11-v1-brief.md` | `slides/s11/s11-v1-prompt.md` | `slides/s11/s11-v1-image.png` | Capability-system contrast | +| s12 | P12 | 第一阶段要求：不是懂 AI，而是会带着 AI 工作 | Confidence / Agentic Entry | production-pass | `slides/s12/s12-v1-design.md`; `slides/s12/s12-v1-brief.md` | `slides/s12/s12-v1-prompt.md` | `slides/s12/s12-v1-image.png` | AI work habit loop | +| s13 | P13 | 我们卖的不是 AI 产品，是一条企业智能化路径 | Business Path / Customer Judgment | production-pass | `slides/s13/s13-v1-design.md`; `slides/s13/s13-v1-brief.md` | `slides/s13/s13-v1-prompt.md` | `slides/s13/s13-v1-image.png` | 想用 AI -> 用好 AI route | +| s14 | P14 | 三级服务路径：培训 → 顾问 → 系统 | Business Path / Customer Judgment | production-pass | `slides/s14/s14-v1-design.md`; `slides/s14/s14-v1-brief.md` | `slides/s14/s14-v1-prompt.md` | `slides/s14/s14-v1-image.png` | Three-stage route | +| s15 | P15 | 培训可以宽，顾问要筛，系统必须严 | Business Path / Customer Judgment | production-pass | `slides/s15/s15-v1-design.md`; `slides/s15/s15-v1-brief.md` | `slides/s15/s15-v1-prompt.md` | `slides/s15/s15-v1-image.png` | Funnel / lock gate | +| s16 | P16 | 客户适配判断模型 | Business Path / Customer Judgment | production-pass | `slides/s16/s16-v1-design.md`; `slides/s16/s16-v1-brief.md` | `slides/s16/s16-v1-prompt.md` | `slides/s16/s16-v1-image.png` | Four-direction compass | +| s17 | P17 | 双轨体系：先探索价值，再工程兑现 | Business Path / Customer Judgment | production-pass | `slides/s17/s17-v1-design.md`; `slides/s17/s17-v1-brief.md` | `slides/s17/s17-v1-prompt.md` | `slides/s17/s17-v1-image.png` | Double-track exploration / engineering route | +| s18 | P18 | 新团队协作结构 | Team Structure / Boundaries | production-pass | `slides/s18/s18-v1-design.md`; `slides/s18/s18-v1-brief.md` | `slides/s18/s18-v1-prompt.md` | `slides/s18/s18-v1-image.png` | Four-role ship-compartment operation map | +| s19 | P19 | 我们是帮客户上船的人 | Team Structure / Boundaries | production-pass | `slides/s19/s19-v1-design.md`; `slides/s19/s19-v1-brief.md` | `slides/s19/s19-v1-prompt.md` | `slides/s19/s19-v1-image.png` | Five role icons around boarding path | +| s20 | P20 | 魏征机制：你们也是我的现实校准器 | Team Structure / Boundaries | production-pass | `slides/s20/s20-v1-design.md`; `slides/s20/s20-v1-brief.md` | `slides/s20/s20-v1-prompt.md` | `slides/s20/s20-v1-image.png` | Compass correction / reality calibration | +| s21 | P21 | L0-L4 成长路径 | Team Structure / Boundaries | production-pass | `slides/s21/s21-v1-design.md`; `slides/s21/s21-v1-brief.md` | `slides/s21/s21-v1-prompt.md` | `slides/s21/s21-v1-image.png` | Ladder / navigation license | +| s22 | P22 | 今天先记住三条 | Team Structure / Boundaries | production-pass | `slides/s22/s22-v1-design.md`; `slides/s22/s22-v1-brief.md` | `slides/s22/s22-v1-prompt.md` | `slides/s22/s22-v1-image.png` | Three safety gates | +| s23 | P23 | 一个月训练：成为 AI 增强型客户经营人员 | Training / Action | production-pass | `slides/s23/s23-v1-design.md`; `slides/s23/s23-v1-brief.md` | `slides/s23/s23-v1-prompt.md` | `slides/s23/s23-v1-image.png` | Four-week training route | +| s24 | P24 | 第一周目标：写出自己的 AI 训练目标 | Training / Action | production-pass | `slides/s24/s24-v1-design.md`; `slides/s24/s24-v1-brief.md` | `slides/s24/s24-v1-prompt.md` | `slides/s24/s24-v1-image.png` | Crew first-week training card | + +## Next Action + +All planned pages s01-s24 now have production-pass images. Use `slides/s01/s01-v1-image.png` and `slides/s02/s02-v1-image.png` as accepted style samples when future repair or append-only retries are requested. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/production-run-status.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/production-run-status.md new file mode 100644 index 0000000..1f94152 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/production-run-status.md @@ -0,0 +1,41 @@ +# Production Run Status + +## Status + +- Project: `2026-06-29-搭上AI这条船` +- Lifecycle phase: formal production +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Package size: 7, with final package `s17-s24` expanded to 8 by user instruction +- User confirmation: clean callback may continue automatically +- Current status: complete + +## Scope + +- Total target units: `s03-s24` +- Completed units: `s03-s24` +- Active child session: none +- Next cursor: complete + +## Callback Target + +- Parent thread: `019f1359-47c9-79e2-b7d4-3d461eb04e28` +- Callback mode: child sends concise callback as final action + +## Latest Callback + +- Status: complete +- Topology: direct-child +- Resolved versions: `s17-v1; s18-v1; s19-v1; s20-v1; s21-v1; s22-v1; s23-v1; s24-v1` +- Handoff path: `projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-03/child-session-handoff.md` +- Image paths: `projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-image.png` +- Problems: none blocking; `s20` first generation discarded for title typo and project image is the retry +- Needs user: none + +## Stop Conditions + +- Artifact collision on any target `sNN-vN-*` path. +- Generated pages drift away from the accepted P01/P02 style. +- Text becomes too broken for internal meeting use. +- The deck drifts into customer proposal, government report, SaaS dashboard, or cyberpunk poster style. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-01/child-session-handoff.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-01/child-session-handoff.md new file mode 100644 index 0000000..bed6f5c --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-01/child-session-handoff.md @@ -0,0 +1,11 @@ +# Child Session 01 Handoff + +- Status: complete +- Topology: direct-child +- Callback: ready-to-send-as-final-action +- Review mode: none +- Resolved versions: s03-v1; s04-v1; s05-v1; s06-v1; s07-v1; s08-v1; s09-v1 +- Image paths: `projects/2026-06-29-搭上AI这条船/slides/s03/s03-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s04/s04-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s05/s05-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s06/s06-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s07/s07-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s08/s08-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s09/s09-v1-image.png` +- Problems: none +- Needs user: none +- Parent summary: Package 1 s03-s09 completed in production-light with direct child topology. Wrote v1 design, brief, prompt, and image for each assigned slide; updated `slides/slides.md` rows to production-pass. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-02/child-session-handoff.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-02/child-session-handoff.md new file mode 100644 index 0000000..8fdb8a6 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-02/child-session-handoff.md @@ -0,0 +1,11 @@ +# Child Session 02 Handoff + +- Status: complete +- Topology: direct-child +- Callback: ready-to-send-as-final-action +- Review mode: none +- Resolved versions: `s10-v1`; `s11-v1`; `s12-v1`; `s13-v1`; `s14-v1`; `s15-v1`; `s16-v1` +- Image paths: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s11/s11-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s12/s12-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s13/s13-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s14/s14-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s15/s15-v1-image.png`; `projects/2026-06-29-搭上AI这条船/slides/s16/s16-v1-image.png` +- Problems: none +- Needs user: none +- Parent summary: Completed formal production package 2 for `s10-s16` under production-light, direct-child, review none. Wrote design, brief, prompt, generated image, and updated `slides/slides.md` rows for all assigned pages. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-03/child-session-handoff.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-03/child-session-handoff.md new file mode 100644 index 0000000..808801d --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-03/child-session-handoff.md @@ -0,0 +1,11 @@ +# Child Session 03 Handoff + +- Status: complete +- Topology: direct-child +- Callback: ready-to-send-as-final-action +- Review mode: none +- Resolved versions: s17-v1; s18-v1; s19-v1; s20-v1; s21-v1; s22-v1; s23-v1; s24-v1 +- Image paths: projects/2026-06-29-搭上AI这条船/slides/s17/s17-v1-image.png; projects/2026-06-29-搭上AI这条船/slides/s18/s18-v1-image.png; projects/2026-06-29-搭上AI这条船/slides/s19/s19-v1-image.png; projects/2026-06-29-搭上AI这条船/slides/s20/s20-v1-image.png; projects/2026-06-29-搭上AI这条船/slides/s21/s21-v1-image.png; projects/2026-06-29-搭上AI这条船/slides/s22/s22-v1-image.png; projects/2026-06-29-搭上AI这条船/slides/s23/s23-v1-image.png; projects/2026-06-29-搭上AI这条船/slides/s24/s24-v1-image.png +- Problems: none blocking; s20 first generation was discarded for title typo and the copied image is the retry +- Needs user: none +- Parent summary: package 3 s17-s24 completed under production-light, direct-child topology, review none; design/brief/prompt/image files written append-only as v1 and slides/slides.md rows updated to production-pass. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/task-log.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/task-log.md new file mode 100644 index 0000000..d0dd015 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/task-log.md @@ -0,0 +1,24 @@ +# Task Log + +## Status + +- Current status: complete. + +## Dispatch / Callback Receipts + +- 2026-06-29 20:34 dispatch: session-01 `019f1360-8d74-7cf0-9ce3-59305fa7b43f`, package 1 `s03-s09`, line `production-light`, review `none`, callback target `019f1359-47c9-79e2-b7d4-3d461eb04e28`. +- 2026-06-29 20:57 callback: complete, direct-child, versions `s03-v1; s04-v1; s05-v1; s06-v1; s07-v1; s08-v1; s09-v1`, handoff `projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-01/child-session-handoff.md`, needs_user none. +- 2026-06-29 20:57 dispatch: session-02 `019f1375-ffe8-78b0-86b7-63c1429970bf`, package 2 `s10-s16`, line `production-light`, review `none`, callback target `019f1359-47c9-79e2-b7d4-3d461eb04e28`. +- 2026-06-29 21:23 callback: complete, direct-child, versions `s10-v1; s11-v1; s12-v1; s13-v1; s14-v1; s15-v1; s16-v1`, handoff `projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-02/child-session-handoff.md`, needs_user none. +- 2026-06-29 21:23 dispatch: session-03 `019f138d-5075-7c50-b23c-0f26954970f6`, package 3 `s17-s24`, line `production-light`, review `none`, callback target `019f1359-47c9-79e2-b7d4-3d461eb04e28`. +- 2026-06-29 21:49 callback: complete, direct-child, versions `s17-v1; s18-v1; s19-v1; s20-v1; s21-v1; s22-v1; s23-v1; s24-v1`, handoff `projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/session-03/child-session-handoff.md`, needs_user none, note `s20` first generation discarded for title typo and project image is the retry. + +## Slide Status Summary + +- Target scope: `s03-s24`. +- Completed in this production run: `s03-s24`. +- Next package: none. + +## Open Decisions + +- None. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/task-plan.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/task-plan.md new file mode 100644 index 0000000..a4e6912 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-formal-production/task-plan.md @@ -0,0 +1,33 @@ +# 2026-06-29 Formal Production + +## Active Scope + +- Line: production-light +- Worker profile: PPT-page-production-lite +- Running mode: prompt and generate +- Review mode: none +- Slides: s03-s24 +- Package split: s03-s09, s10-s16, s17-s24 +- Child session: session-03 complete / `019f138d-5075-7c50-b23c-0f26954970f6` / `子会话：AI船 s17-s24` +- Callback target: 019f1359-47c9-79e2-b7d4-3d461eb04e28 +- Write policy: append-only; overwrite allowed: no +- Status: complete + +## Context To Use + +- `AGENTS.md` +- `handoff/2026-06-29-ai-ship-formal-production-handoff.md` +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段5：P1-P24 单页设计骨架.md` + +## Stop Conditions + +- Artifact collision on any target `sNN-vN-*` path. +- Generated pages drift away from the accepted P01/P02 style. +- Text becomes too broken for internal meeting use. +- The deck drifts into customer proposal, government report, SaaS dashboard, or cyberpunk poster style. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-config.yaml b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-config.yaml new file mode 100644 index 0000000..1dc910e --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-config.yaml @@ -0,0 +1,29 @@ +watched_paths: + - "*.md" +status_fields: + - status + - lifecycle +forbidden_status_values: + - stable + - final + - released + - production-ready +warning_status_values: + - accepted + - confirmed +required_evidence_markers: + - user_decision + - evidence +approved_phrases: + - owner-approved + - ccra-approved + - production-ready + - final + - released +forbidden_phrases: + - production-ready +allowed_contexts: + - "Do not" + - "do not" + - "not an" + - "example:" diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-output/lifecycle-status-guard-scan.json b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-output/lifecycle-status-guard-scan.json new file mode 100644 index 0000000..21019d3 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-output/lifecycle-status-guard-scan.json @@ -0,0 +1,24 @@ +{ + "scan_root": "C:\\Users\\wangq\\Documents\\Codex\\video-workbench\\projects\\2026-06-29-搭上AI这条船\\handoff", + "config_path": "C:\\Users\\wangq\\Documents\\Codex\\video-workbench\\projects\\2026-06-29-搭上AI这条船\\tasks\\2026-06-29-visual-system-alignment\\lifecycle-guard-config.yaml", + "files_scanned": [ + "2026-06-29-ai-ship-formal-production-handoff.md" + ], + "possible_overclaims": [], + "field_level_findings": [], + "phrase_level_findings": [], + "missing_evidence_markers": [], + "warnings": [], + "blocking_errors": [], + "observations": [], + "machine_readable_summary": { + "status": "PASS", + "files_scanned_count": 1, + "field_finding_count": 0, + "phrase_finding_count": 0, + "missing_evidence_count": 0, + "warning_count": 0, + "blocking_count": 0, + "observation_count": 0 + } +} \ No newline at end of file diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-output/lifecycle-status-guard-scan.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-output/lifecycle-status-guard-scan.md new file mode 100644 index 0000000..1bf49f1 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/lifecycle-guard-output/lifecycle-status-guard-scan.md @@ -0,0 +1,25 @@ +# Lifecycle Status Guard Scan + +## Summary + +- Status: `PASS` +- Files scanned: 1 +- Blocking findings: 0 +- Warnings: 0 +- Evidence-present observations: 0 + +## Blocking Findings + +- None + +## Warnings + +- None + +## Observations + +- None + +## Files Scanned + +- `2026-06-29-ai-ship-formal-production-handoff.md` diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/task-log.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/task-log.md new file mode 100644 index 0000000..59af24c --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/task-log.md @@ -0,0 +1,20 @@ +# Task Log + +## Status + +- Current status: P01/P02 samples user-confirmed; formal production handoff ready. + +## Receipts + +- 2026-06-29 setup: user chose full-page visual-image-led PPT. +- 2026-06-29 setup: source charter path recorded as fact-check backup only. +- 2026-06-29 setup: visual-system files initialized; no image generation authorized. +- 2026-06-29 alignment: user approved unified deep blue-black AI route operation-map base across every page, with only light motif changes by page family. +- 2026-06-29 alignment: user approved P01 as both cover and public-style sample, then P02 as content-page sample; if both pass, move to production. +- 2026-06-29 design: wrote P01 and P02 design drafts for user review: `slides/s01/s01-v1-design.md`, `slides/s02/s02-v1-design.md`. +- 2026-06-29 generation: user approved both designs; main session wrote `s01-v1-brief.md`, `s01-v1-prompt.md`, `s02-v1-brief.md`, `s02-v1-prompt.md`; generated and copied images to `slides/s01/s01-v1-image.png` and `slides/s02/s02-v1-image.png`. Review files, child sessions, and completeness gates intentionally not used. +- 2026-06-29 decision: user confirmed both generated images passed and asked for a handoff document; next new session will start formal production. + +## Open Decisions + +- New clean session loads the formal production handoff and starts from P03 / `s03`. diff --git a/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/task-plan.md b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/task-plan.md new file mode 100644 index 0000000..14d7495 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/tasks/2026-06-29-visual-system-alignment/task-plan.md @@ -0,0 +1,50 @@ +# Visual-System Alignment Task + +## Status + +- Task id: `2026-06-29-visual-system-alignment` +- Worker profile: PPT-page-production pending; use direct main-session setup only. +- Running mode: design / prompt-system setup only. +- Status: active. + +## User Instruction + +The user selected a full-page visual-image-led PPT because this is a time-constrained internal meeting. Minor typos, font issues, and typography imperfections are acceptable. The next step is to create the project files / folders and align the `visual-system`. + +## Active Scope + +- Line: test/audit setup. +- Review mode: user alignment only. +- Slides: P01-P24 inventory only; no per-page production. +- Write policy: append-only; overwrite allowed: no. + +## Context To Use + +Project intake: + +- `../../intake/阶段3：搭上 AI 这条船PPT总纲.md` +- `../../intake/阶段4：通用表达与视觉系统.md` +- `../../intake/阶段5：P1-P24 单页设计骨架.md` +- `../../intake/阶段5：全局页面规则.md` +- `../../intake/阶段5：页面清单骨架.md` + +Backup source: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\AI智能化客户经营团队启动会议章程.md +``` + +## Expected Outputs + +- `../../project.md` +- `../../execution-plan.md` +- `../../visual-system/visual-system.md` +- `../../visual-system/style/style-prompt-master.md` +- `../../visual-system/motifs/motif-registry.md` +- `../../slides/slides.md` + +## Stop Conditions + +- Stop before image generation. +- Stop before writing per-page `design`, `brief`, or `prompt` files. +- Ask the user to confirm the visual-system direction before page production. diff --git a/projects/2026-06-29-搭上AI这条船/visual-system/motifs/motif-registry.md b/projects/2026-06-29-搭上AI这条船/visual-system/motifs/motif-registry.md new file mode 100644 index 0000000..3dfb313 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/visual-system/motifs/motif-registry.md @@ -0,0 +1,72 @@ +# Motif Registry + +## Status + +- Document status: draft for user alignment. +- Purpose: shared motif registry for the full-page visual-image-led PPT. +- Generation status: no image generation is authorized by this file. + +## Global Motif Rule + +All motifs should serve the same core metaphor: + +> 搭上 AI 这条船。 + +The deck should feel like a dark AI maritime operation map, not a literal cartoon story about boats. + +## Active Motifs + +| Motif | Visual Treatment | Meaning | Default Pages | +| --- | --- | --- | --- | +| AI 航线 | Glowing cyan route line over dark map / sea grid | From opportunity to action; from training to system | P01, P04, P13, P14, P23 | +| 船票 | Abstract boarding pass with gold edge / cyan data marks | Opportunity is available; first-week action card | P01, P09, P10, P24 | +| 雷达 | Circular scan, customer dots, risk / opportunity signals | Read people, situations, customers, and risks | P03, P09, P16, P19 | +| 罗盘 | Compass rose, direction calibration, route correction | Method, customer-fit model, reality calibration | P16, P20 | +| 港口 / 灯塔 | Distant lights on dark route | New AI entry has arrived | P01, P04, P13 | +| 登船坡道 | Ramp replacing high technical wall | Agentic era lowers entry barrier | P10, P12 | +| 航道闸门 | Narrowing lock gate / checkpoint | Training broad, consulting filtered, system strict | P15, P22 | +| 双轨 / 双航道 | Two parallel routes with sequencing | Exploration first, engineering later | P17 | +| 船舱 / 作战地图 | Functional compartments around customer journey | New team cooperation structure | P18, P19 | +| 校准罗盘 | Compass being corrected back to route | Wei Zheng mechanism / reality feedback | P20 | +| L0-L4 阶梯 | Navigation license / tiered ladder | Growth route, not instant title granting | P21 | +| 三道安全闸 | Three stamped gates / seals | Do not pretend, do not overpromise, do not push immature customers to system | P22 | +| 训练路线图 | Four-week route across dark map | One-month AI-enhanced customer operations training | P23 | +| 船员训练卡 | Boarding pass transformed into training worksheet | First-week personal AI goal | P24 | + +## Page-Family Motif Mapping + +| Family | Pages | Primary Motifs | Secondary Motifs | +| --- | --- | --- | --- | +| Opening / Consensus | P01-P03 | AI 航线, 船票, 雷达 | 港口 / 灯塔 | +| Pressure / Role Transition | P04-P07 | AI 航线, 港口, multi-engine route | center-node pressure map | +| Confidence / Agentic Entry | P08-P12 | 登船坡道, 雷达, 船票 | work-loop route | +| Business Path / Customer Judgment | P13-P17 | AI 航线, 航道闸门, 罗盘, 双轨 | service-stage nodes | +| Team Structure / Boundaries | P18-P22 | 船舱 / 作战地图, 校准罗盘, L0-L4 阶梯, 三道安全闸 | role icons | +| Training / Action | P23-P24 | 训练路线图, 船员训练卡 | 船票 | + +## Motif Constraints + +Use: + +- Abstract maps, route lines, radar glow, compass geometry, and ticket/card surfaces. +- Dark business cinematic atmosphere. +- Cyan for active AI signals. +- Gold for action, opportunity, and key commitments. + +Avoid: + +- Literal cute ships. +- Pirate, fantasy, or adventure-film ship styling. +- Overly realistic ocean disaster scenes. +- Stock-photo meeting rooms. +- Excessive UI dashboards. +- Random robot or AI face icons. +- Decorative motifs that do not support the page judgment. + +## Text Label Rule + +Motif labels should be short: + +- 2-8 Chinese characters preferred. +- 1 page title + 1 core judgment + 3-5 short labels maximum for most pages. +- If a page has more than 5 labels in the source skeleton, compress them before image prompt construction. diff --git a/projects/2026-06-29-搭上AI这条船/visual-system/style/style-prompt-master.md b/projects/2026-06-29-搭上AI这条船/visual-system/style/style-prompt-master.md new file mode 100644 index 0000000..a825367 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/visual-system/style/style-prompt-master.md @@ -0,0 +1,327 @@ +# Style Prompt Master + +## Status + +- Document status: active public-style base. +- Project: `2026-06-29-搭上AI这条船`. +- Purpose: reusable style prompt master for later full-page PPT image prompts. +- Scope: global style kernel, page-family modules, text-in-image policy, reference roles, forbidden drift. +- Generation status: no image generation is authorized by this file. + +This file defines what each page prompt should inherit. It does not replace per-page `sNN-vN-prompt.md` files. + +Accepted continuity rule: + +> Every page uses the same deep navy-black AI route operation-map base. Page families may vary motifs lightly, but not the base style. + +## Skill Mode Record + +Mode check command: + +```powershell +node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json +``` + +Result: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: + +- Use the `gpt-image-2` Skill as the prompt-engineering workflow. +- Garden local generation is not enabled. +- Do not call Garden generation scripts from this document. +- If later generation is requested, create or update the relevant per-page prompt/spec first, then follow the host-native image generation path. + +## Skill Template / Reference Basis + +Skill files read for this master: + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` + +Template adaptation: + +- `dense-explainer-slides.md` informs page-level structure and high-density one-page logic. +- `visual-report-page.md` informs business credibility and restrained executive visual language. +- `educational-diagram-slide.md` informs simple one-model explanation pages. +- `campaign-kv.md` informs consistent cross-page campaign-like visual identity. +- `title-safe-poster.md` informs large judgment text and readable slogan pages. + +## Project Sources Actually Used + +Project control: + +- `project.md` +- `execution-plan.md` +- `visual-system/visual-system.md` +- `visual-system/motifs/motif-registry.md` +- `slides/slides.md` + +Intake: + +- `intake/阶段3：搭上 AI 这条船PPT总纲.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P24 单页设计骨架.md` +- `intake/阶段5：全局页面规则.md` +- `intake/阶段5：页面清单骨架.md` + +Backup source recorded but not compressed into the visual system: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\AI智能化客户经营团队启动会议章程.md +``` + +## Global Style Kernel + +Every page prompt should inherit this kernel unless a later approved revision changes the visual system. + +Core visual definition: + +> Deep navy-black executive background, AI maritime route map, radar glow, compass and boarding-ticket motifs, cyan and gold signal highlights, internal kickoff war-map energy. + +Chinese working definition: + +> 深蓝黑商务底，AI 航线作战图，雷达光效，罗盘与船票母题，青色和金色信号高亮，内部启动会的开局感。 + +Default prompt kernel: + +```text +Create a 16:9 full-page visual slide image for an internal business kickoff meeting. Deep navy-black executive background, AI maritime route-map atmosphere, radar glow, compass lines, subtle grid and navigation marks, cyan signal light and restrained gold highlights. The page should feel like an AI boarding route / war map for a company team opening a new business line. High-energy but disciplined, cinematic business visual, not a customer proposal, not a training manual, not a generic SaaS dashboard. +``` + +Default text handling: + +```text +Include only short, large, high-contrast Chinese slide text: one main title, one core judgment, and a few short labels if needed. Text may be embedded in the image. Prioritize bold readable Chinese characters over decorative typography. Avoid long paragraphs. +``` + +Default negative drift: + +```text +Avoid government-report style, customer proposal deck, formal charter document, dense training manual, cute cartoon ship, pirate or fantasy ship, cyberpunk neon overload, generic tech dashboard UI, humanoid robots, stock-photo meeting people, concrete attendee portraits, childish illustration, pure gradient background, excessive UI cards, unreadable dense text, logos, watermarks. +``` + +## Page-Family Modules + +### Module A: Opening / Consensus + +Use for: + +- P01-P03 + +Reusable prompt module: + +```text +Opening and consensus page. Use a large dark AI航线 background, glowing route line, port lights, boarding-ticket or radar-center motif. The page should say: this is not another mobilization meeting; this is the moment the team boards together and turns the plan into shared consensus. Composition should be bold and ceremonial, but still internal and pragmatic. +``` + +Recommended motifs: + +- Ship ticket. +- Route line. +- Radar center. +- Shared boarding point. + +Avoid: + +```text +No government opening ceremony, no customer sales brochure, no literal crowd photo, no cartoon ship, no overly formal seal-heavy layout. +``` + +### Module B: Pressure / Role Transition + +Use for: + +- P04-P07 + +Reusable prompt module: + +```text +Pressure and transition page. Show old route pressure turning into a new AI route, or a single overloaded center node becoming a multi-engine navigation system. Use dark sea / port / route-map metaphors, with cyan active route and gold decision point. The emotion should be realistic pressure plus new opening, not pessimism. +``` + +Recommended motifs: + +- Old route vs new AI route. +- Single engine to multi-engine fleet. +- Center node pressure to distributed route map. + +Avoid: + +```text +No collapse disaster scene, no personal portrait hero, no complaint mood, no over-dramatic storm. +``` + +### Module C: Confidence / Agentic Entry + +Use for: + +- P08-P12 + +Reusable prompt module: + +```text +Confidence-building page for experienced salespeople entering the AI era. Use boarding ramp, lowered technical wall, radar reading customers, and AI work-loop motifs. The visual should communicate that old sales experience is not obsolete; it receives a new engine. Keep business confidence, not technical lecture. +``` + +Recommended motifs: + +- Boarding ramp instead of high wall. +- Radar over customer-organization dots. +- Natural-language task chain. +- Before-meeting / after-meeting AI work loop. + +Avoid: + +```text +No programmer worship, no code walls, no robot teacher, no mocking traditional sales, no dense technical architecture. +``` + +### Module D: Business Path / Customer Judgment + +Use for: + +- P13-P17 + +Reusable prompt module: + +```text +Business path and customer judgment page. Use a maritime route from "想用 AI" to "用好 AI", three-stage service route, funnel / lock gate, compass, and double-track exploration-to-engineering system. The page must feel like a practical navigation model that the team can use with clients. +``` + +Recommended motifs: + +- Route map with nodes. +- Three-stage path: 培训 -> 顾问 -> 系统. +- Funnel / lock gate. +- Four-direction compass. +- Double track / double channel. + +Avoid: + +```text +No generic sales funnel clipart, no crowded spreadsheet, no shiny software UI, no system architecture lecture. +``` + +### Module E: Team Structure / Boundaries + +Use for: + +- P18-P22 + +Reusable prompt module: + +```text +Team cooperation and boundary page. Use a ship-compartment / operation-map structure: expert, customer operations, AI business engineer, and deterministic engineering foundation around the customer intelligentization journey. Use calibration compass, role icons, L0-L4 ladder, and safety gates. The tone should be brotherly trust plus company discipline. +``` + +Recommended motifs: + +- Crew compartments. +- Five role icons. +- Compass correction. +- L0-L4 ladder /航行资格. +- Three safety gates. + +Avoid: + +```text +No stiff org chart, no HR policy page, no punishment board, no heavy compliance training look. +``` + +### Module F: Training / Action + +Use for: + +- P23-P24 + +Reusable prompt module: + +```text +Training and action page. Use a four-week training route and first-week AI training card / crew-member card. The page should close the meeting with immediate behavior: use AI before and after meetings, write a first-week training target, and start from oneself. +``` + +Recommended motifs: + +- Four-week route map. +- Crew training card. +- Checklist board. +- Boarding pass upgraded into first-week action card. + +Avoid: + +```text +No school homework cartoon, no dense course syllabus, no formal certification poster, no empty motivational slogan. +``` + +## Per-Page Prompt Requirements + +Every future `sNN-vN-prompt.md` should include: + +```text +Reference Inputs + +- Page: PNN / S-NN. +- Page family: A / B / C / D / E / F. +- Active style module: exact module from this file. +- Core motif: exact motif from visual-system/motifs/motif-registry.md. +- Main title: exact page title from P1-P24 skeleton. +- Core judgment: exact or compressed page conclusion. +- Text complexity: low / medium / high. +- Text-in-image note: minor text defects acceptable, but use short labels. +- Generation path note: host-native / Advisor; Garden expected: no. +``` + +Rules: + +- Page title and core conclusion come from `intake/阶段5：P1-P24 单页设计骨架.md`. +- Do not use the original charter as a page-generation source unless fact checking requires it. +- Do not invent new page order or new core conclusions. +- Do not turn pages into dense customer-facing proposal slides. +- Do not generate images before the user authorizes a slide scope and running mode. + +## Sample-Gate Plan + +The approved sample sequence is: + +| Page | Module | Reason | +| --- | --- | --- | +| P01 | A | Cover atmosphere, public base style, ship-ticket metaphor, route glow, title treatment. | +| P02 | A | First content-page sample: tests ordinary page readability and `不是 / 是` content structure under the same base. | + +Adjustment rule: + +- P01 common base issue: revise this master and `visual-system/visual-system.md`. +- P01 cover-only issue: revise P01 only. +- P02 content-system issue: revise this master and `visual-system/visual-system.md`. +- P02 page-only issue: revise P02 only. + +## Active Directory Policy + +Keep this file active in: + +```text +visual-system/style/style-prompt-master.md +``` + +Future process files, rejected variants, and discarded visuals belong under: + +```text +archive/ +``` diff --git a/projects/2026-06-29-搭上AI这条船/visual-system/visual-system.md b/projects/2026-06-29-搭上AI这条船/visual-system/visual-system.md new file mode 100644 index 0000000..02bfb31 --- /dev/null +++ b/projects/2026-06-29-搭上AI这条船/visual-system/visual-system.md @@ -0,0 +1,263 @@ +# Visual System + +## Source State + +This file merges the public visual guidance from the accepted intake files. It is an execution control file, not a duplicate of all intake text. + +Status: + +- Public visual base accepted by user. +- P01 is the first public-style and cover sample. +- P02 is the first content-page sample after P01 acceptance. + +Primary source files: + +- `../intake/阶段5：P1-P24 单页设计骨架.md` +- `../intake/阶段5：页面清单骨架.md` +- `../intake/阶段5：全局页面规则.md` +- `../intake/阶段4：通用表达与视觉系统.md` +- `../intake/阶段3：搭上 AI 这条船PPT总纲.md` + +Backup fact-check source: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\AI智能化客户经营团队启动会议章程.md +``` + +## Current Visual Definition + +> 深蓝黑商务底 + AI 航线作战图 + 雷达 / 罗盘 / 船票 / 路线图母题 + 青色与金色信号高亮。 + +Working visual sentence: + +> 这不是一份制度文件，而是一张上船前的 AI 作战航线图。 + +Accepted continuity rule: + +> 每页底板风格完全统一；页面家族只更换轻微母题，不改变底板气质。 + +## Deck Tone + +The tone should hold four feelings: + +1. 兴奋感：AI 这条船不是口号，已经有船票了。 +2. 信心感：参会者不是因为懂技术才被需要，而是因为懂人、懂局、懂客户。 +3. 秩序感：兄弟一起开新局，但未来必须公司化、流程化。 +4. 行动感：会后不空谈，马上进入第一周训练。 + +Language direction: + +> 自己人口吻 + 公司化骨架 + 战斗前夜的兴奋感。 + +## Format Rules + +- Output page: 16:9 full-page visual image. +- Page text may be embedded in the image. +- Minor typo / font / size issues are acceptable for this internal, time-constrained meeting use. +- Each page should still preserve one clear judgment. +- Best page structure: title + core judgment + one visual model / three short points / one relationship map. +- Do not copy long charter paragraphs into the page image. + +## Palette + +### Base + +- Deep blue-black. +- Dark navy. +- Near-black business background. +- Cool slate gray for secondary structures. + +### Signal Colors + +- Cyan / blue-green for AI signal, radar, route, and active paths. +- Gold / warm amber for key decisions, ship ticket, commitment, and action emphasis. +- White / pale blue for readable page titles and labels. + +### Avoid + +- Government-report red / gold heaviness. +- Bright cyberpunk neon. +- Cute cartoon palette. +- Customer-proposal clean white corporate SaaS look. +- Training-course pastel look. + +## Motif System + +| Motif | Meaning | Use | +| --- | --- | --- | +| 船票 | AI 时代的新机会已经出现 | P01, P09, P10, P24 | +| 上船 / 登船坡道 | 有意愿的人先进入训练和协作 | P01, P10, P12 | +| 航线 | 培训 -> 顾问 -> 系统；从想用 AI 到用好 AI | P01, P13, P14, P23 | +| 雷达 | 客户判断、风险识别、机会发现 | P03, P09, P16, P19 | +| 罗盘 | 方法论、客户适配模型、现实校准 | P16, P20 | +| 航道闸门 | 宽入口、严系统、客户筛选 | P15, P22 | +| 双轨 / 双航道 | 探索价值与工程兑现 | P17 | +| 船舱 / 作战地图 | 团队协作结构 | P18, P19 | +| 阶梯 / 航行资格 | L0-L4 成长路径 | P21 | +| 训练卡 / 船员卡 | 第一周 AI 训练目标 | P23, P24 | + +Detailed motif handling lives in: + +```text +visual-system/motifs/motif-registry.md +``` + +## Page Families + +### Family A: Opening / Consensus + +Pages: + +- P01-P03 + +Function: + +- Establish the meeting as a shared opening, not a command or customer report. + +Visual pattern: + +- Big dark route background. +- Ship-ticket or route-map hero. +- Radar-centered identity map. + +### Family B: Pressure / Role Transition + +Pages: + +- P04-P07 + +Function: + +- Convert anxiety and strong personal dependency into a reason for team upgrade. + +Visual pattern: + +- Old route vs new AI route. +- Single engine to multi-engine fleet. +- Central pressure node to distributed system. + +### Family C: Confidence / Agentic Entry + +Pages: + +- P08-P12 + +Function: + +- Make old sales experience feel newly valuable in the AI era. + +Visual pattern: + +- Traditional funnel vs customer journey route. +- Radar reading people / situation / timing. +- Boarding ramp replacing high technical wall. +- Work-loop diagram for using AI before and after meetings. + +### Family D: Business Path / Customer Judgment + +Pages: + +- P13-P17 + +Function: + +- Explain what the team sells and how customers should be filtered. + +Visual pattern: + +- Route map from "想用 AI" to "用好 AI". +- Three-stage route / stair: training, consulting, system. +- Funnel / lock gate. +- Four-direction compass. +- Double track: exploration then engineering. + +### Family E: Team Structure / Boundaries + +Pages: + +- P18-P22 + +Function: + +- Clarify cooperation, roles, calibration mechanism, growth route, and first bottom lines. + +Visual pattern: + +- Crew compartments around customer journey. +- Five role icons around boarding path. +- Compass correction / route calibration. +- L0-L4 ladder. +- Three safety gates / seals. + +### Family F: Training / Action + +Pages: + +- P23-P24 + +Function: + +- Move from shared confidence to first-week AI training behavior. + +Visual pattern: + +- Four-week route map. +- First-week training card / ship-member card. + +## Text Rendering Policy + +Because the selected route is full-page visual-image-led: + +- Let the image carry the main page title and key phrase when possible. +- Keep generated text short, bold, and central. +- Prefer labels of 2-8 Chinese characters over long sentences inside diagrams. +- Long lists should be simplified into fewer phrases before image generation. +- Do not spend production time on pixel-perfect typography unless the user requests repair. + +Risk note: + +- AI-generated Chinese text may be imperfect. This project accepts minor text defects, but page prompts should still reduce text complexity to avoid severe unreadability. + +## Forbidden Drift + +Avoid: + +- Customer proposal deck style. +- Formal archive charter page. +- Dense training manual. +- Government report. +- Cute ship cartoon. +- Pirate / fantasy ship. +- Generic tech dashboard UI. +- Cyberpunk neon city. +- Random humanoid robots. +- Concrete portraits of attendees. +- Excessive decorative gradients that replace the route / radar / compass logic. + +## Page Review Questions + +For each generated page image, ask only lightweight fit questions unless the user asks for deeper review: + +1. Does the page's first read match its core judgment? +2. Does it feel like an internal kickoff route map, not a customer proposal? +3. Is the AI航线 / 雷达 / 罗盘 / 船票 motif clear enough? +4. Does the page preserve confidence and action instead of becoming a rule lecture? +5. Is the text at least usable for an internal meeting? + +## Materialization Log + +| Date | Target | Result | Notes | +| --- | --- | --- | --- | +| 2026-06-29 | Extract merged visual system | initialized | Created from accepted intake; no images generated. | + +## Sample Adjustment Rule + +During P01 / P02 sampling: + +- Public style issue: update this file and `visual-system/style/style-prompt-master.md`. +- Page-specific issue: update only the relevant `slides/sNN/sNN-vN-*` artifacts. +- Do not turn one page's local correction into a global rule unless it affects later pages. + +## Next Action + +Create P01 / `s01` as the cover and public-style sample. diff --git a/projects/2026-07-01-为什么是我们/execution-plan.md b/projects/2026-07-01-为什么是我们/execution-plan.md new file mode 100644 index 0000000..ef8ceb7 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/execution-plan.md @@ -0,0 +1,68 @@ +# Execution Plan + +## Current Medium Branch + +- Branch: internal sales-alignment PPT full-page visual image production. +- Format: 16:9 horizontal. +- Main page count: 22. +- Output path: page images first, optional PPT assembly later. +- Prompt ownership: Codex owns final image prompts; intake files are source specification, not final prompts. +- Image workflow: `gpt-image-2` Advisor / host-native path only unless the user explicitly changes policy. + +## Current Execution Focus + +Production closeout: + +1. P01 / `s01`: cover sample passed. +2. P10 / `s10`: content anchor sample passed. +3. Remaining pages completed in packages of up to 8. +4. Final full-image PPTX assembled under `slides/`. + +The user explicitly authorized formal production after approving both validation images. + +## Validation Decision Rule + +| Result | Action | +| --- | --- | +| P01 has a common base-style issue | Revise `visual-system/` and regenerate append-only. | +| P01 has only a cover issue | Revise only `slides/s01/` append-only. | +| P10 has a content-page system issue | Revise `visual-system/` and `style-prompt-master.md`, then regenerate append-only. | +| P10 has only a local composition issue | Revise only `slides/s10/` append-only. | +| P01 and P10 pass | Enter production-light for remaining pages. | + +## Production Defaults After Validation + +| Item | Default | +| --- | --- | +| Line | production-light | +| Review | none | +| Carrier | clean child session if package production is requested | +| Scope source | `slides/slides.md` plus user-authorized package | +| Versioning | next unused `sNN-vN`; overwrite allowed: no | +| Fact-check source | backup only, never a PPT compression source | + +## Production Packages + +| Package | Scope | Child Session | Status | +| --- | --- | --- | --- | +| package-01 | S-02 through S-09 | `019f1b86-b337-7553-9084-610f0421e5e3` | complete | +| package-02 | S-11 through S-18 | `019f1b87-7dd8-7e91-b50e-7f2e25dd5464` | complete | +| package-03 | S-19 through S-22 | `019f1b88-4d73-79e1-bf4d-b59d7e79dfa0` | complete | + +## Current Round + +- R0: project intake files exist. +- R1: validation page selection aligned: P01 and P10. +- R2: project control files and visual system initialized. +- R3: P01 and P10 design / brief / prompt prepared for host-native generation. +- R4: P01 and P10 validation images generated and copied into project slide folders. +- R5: User confirmed P01/P10 passed; formal production packages authorized. +- R6: Three clean visible child sessions created and dispatched for S02-S09, S11-S18, and S19-S22. +- R7: package-03 callback received; S19-S22 verified present and recorded complete. +- R8: package-01 callback received; S02-S09 verified present, no review files found, and recorded complete. +- R9: package-02 callback received; S11-S18 verified present, no review files found, and recorded complete. Full P01-P22 image production is now complete. +- R10: assembled `slides/why-us-full-page-images.pptx`; artifact-tool import reported 22 slides; final render produced 22 PNG previews; `slides_test.py` passed with no overflow. + +## Open Decision + +Optional next steps: run user-directed visual sampling or route append-only repairs for any page the user marks unusable. diff --git a/projects/2026-07-01-为什么是我们/intake/阶段3：PPT 总纲 v1.md b/projects/2026-07-01-为什么是我们/intake/阶段3：PPT 总纲 v1.md new file mode 100644 index 0000000..a946f13 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/intake/阶段3：PPT 总纲 v1.md @@ -0,0 +1,201 @@ +# 《为什么是我们》PPT 总纲 v1 + +## 1. 这套 PPT 的定位 + +这套 PPT 是上一套《搭上 AI 这条船》的**前传 / 补充篇**。 + +上一套解决的是： + +> **我们怎么上船，怎么组队，怎么训练，怎么开始干。** + +这一套解决的是： + +> **为什么这艘船值得上？ +> 为什么不是平台？ +> 为什么不是普通 AI 开发公司？ +> 客户凭什么选我们？** + +原材料本身就是为回答销售团队提出的“为什么是我们”而写，核心问题包括：平台是不是也在做、AI 开发公司有什么区别、客户凭什么选择我们，以及我们的商业差异是否成立。 + +--- + +## 2. 标题建议 + +主标题已定： + +> **为什么是我们** + +副标题用： + +**当客户的问题进入 AI 深水区，谁来做专家智能体？** + +这个副标题和上一套“上船”体系呼应，也适合以后放到新销售招募会前面。 + +--- + +## 3. 核心主线 + +这套 PPT 的主线是： + +```text +销售提出了一个真问题 +↓ +市场上确实有平台，也有很多 AI 开发公司 +↓ +但客户真正难的，不是“工具怎么搭” +↓ +而是“该搭什么、为什么搭、专家经验怎么变成可运行能力” +↓ +我们的定位不是平台，不是外包，而是专家智能体的系统架构师与模具师 +↓ +客户选择我们，不是因为我们最大、最便宜，而是因为我们能进业务深水区 +↓ +但这个差异不是天然成立，必须靠案例、工具、流程、评测和团队复制能力证明 +↓ +所以后面要建设销售武器库 +``` + +一句话主轴： + +> **平台解决工具搭建，普通 AI 开发公司解决功能实现，我们解决专家能力工程化。** + +这也是原材料里最核心的判断。 + +--- + +## 4. 与上一套 PPT 的关系 + +建议以后新销售招募或培训时，顺序调整为： + +### 第一套：为什么是我们 + +回答： + +> 我们凭什么做这件事？ +> 客户凭什么选我们？ +> 销售凭什么有信心？ + +### 第二套：搭上 AI 这条船 + +回答： + +> 我们怎么组队？ +> 你们怎么参与？ +> 怎么训练？ +> 第一周怎么开始？ + +也就是说，这套 PPT 是**信心前置**，上一套 PPT 是**组织启动**。 + +--- + +## 5. 主金句库 + +可以分散放入页面： + +1. **平台解决工具怎么搭，我们解决专家能力怎么落地。** +2. **普通 AI 助手是会说话的工具，专家智能体是有岗位职责的数字员工。** +3. **客户真正难的不是没有工具，而是不知道该把什么变成智能能力。** +4. **简单 AI，客户自己用平台就可以；复杂专家智能体，才是我们该做的事。** +5. **我们不和平台抢工具，不和外包拼低价。** +6. **我们进入的是专家经验、业务判断、组织协同和系统落地的深水区。** +7. **商业差异不是喊出来的，是靠案例、工具、流程、评测和团队复制能力证明出来的。** +8. **销售武器库越成熟，销售越有底气。** + +--- + +## 6. PPT 模块结构 + +建议做 **22 页**，讲 30-40 分钟。 + +### 模块一：问题提出 + +| 页码 | 页面标题 | 页面功能 | 核心结论 | +| --: | --------- | ---- | ------------------------------- | +| P01 | 为什么是我们 | 封面 | 这次回答销售最关键的信心问题 | +| P02 | 销售问了一个真问题 | 问题引入 | 不是大家没信心，而是这个问题必须说透 | +| P03 | 三个必须回答的问题 | 建立议题 | 平台是不是也在做？AI 开发公司有什么区别？客户凭什么选我们？ | + +### 模块二：市场对照 + +| 页码 | 页面标题 | 页面功能 | 核心结论 | +| --: | ------------------- | ----- | ------------------------ | +| P04 | 先承认：平台很强，也很重要 | 防止自嗨 | 平台是工具箱、底座和供应商之一 | +| P05 | 平台解决“怎么搭”，不解决“该搭什么” | 平台差异 | 平台提供能力，但不自动完成场景判断和专家经验抽取 | +| P06 | 平台像工厂，我们像模具师 | 核心隐喻 | 工厂能生产，模具决定生产什么、精度在哪里 | +| P07 | 简单场景，客户自己用平台就可以 | 主动筛客户 | 简单问答、摘要、文案、普通自动化不一定需要我们 | + +### 模块三：我们定位 + +| 页码 | 页面标题 | 页面功能 | 核心结论 | +| --: | ---------------------- | ---- | ---------------------------- | +| P08 | 我们做的不是通用 AI 助手 | 定义边界 | 普通 AI 助手是工具，专家智能体是有岗位职责的数字员工 | +| P09 | 什么是专家智能体 | 建立概念 | 它要在具体岗位、场景、流程和责任边界中工作 | +| P10 | 我们是谁：专家智能体的系统架构师与模具师 | 定位揭晓 | 我们帮助企业把人脑里的专家能力变成组织可复用的智能能力 | +| P11 | 不是写提示词，而是专家能力工程化 | 反差页 | 只会调用模型，不等于会做专家智能体 | +| P12 | 普通 AI 开发公司的路径 vs 我们的路径 | 流程对比 | 前者做 AI 功能开发，后者做专家能力工程化 | + +原材料对专家智能体的定义很关键：它不是“什么都能聊”的通用助手，而是在具体岗位、具体场景、具体流程和责任边界中，具备专家视角、专家判断、专家表达和持续校准能力的数字员工。 + +### 模块四：客户为什么选择我们 + +| 页码 | 页面标题 | 页面功能 | 核心结论 | +| --: | ------------------- | ------ | ------------------------- | +| P13 | 客户选择我们，不是因为我们最大或最便宜 | 破除误解 | 我们不和平台抢工具，不和外包拼低价 | +| P14 | 我们能帮客户判断“该不该做 AI” | 价值理由 1 | 选对方向，是 AI 项目最重要的第一步 | +| P15 | 我们同时懂管理、信息化和 AI | 价值理由 2 | 我们的差异来自交叉能力，不是单一技术能力 | +| P16 | 我们能抽取专家经验，而不是只上传资料 | 价值理由 3 | 真正的专家经验很多不在文档里，而在人脑和组织经验里 | +| P17 | 我们先验证智能流，再投入系统建设 | 价值理由 4 | 不一上来重开发，先低成本确认价值 | +| P18 | 我们不只追求能跑，还追求好改 | 价值理由 5 | AI 出错后，要能发现、解释、纠正和沉淀 | + +这里的关键结论是：客户选择我们，不是因为我们有比大厂更大的平台，也不是因为我们比所有开发公司都便宜，而是因为我们知道怎样把企业里的专家经验、业务流程和组织判断，变成可运行、可校准、可落地的专家智能体。 + +### 模块五：清醒判断 + +| 页码 | 页面标题 | 页面功能 | 核心结论 | +| --: | ----------------- | ---- | ------------------------------------- | +| P19 | 我们的商业差异成立，但不是天然成立 | 坦诚页 | 差异必须靠案例、工具、流程、评测和团队复制能力证明 | +| P20 | 已经成立的部分 | 建立底气 | AI 学习、培训、管理咨询、信息化、智能体实践、方法论、团队雏形已经有基础 | +| P21 | 还没有完全成立的部分 | 建立清醒 | 案例、模板、成果、样板、产品包、反驳能力还要补 | + +原材料明确指出：我们的商业差异“成立，但不是天然成立”，必须通过案例、工具、流程、评测和团队复制能力证明。 + +### 模块六：销售武器库建设路线图 + +| 页码 | 页面标题 | 页面功能 | 核心结论 | +| --: | ---------------- | ---- | -------------------------------- | +| P22 | 销售武器库：从立场文件到作战工具 | 行动收束 | 后续要把定位、对比页、样板库、案例页、评测页、问答库做成销售工具 | + +销售工具部分建议不叫“待办清单”，而叫： + +> **销售武器库成熟度地图** + +内容包括： + +* 一页纸定位； +* 平台差异对比页； +* AI 开发公司差异对比页； +* 专家智能体样板库； +* 案例页； +* 评测页； +* 客户问答库； +* 标准话术卡； +* 不适合客户清单； +* 销售自检表。 + +原材料已经列出这些后续销售工具，包括一页纸定位、平台差异对比页、AI 开发公司差异对比页、专家智能体样板库、案例页和评测页。 + +--- + +## 关键页面建议 + +**最重要的 5 页** + +这套 PPT 的灵魂页是： + +1. **P05：平台解决“怎么搭”，不解决“该搭什么”** +2. **P06：平台像工厂，我们像模具师** +3. **P10：我们是谁：专家智能体的系统架构师与模具师** +4. **P12：普通 AI 开发公司的路径 vs 我们的路径** +5. **P19：商业差异成立，但不是天然成立** + +如果这 5 页立住，整套 PPT 就立住。 diff --git a/projects/2026-07-01-为什么是我们/intake/阶段4：通用表达与视觉系统.md b/projects/2026-07-01-为什么是我们/intake/阶段4：通用表达与视觉系统.md new file mode 100644 index 0000000..42cc7cf --- /dev/null +++ b/projects/2026-07-01-为什么是我们/intake/阶段4：通用表达与视觉系统.md @@ -0,0 +1,71 @@ +# 阶段4：通用表达与视觉系统 + +## 1. 表达任务 + +这套 PPT 要让销售形成三个判断： + +1. **不是只有我们在做 AI，但我们做的不是普通 AI。** +2. **客户不是因为我们有平台才选我们，而是因为我们能进业务深水区。** +3. **我们的差异有基础，但必须靠销售武器库继续证明。** + +--- + +## 2. 语言风格 + +沿用上一套风格： + +> **自己人口吻 + 公司化判断 + 战前校准感。** + +但这一套要比启动会更“硬”一点。 + +上一套是“上船”。 +这一套是“看清水深”。 + +关键词： + +* 不贬低平台； +* 不贬低开发公司； +* 不吹我们万能； +* 直接说清差异； +* 坦诚说短板； +* 最后落到工具建设。 + +--- + +## 3. 统摄性隐喻 + +延续“船”的系统，但从“上船”升级为： + +> **深水区 / 工具箱 / 模具师 / 航道判断** + +隐喻对应： + +| 隐喻 | 对应内容 | +| ---------- | ---------------- | +| 平台 | 工具箱、工厂、发动机、基础设施 | +| 普通 AI 开发公司 | 按图施工的功能开发队 | +| 我们 | 专家智能体的模具师、航道判断者 | +| 客户复杂问题 | AI 深水区 | +| 专家经验 | 藏在老师傅脑子里的模具 | +| 销售工具 | 船上的武器库、罗盘、雷达、航海图 | +| 商业差异 | 不是口号，是要被证明的航行能力 | + +--- + +## 4. 视觉基调 + +继续使用上一套： + +> **深蓝黑商务底 + AI 航线 + 雷达 + 罗盘 + 金色 / 青色高亮关键词。** + +这一套新增几个视觉母题： + +* 深水区； +* 工厂与模具； +* 平台工具箱； +* 专家模型剖面图； +* 销售武器库； +* 成熟度地图； +* 证据链。 + +--- diff --git a/projects/2026-07-01-为什么是我们/intake/阶段5：P1-P22 单页设计骨架.md b/projects/2026-07-01-为什么是我们/intake/阶段5：P1-P22 单页设计骨架.md new file mode 100644 index 0000000..7925e62 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/intake/阶段5：P1-P22 单页设计骨架.md @@ -0,0 +1,1786 @@ +# 《为什么是我们》P1-P22 单页设计骨架 v1 + +**副标题：当客户的问题进入 AI 深水区，谁来做专家智能体？** + +这套 PPT 是内部销售认知补丁，不是客户版，也不是对外宣传稿。它要回答销售在启动会后提出的三个关键问题：**平台是不是也在做？我们和 AI 开发公司有什么区别？客户凭什么选择我们？** 原材料的核心结论是：我们不是卖大模型、卖平台或卖普通 AI 功能，而是把企业里的专家经验、业务流程、组织判断和决策边界，工程化为可运行、可校准、可追踪、可落地的专家智能体。 + +--- + +## 一、全局页面规则 + +### 1. 页面气质 + +延续上一套《搭上 AI 这条船》的风格： + +> **深蓝黑商务底 + AI 航线 + 雷达 + 罗盘 + 金色 / 青色高亮关键词。** + +但这一套比启动会更“硬”。 + +上一套是： + +> **我们怎么上船。** + +这一套是： + +> **为什么这艘船值得上。** + +--- + +### 2. 统一视觉母题 + +本套 PPT 继续使用“船”的系统，但从“上船”升级为： + +> **深水区 / 工具箱 / 工厂 / 模具师 / 专家能力 / 销售武器库。** + +视觉对应： + +| 概念 | 视觉母题 | +| ---------- | ------------------ | +| 平台 | 工具箱、工厂、基础设施、发动机 | +| 普通 AI 开发公司 | 按图施工队、功能开发流水线 | +| 我们 | 模具师、航道判断者、专家智能体架构师 | +| 客户复杂问题 | AI 深水区 | +| 专家经验 | 藏在老师傅脑子里的模具 | +| 销售工具 | 武器库、罗盘、雷达、航海图 | +| 商业差异 | 证据链、成熟度地图 | + +--- + +### 3. 页面文字策略 + +这套是内部销售材料，页面文字可以比客户版更直接。 + +但每页仍然要遵守： + +> **一句大判断 + 一个核心图示 + 三到五个支撑点。** + +不要把原材料整段塞进页面。 +要把原材料变成销售能记住、能复述、能转成话术的判断。 + +--- + +### 4. 讲述策略 + +每页备注不需要完整讲稿，只保留： + +* 讲述关键词； +* 现场提醒； +* 过渡句； +* 容易讲偏的风险。 + +这套 PPT 的讲法要像一次内部校准会： + +> **不自嗨，不贬低别人，不吹万能，但要讲出我们真正的差异。** + +--- + +## 二、P1-P22 单页设计骨架 + +--- + +### P01：为什么是我们 + +#### 1. 本页功能 + +封面定调。 +把这套 PPT 从“启动会补充材料”提升为“销售信心前置课”。 + +#### 2. 页面核心结论 + +> **客户的问题一旦进入 AI 深水区，就不是简单买平台、找外包能解决的。** + +#### 3. 页面文字方向 + +主标题： + +> **为什么是我们** + +副标题： + +> **当客户的问题进入 AI 深水区，谁来做专家智能体？** + +底部小字： + +> 内部销售认知补充会 / 专家智能体销售立场文件 + +封面金句： + +> **简单 AI 工具，客户可以自己做；复杂专家智能体，才是我们该做的事。** + +#### 4. 页面结构 / Layout + +全屏封面。 + +画面中心是标题。 +背景是深蓝色“AI 深水区”航道。 +远处有一条船进入深海，海面下隐约有复杂的业务流程、组织结构、专家经验网络。 + +#### 5. 视觉资产设计 + +* 深蓝黑海面； +* 发光航线； +* 深水区分层； +* 雷达扫描； +* 远处灯塔； +* 半透明“专家智能体”结构图。 + +不要出现人物。 + +#### 6. 讲述关键词 + +* 上次讲的是怎么上船； +* 今天讲为什么是我们这艘船； +* 销售问的问题很对； +* 不说透，后面面对客户没底气。 + +#### 7. 承上启下 + +进入销售提出的问题： + +> 启动会上，大家问了一个真问题。 + +#### 8. 验收关注点 + +封面要和上一套视觉统一，但要更有“深水区”和“硬判断”的感觉。 + +--- + +### P02：销售问了一个真问题 + +#### 1. 本页功能 + +承认问题价值。 +让销售知道这不是质疑，而是进入真实市场前必须补上的认知。 + +#### 2. 页面核心结论 + +> **不是大家没信心，而是“为什么是我们”必须说透。** + +#### 3. 页面文字方向 + +标题： + +> **销售问了一个真问题** + +正文三句话： + +> 启动会解决了：我们怎么组队、怎么训练、怎么开始。 +> 但销售真正面对客户时，还会被追问：你们凭什么？ +> 这个问题不说透，销售就只能靠热情，不能靠判断。 + +底部金句： + +> **信心不是喊出来的，是把差异讲明白之后长出来的。** + +#### 4. 页面结构 / Layout + +左侧：上一套 PPT 的“上船”简化图。 +右侧：三个问号浮出水面。 + +三个问号： + +1. 平台是不是也在做？ +2. AI 开发公司有什么区别？ +3. 客户凭什么选择我们？ + +#### 5. 视觉资产设计 + +* 船已经离港； +* 前方出现三块礁石或三道关口； +* 每道关口对应一个销售问题。 + +#### 6. 讲述关键词 + +* 这不是抬杠； +* 这是销售未来一定会遇到的问题； +* 能问出来，说明大家开始进入真实作战状态； +* 这份材料就是补这个漏洞。 + +#### 7. 承上启下 + +下一页把三个问题正式列出来。 + +#### 8. 验收关注点 + +不能让销售觉得被批评。 +这一页要让他们感觉“你们问得对”。 + +--- + +### P03：三个必须回答的问题 + +#### 1. 本页功能 + +建立全套 PPT 的议题框架。 + +#### 2. 页面核心结论 + +> **我们必须同时回答平台、开发公司和客户选择三个问题。** + +#### 3. 页面文字方向 + +标题： + +> **三个必须回答的问题** + +三个问题卡片： + +> **1. 现有大模型 / Agent 平台是不是也在做？** +> Dify、Coze、Copilot Studio 等平台已经很强，我们的位置在哪里？ + +> **2. 我们和其他 AI 开发公司有什么区别？** +> 别人也能接模型、做知识库、写 Prompt、搭工作流，我们凭什么不同？ + +> **3. 客户凭什么选择我们？** +> 不是最大，不一定最便宜，那客户为什么愿意信我们？ + +底部短句： + +> **这三个问题回答不清，销售就没有真正的底气。** + +#### 4. 页面结构 / Layout + +三张问题卡片横排。 +每张卡片下面有一个图标： + +* 平台：工具箱； +* AI 开发公司：代码 / 工程图； +* 客户选择：握手 / 罗盘。 + +#### 5. 视觉资产设计 + +背景使用深色雷达屏。 +三个问题像雷达上锁定的三个目标。 + +#### 6. 讲述关键词 + +* 平台确实强； +* AI 开发公司也不少； +* 客户不会因为我们说自己好就买单； +* 今天就把这三件事摊开讲。 + +#### 7. 承上启下 + +先看第一个问题：平台到底强不强？ + +#### 8. 验收关注点 + +这页要清晰，不能加太多解释。 +它是目录页，也是问题框架页。 + +--- + +### P04：先承认：平台很强，也很重要 + +#### 1. 本页功能 + +避免自嗨。 +先承认平台价值，再讲我们的差异。 + +#### 2. 页面核心结论 + +> **平台是工具箱、底座和供应商之一，不是我们的敌人。** + +#### 3. 页面文字方向 + +标题： + +> **先承认：平台很强，也很重要** + +页面要点： + +> 现在的大模型平台、Agent 平台、低代码平台，已经能做很多事。 + +能力标签： + +> 模型调用 +> Prompt 配置 +> RAG 知识库 +> 工作流编排 +> 插件和工具调用 +> 多智能体协作 +> 发布渠道 +> 权限管理 +> 日志追踪 +> 基础评测 + +底部金句： + +> **我们不贬低平台，平台是我们的工具箱。** + +#### 4. 页面结构 / Layout + +中心是一个打开的“平台工具箱”。 +工具箱里放出多个能力模块。 + +#### 5. 视觉资产设计 + +* 工具箱； +* 模块积木； +* 平台能力图标； +* 深蓝背景上的发光模块。 + +可以点名平台： + +> Dify / Coze / Copilot Studio / 大模型平台 / Agent 平台 + +但点名放在角落，不要做成对抗。 + +#### 6. 讲述关键词 + +* 不能为了证明自己，就说平台不行； +* 平台越来越强； +* 我们以后也会使用平台； +* 先承认它强，后面差异才可信。 + +#### 7. 承上启下 + +平台强，但平台主要解决的是“怎么搭”。客户真正难的是“该搭什么”。 + +#### 8. 验收关注点 + +这一页要显得客观、成熟。 +不要出现“平台不行”的语气。 + +--- + +### P05：平台解决“怎么搭”，不解决“该搭什么” + +#### 1. 本页功能 + +讲清我们与平台的第一层差异。 + +#### 2. 页面核心结论 + +> **平台提供工具能力，我们提供场景判断和专家能力建模。** + +#### 3. 页面文字方向 + +标题： + +> **平台解决“怎么搭”，不解决“该搭什么”** + +左侧：平台能回答的问题 + +> 怎么接模型？ +> 怎么接知识库？ +> 怎么编排工作流？ +> 怎么调用工具？ +> 怎么发布给用户？ +> 怎么记录日志？ + +右侧：客户真正困难的问题 + +> 哪个场景值得做 AI？ +> 专家经验在哪里？ +> 老员工的隐性判断怎么抽取？ +> 业务规则怎么转译？ +> 哪些结果必须人工裁决？ +> AI 出错后怎么纠正？ +> 如何避免做成没人用的 AI 玩具？ + +底部金句： + +> **平台默认帮助客户实现想法，我们先帮助客户判断这个想法是否成立。** + +#### 4. 页面结构 / Layout + +左右对比页。 + +左侧是“工具层”。 +右侧是“业务深水区”。 +中间有一条从浅水到深水的分界线。 + +#### 5. 视觉资产设计 + +* 左侧：工具面板； +* 右侧：深水区剖面； +* 右侧海底有“专家经验、组织判断、业务规则、责任边界”等标签。 + +#### 6. 讲述关键词 + +* 平台解决运行能力； +* 但客户难在业务判断； +* 客户提出的需求不一定是真问题； +* 我们要先判断问题性质。 + +#### 7. 承上启下 + +用一个更容易懂的比喻：平台像工厂，我们像模具师。 + +#### 8. 验收关注点 + +这是核心页之一。 +必须让销售能复述这句话。 + +--- + +### P06：平台像工厂，我们像模具师 + +#### 1. 本页功能 + +用低阻抗隐喻讲透平台与我们的关系。 + +#### 2. 页面核心结论 + +> **工厂提供生产能力，模具决定生产什么、精度在哪里、能不能稳定产出。** + +#### 3. 页面文字方向 + +标题： + +> **平台像工厂，我们像模具师** + +页面比喻： + +> 平台是工厂： +> 有机器、流水线、生产能力。 + +> 我们是模具师： +> 判断要生产什么，设计模具结构，控制关键精度，持续校准产出。 + +底部金句： + +> **没有平台，很多东西跑不起来；只有平台，也可能做出一堆看起来智能、实际无效的东西。** + +#### 4. 页面结构 / Layout + +左侧：大型数字工厂。 +右侧：模具师设计精密模具。 +中间：产出结果对比。 + +结果对比： + +> 无模具：一堆泛化 AI 输出 +> 有模具：专家智能体稳定产出 + +#### 5. 视觉资产设计 + +* 工厂流水线； +* 精密模具剖面； +* AI 输出成品； +* 校准仪表盘。 + +#### 6. 讲述关键词 + +* 工厂很强； +* 但工厂不能替你决定生产什么； +* 模具决定精度； +* 我们做的是专家能力的模具。 + +#### 7. 承上启下 + +那么什么场景不需要我们？简单场景，客户自己用平台就可以。 + +#### 8. 验收关注点 + +这个隐喻要做得很直观。 +它是销售未来对客户解释平台差异的核心类比。 + +--- + +### P07：简单场景，客户自己用平台就可以 + +#### 1. 本页功能 + +主动筛掉不该做的客户和场景。 +建立专业感。 + +#### 2. 页面核心结论 + +> **我们不是什么 AI 都抢，简单 AI 工具客户自己做就可以。** + +#### 3. 页面文字方向 + +标题： + +> **简单场景，客户自己用平台就可以** + +适合客户自己做的场景： + +> 简单资料问答 +> 文档摘要 +> 周报生成 +> 普通客服机器人 +> 简单流程自动化 +> 通用文案生成 +> 内部资料检索 + +我们真正适合的场景： + +> 高专家密度 +> 高业务语境 +> 高判断复杂度 +> 高组织协同 +> 高校准需求 +> 高持续复盘价值 + +底部金句： + +> **简单 AI，不必找我们；复杂专家智能体，才是我们的场。** + +#### 4. 页面结构 / Layout + +上下分层。 + +上层：浅水区。 +下层：深水区。 + +浅水区放简单 AI 场景。 +深水区放专家智能体场景。 + +#### 5. 视觉资产设计 + +* 海面浅水区：轻量工具图标； +* 海底深水区：复杂业务网络、专家判断节点； +* 一条船从浅水驶向深水。 + +#### 6. 讲述关键词 + +* 不是所有客户都适合我们； +* 低价值、低复杂度的事，我们不抢； +* 销售以后要敢于判断不适合； +* 这不是退让，是专业。 + +#### 7. 承上启下 + +既然我们的战场是复杂场景，那我们做的到底不是普通 AI 助手。 + +#### 8. 验收关注点 + +这页要建立“我们不是什么都做”的清醒边界。 + +--- + +### P08：我们做的不是通用 AI 助手 + +#### 1. 本页功能 + +从市场常见“智能体”概念中切出我们的定义。 + +#### 2. 页面核心结论 + +> **普通 AI 助手是工具，专家智能体是有岗位职责的数字员工。** + +#### 3. 页面文字方向 + +标题： + +> **我们做的不是通用 AI 助手** + +市场上很多所谓智能体，可能只是： + +> 一个聊天窗口 +> 一个知识库问答 +> 一个提示词模板 +> 一个单智能体调用 +> 一个工作流自动化 +> 一个 API 封装 +> 一个前端页面加大模型接口 + +页面转折： + +> 这些当然也是 AI 应用，但它们离专家智能体还有距离。 + +底部金句： + +> **会回答，不等于会承担岗位职责。** + +#### 4. 页面结构 / Layout + +左侧：普通 AI 工具堆叠。 +右侧：专家智能体岗位卡片。 +中间用箭头标注“从工具到岗位”。 + +#### 5. 视觉资产设计 + +* 聊天窗口； +* 知识库； +* 工作流节点； +* API 图标； +* 数字员工岗位卡。 + +#### 6. 讲述关键词 + +* 现在很多东西都叫智能体； +* 但名字一样，深度差很多； +* 我们要把销售的嘴统一起来； +* 不要把专家智能体讲成普通聊天机器人。 + +#### 7. 承上启下 + +下一页正式定义：什么是专家智能体。 + +#### 8. 验收关注点 + +这页要把“普通 AI 助手”和“专家智能体”的距离拉开。 + +--- + +### P09：什么是专家智能体 + +#### 1. 本页功能 + +建立核心概念。 +让销售能用一句话讲清“专家智能体”。 + +#### 2. 页面核心结论 + +> **专家智能体是在具体岗位、场景、流程和责任边界中工作的数字员工。** + +#### 3. 页面文字方向 + +标题： + +> **什么是专家智能体** + +定义： + +> **专家智能体不是“什么都能聊”的通用助手，而是在具体岗位、具体场景、具体流程、具体责任边界中，具备专家视角、专家判断、专家表达和持续校准能力的数字员工。** + +四个关键词： + +> 岗位职责 +> 专家判断 +> 业务流程 +> 持续校准 + +底部金句： + +> **普通 AI 助手是会说话的工具；专家智能体是有岗位职责的数字员工。** + +#### 4. 页面结构 / Layout + +中心模型。 + +中心是“专家智能体”。 +四周环绕四个能力环： + +1. 岗位； +2. 场景； +3. 流程； +4. 边界。 + +外圈是： + +> 专家视角 / 专家判断 / 专家表达 / 持续校准 + +#### 5. 视觉资产设计 + +* 数字员工档案卡； +* 岗位说明书； +* 流程节点； +* 校准仪表盘； +* 专家能力光环。 + +#### 6. 讲述关键词 + +* 专家智能体不是万能； +* 它越具体越有价值； +* 它不是回答所有问题，而是在一个岗位上稳定工作； +* 核心是专家能力被封装进去。 + +#### 7. 承上启下 + +那我们是谁？我们就是帮助企业打造这种专家智能体的人。 + +#### 8. 验收关注点 + +定义可以长一点，但页面上要用关键词拆开，不要堆成一整段。 + +--- + +### P10：我们是谁：专家智能体的系统架构师与模具师 + +#### 1. 本页功能 + +正式揭晓我们的定位。 + +#### 2. 页面核心结论 + +> **我们帮助企业把人脑里的专家能力，变成组织可复用的智能能力。** + +#### 3. 页面文字方向 + +标题： + +> **我们是谁：专家智能体的系统架构师与模具师** + +页面主句： + +> **我们不是传统软件公司简单转型 AI，也不是只会调用大模型接口的 AI 外包团队。** + +定位句： + +> **我们是专家智能体的系统架构师与模具师。** + +对外直白版： + +> **我们帮助企业把“人脑里的专家能力”，变成“组织可复用的智能能力”。** + +底部金句： + +> **我们做的不是工具调用，而是专家能力工程化。** + +#### 4. 页面结构 / Layout + +三段式结构： + +左侧：人脑里的专家能力。 +中间：我们的方法论和模具。 +右侧：组织可复用的智能能力。 + +#### 5. 视觉资产设计 + +* 左侧：专家经验云团； +* 中间：模具 / 架构图 / 方法论引擎； +* 右侧：专家智能体岗位矩阵； +* 底部：组织流程接入线。 + +#### 6. 讲述关键词 + +* 这是我们最重要的定位； +* 我们不和平台抢工具； +* 不和外包拼低价； +* 我们做的是专家能力怎么被抽取、封装、验证、校准。 + +#### 7. 承上启下 + +这件事不是写几个提示词能完成的。 + +#### 8. 验收关注点 + +这是全套 PPT 的定位核心页。 +页面要稳、要有分量，不能花哨。 + +--- + +### P11：不是写提示词，而是专家能力工程化 + +#### 1. 本页功能 + +拆掉“你们是不是就是写 Prompt”的误解。 + +#### 2. 页面核心结论 + +> **只会调用模型，不等于会做专家智能体。** + +#### 3. 页面文字方向 + +标题： + +> **不是写提示词，而是专家能力工程化** + +左侧：表层 AI 开发 + +> 写角色设定 +> 写提示词 +> 接入模型 +> 加前端页面 +> 调用工具 +> 输出结果 + +右侧：专家智能体必须回答 + +> 它扮演什么岗位？ +> 专家模型来自哪里？ +> 依据什么判断？ +> 能力边界是什么？ +> 什么时候必须人工介入？ +> 错了如何解释和校准？ +> 如何接入真实流程？ +> 如何持续评测和迭代？ + +底部金句： + +> **如果只写一个提示词，那是 AI 表演，不是专家能力工程化。** + +#### 4. 页面结构 / Layout + +左右对比。 + +左侧是“表演层”。 +右侧是“工程化层”。 +中间一条分界线：从“能回答”到“能负责”。 + +#### 5. 视觉资产设计 + +* 左侧：舞台 / 聊天框 / Prompt 卡片； +* 右侧：工程剖面 / 责任边界 / 测评仪表盘； +* 中间：专家模型核心。 + +#### 6. 讲述关键词 + +* 写提示词有价值，但不够； +* 客户买的不是一句话； +* 客户要的是能进入流程的能力； +* 这就是我们和普通 AI 应用的差异。 + +#### 7. 承上启下 + +再对比普通 AI 开发公司的路径和我们的路径。 + +#### 8. 验收关注点 + +这一页要打掉误解，但不要显得看不起 Prompt。 +重点是“Prompt 只是入口，不是全部”。 + +--- + +### P12：普通 AI 开发公司的路径 vs 我们的路径 + +#### 1. 本页功能 + +通过流程对比讲清我们与 AI 开发公司的区别。 + +#### 2. 页面核心结论 + +> **前者做 AI 功能开发，后者做专家能力工程化。** + +#### 3. 页面文字方向 + +标题： + +> **普通 AI 开发公司的路径 vs 我们的路径** + +左侧：普通 AI 开发路径 + +```text +客户提出需求 +↓ +整理功能清单 +↓ +选模型 / 平台 +↓ +写 Prompt +↓ +做 RAG / 工作流 / 插件 +↓ +上线 +↓ +调试 +``` + +右侧：我们的路径 + +```text +客户提出业务困惑 +↓ +判断问题类型：Q / P / I +↓ +判断是否值得做 AI +↓ +抽取专家经验与业务逻辑 +↓ +定义专家智能体岗位 +↓ +明确能力、边界、流程、责任 +↓ +低成本验证智能流 +↓ +构建最小可用专家智能体 +↓ +进入试点场景 +↓ +持续校准 +↓ +必要时进入系统化建设 +``` + +底部金句： + +> **普通路径从功能开始，我们从问题性质开始。** + +#### 4. 页面结构 / Layout + +双流程图。 + +左侧流程短、直、偏工程。 +右侧流程长、分层、偏诊断和建模。 + +中间用大字区分： + +> AI 功能开发 +> vs +> 专家能力工程化 + +#### 5. 视觉资产设计 + +* 左侧：开发流水线； +* 右侧：深水探测 + 模具设计 + 小试点 + 系统化建设； +* 使用不同颜色强调两条路径。 + +#### 6. 讲述关键词 + +* 不是说别人不会开发； +* 是出发点不同； +* 他们问“客户要什么功能”； +* 我们问“客户真正的问题是什么”。 + +#### 7. 承上启下 + +讲完和平台、开发公司的差异，接下来回答：客户凭什么选我们？ + +#### 8. 验收关注点 + +流程右侧信息比较多，页面上可以只放关键节点，详细解释放讲述里。 + +--- + +### P13：客户选择我们，不是因为我们最大或最便宜 + +#### 1. 本页功能 + +破除错误竞争思路。 +避免销售把我们拖进拼价格、拼平台、拼功能的市场。 + +#### 2. 页面核心结论 + +> **我们不和平台抢工具，不和外包拼低价。** + +#### 3. 页面文字方向 + +标题： + +> **客户选择我们，不是因为我们最大或最便宜** + +页面三不： + +> 不因为我们有最大平台。 +> 不因为我们价格最低。 +> 不因为我们什么 AI 都能做。 + +页面三是： + +> 是因为我们能判断该不该做。 +> 是因为我们能抽取专家经验。 +> 是因为我们能让智能体进入业务流程并持续校准。 + +底部金句： + +> **客户选择我们，是因为我们能进业务深水区。** + +#### 4. 页面结构 / Layout + +左侧：错误竞争方式。 +右侧：正确价值理由。 + +左侧灰色： + +> 拼平台 / 拼低价 / 拼万能 + +右侧高亮： + +> 场景判断 / 专家抽取 / 智能流验证 / 持续校准 + +#### 5. 视觉资产设计 + +* 左侧：价格牌、平台 Logo 墙、功能清单； +* 右侧：深水区航道图； +* 一条船绕开价格战浅滩，驶向深水区。 + +#### 6. 讲述关键词 + +* 不要把自己讲成万能开发公司； +* 不要一上来和平台比能力； +* 我们的价值不在“更大更便宜”； +* 在更懂复杂业务场景怎么做。 + +#### 7. 承上启下 + +客户选择我们的第一个理由：我们能帮客户判断该不该做 AI。 + +#### 8. 验收关注点 + +这页要帮销售建立正确竞争姿态。 + +--- + +### P14：我们能帮客户判断“该不该做 AI” + +#### 1. 本页功能 + +客户价值理由 1：方向判断。 + +#### 2. 页面核心结论 + +> **选对方向，是 AI 项目最重要的第一步。** + +#### 3. 页面文字方向 + +标题： + +> **我们能帮客户判断“该不该做 AI”** + +客户常见误区： + +> 老板焦虑，觉得必须上 AI。 +> 听完一场课，觉得什么都能智能化。 +> 业务部门提一堆模糊需求。 +> 客户把组织问题误认为工具问题。 +> 客户以为买个系统就完成智能化。 + +我们要帮助客户判断： + +> 这个场景该不该做？ +> 适合培训、顾问、试点，还是系统？ +> 是简单问答、流程难题，还是组织课题？ +> 需要轻量工具，还是专家智能体？ +> 需要信息化补课，还是可以进入智能化建设？ + +底部金句： + +> **方向错了，后面越努力越浪费。** + +#### 4. 页面结构 / Layout + +决策罗盘页。 + +中心是： + +> 该不该做 AI？ + +四周是判断方向： + +* 场景价值； +* 组织认知； +* 信息化基础； +* 权力结构。 + +#### 5. 视觉资产设计 + +* 罗盘； +* 错误航线 vs 正确航线； +* AI 深水区前的“入海检查站”。 + +#### 6. 讲述关键词 + +* 很多客户不是不会做 AI； +* 是不知道什么值得做； +* 销售以后也要有这个判断意识； +* 不要客户说什么我们就接什么。 + +#### 7. 承上启下 + +第二个理由：我们同时懂管理、信息化和 AI。 + +#### 8. 验收关注点 + +这页要让销售明白：判断客户，比推产品更重要。 + +--- + +### P15：我们同时懂管理、信息化和 AI + +#### 1. 本页功能 + +客户价值理由 2：交叉能力。 + +#### 2. 页面核心结论 + +> **我们的差异来自管理咨询、信息化落地和 AI 智能化方法论的交叉能力。** + +#### 3. 页面文字方向 + +标题： + +> **我们同时懂管理、信息化和 AI** + +发展脉络： + +```text +企业管理咨询 +↓ +信息化系统落地 +↓ +AI 学习与科普 +↓ +专家智能体方法论 +↓ +企业智能化转型 +``` + +三类问题： + +> 管理问题：企业到底哪里需要智能化，哪里只是管理没做好。 +> 信息化问题：数据、流程、系统、权限、接口、运维能不能支撑落地。 +> AI 问题：哪些场景适合智能体，哪些必须人机协作，哪些不能做。 + +底部金句： + +> **很多团队只站在一个点上，我们站在三条线的交叉处。** + +#### 4. 页面结构 / Layout + +三圆交叉图。 + +三个圆： + +* 管理咨询； +* 信息化落地； +* AI 智能化。 + +交叉中心： + +> 专家智能体落地能力 + +#### 5. 视觉资产设计 + +* 三圆 Venn 图； +* 每个圆有对应图标； +* 中心高亮为“深水区判断能力”。 + +#### 6. 讲述关键词 + +* 我们不是单一技术路径； +* 不只是会讲课； +* 不只是会做系统； +* 不只是会用 AI； +* 是三者形成闭环。 + +#### 7. 承上启下 + +第三个理由：我们能抽取专家经验，而不是只上传资料。 + +#### 8. 验收关注点 + +这页要建立“综合能力”，不要讲成强哥履历展示。 + +--- + +### P16：我们能抽取专家经验，而不是只上传资料 + +#### 1. 本页功能 + +客户价值理由 3：专家经验抽取。 + +#### 2. 页面核心结论 + +> **不是把资料塞给 AI，而是把专家能力教给 AI。** + +#### 3. 页面文字方向 + +标题： + +> **我们能抽取专家经验，而不是只上传资料** + +页面对比： + +> 很多企业以为： +> 做 AI 知识库 = 把文档上传进去。 + +真正的专家经验在： + +> 老员工脑子里 +> 老板的判断习惯里 +> 高管的取舍标准里 +> 一线人员的隐性经验里 +> 客户经理的察言观色里 +> 项目经理的风险直觉里 +> 老师傅的现场判断里 +> 组织长期形成的潜规则里 + +底部金句： + +> **文档是知识的影子，专家判断才是能力本体。** + +#### 4. 页面结构 / Layout + +冰山图。 + +水面上： + +> 文档 / 资料 / 知识库 + +水面下： + +> 经验 / 判断 / 反例 / 取舍 / 边界 / 潜规则 + +右侧箭头： + +> 隐性经验 → 显性模型 → 专家智能体 + +#### 5. 视觉资产设计 + +* 冰山； +* 老师傅经验光点； +* 专家模型抽取管线； +* AI 可用结构。 + +#### 6. 讲述关键词 + +* 客户经常以为上传资料就够； +* 真正值钱的东西不在文件里； +* 在人的判断里； +* 我们要做思想考古，把隐性经验挖出来。 + +#### 7. 承上启下 + +第四个理由：我们不是一上来重开发，而是先验证智能流。 + +#### 8. 验收关注点 + +这页要让销售以后能解释：专家智能体为什么比知识库问答更深。 + +--- + +### P17：我们先验证智能流，再投入系统建设 + +#### 1. 本页功能 + +客户价值理由 4：低成本验证，避免重开发陷阱。 + +#### 2. 页面核心结论 + +> **很多 AI 项目失败，是因为太早开发。** + +#### 3. 页面文字方向 + +标题： + +> **我们先验证智能流，再投入系统建设** + +错误路径： + +```text +客户一说需求 +↓ +马上做页面 +↓ +接接口 +↓ +搭知识库 +↓ +写 Prompt +↓ +做系统 +↓ +最后发现没人用 +``` + +我们的原则： + +> 先用专家和 AI 工具跑通最小智能流。 +> 先确认场景真的有价值。 +> 再决定是否系统化建设。 + +底部金句： + +> **先跑通价值，再投入开发。** + +客户话术版： + +> “我们不会一上来让客户花大钱开发系统。我们会先用专家和 AI 工具跑通最小智能流，确认这个场景真的有价值，再决定是否系统化。” + +#### 4. 页面结构 / Layout + +两条路线图。 + +上面：重开发路线，红色风险标记。 +下面：智能流验证路线，绿色逐步推进。 + +#### 5. 视觉资产设计 + +* 上方：大型工程船直接冲进深水区，触礁； +* 下方：小型探测船先试航，再派工程船； +* 关键节点：试点、反馈、校准、系统化。 + +#### 6. 讲述关键词 + +* 客户容易一上来要系统； +* 我们不能被带着跑； +* 先验证价值是保护客户，也是保护我们； +* 这和上一套“培训可以宽，顾问要筛，系统必须严”是一致的。 + +#### 7. 承上启下 + +第五个理由：我们不只追求能跑，还追求好改。 + +#### 8. 验收关注点 + +这页要讲成专业方法，不要讲成“我们开发能力不足所以先试试”。 + +--- + +### P18：我们不只追求能跑，还追求好改 + +#### 1. 本页功能 + +客户价值理由 5：纠错与校准机制。 + +#### 2. 页面核心结论 + +> **AI 出错后，要能被发现、解释、纠正和沉淀。** + +#### 3. 页面文字方向 + +标题： + +> **我们不只追求能跑，还追求好改** + +很多 AI 项目失败，不是完全不能跑，而是： + +> 演示不错，长期不稳。 +> 输出看起来有道理，专家一看就知道不对。 +> 错在哪里说不清。 +> 用户不知道怎么改。 +> 改了以后系统不吸收。 +> 最后没人愿意用。 + +我们追求： + +> 可发现 +> 可解释 +> 可纠正 +> 可沉淀 +> 可迭代 + +底部金句： + +> **普通 AI 开发交付结果，我们交付结果，同时交付纠错机制和校准机制。** + +#### 4. 页面结构 / Layout + +闭环图。 + +```text +AI 输出 +↓ +专家审查 +↓ +用户反馈 +↓ +错误解释 +↓ +修正记录 +↓ +模型 / 流程 / 规则校准 +↓ +再次输出 +``` + +#### 5. 视觉资产设计 + +* 仪表盘； +* 反馈槽； +* 校准旋钮； +* 版本迭代曲线； +* 错误被捕获并进入数据仓。 + +#### 6. 讲述关键词 + +* AI 最怕黑盒； +* 客户真正担心的是错了怎么办； +* 我们的价值不是说 AI 永远不犯错； +* 而是错了能低成本改回来，并形成经验。 + +#### 7. 承上启下 + +除了交付智能体，过程中的修改、反驳、废弃也都是数据。 + +#### 8. 验收关注点 + +这页要让销售能回答客户：“你们怎么保证效果？AI 错了怎么办？” + +--- + +### P19：我们的商业差异成立，但不是天然成立 + +#### 1. 本页功能 + +内部清醒页。 +防止销售听完前面后开始过度自信。 + +#### 2. 页面核心结论 + +> **差异不是喊出来的，必须靠案例、工具、流程、评测和团队复制能力证明。** + +#### 3. 页面文字方向 + +标题： + +> **我们的商业差异成立，但不是天然成立** + +页面主句： + +> 我们有资格回答“为什么是我们”。 +> 但还不能靠口号成立。 + +差异成立需要五类证据： + +> 案例 +> 工具 +> 流程 +> 评测 +> 团队复制能力 + +底部金句： + +> **清醒的信心，比盲目的信心更值钱。** + +#### 4. 页面结构 / Layout + +证据链结构。 + +左侧： + +> 商业差异 + +右侧五个证据支柱： + +1. 案例； +2. 工具； +3. 流程； +4. 评测； +5. 复制。 + +每个支柱标注当前状态： + +> 有基础 / 待补齐 / 需产品化 + +#### 5. 视觉资产设计 + +* 深水航道上五座灯塔； +* 每座灯塔代表一个证明材料； +* 有些灯塔亮，有些正在建设。 + +#### 6. 讲述关键词 + +* 我们不能自满； +* 现在是立场成立，不等于市场已经完全证明； +* 销售必须知道哪些能讲，哪些还要补； +* 这不是泼冷水，是形成作战地图。 + +#### 7. 承上启下 + +那已经成立的部分有哪些？ + +#### 8. 验收关注点 + +这一页是内部版必须保留的关键页。 +客户版未来要换表达。 + +--- + +### P20：已经成立的部分 + +#### 1. 本页功能 + +建立底气。 +让销售知道“为什么是我们”不是凭空说出来的。 + +#### 2. 页面核心结论 + +> **我们已经具备回答“为什么是我们”的基础。** + +#### 3. 页面文字方向 + +标题： + +> **已经成立的部分** + +七项基础： + +> 1. 长期 AI 学习和写作积累 +> 2. AI 科普和培训经验 +> 3. 企业管理咨询背景 +> 4. 信息化系统落地背景 +> 5. 专家智能体实践 +> 6. HiFi Agent Studio 方法论抽象 +> 7. 团队分工雏形 + +底部金句： + +> **我们不是从零开始，而是把过去的积累汇到了一条新航线上。** + +#### 4. 页面结构 / Layout + +能力底座图。 + +底部是多年积累。 +上方托起“专家智能体商业能力”。 + +七个模块像船体的七块龙骨。 + +#### 5. 视觉资产设计 + +* 船体剖面； +* 七块结构龙骨； +* 每块写一项基础； +* 顶部是一艘“专家智能体”船。 + +#### 6. 讲述关键词 + +* 管理咨询不是过去式； +* 信息化也不是过去式； +* AI 学习、培训、智能体实践都汇在一起； +* 这才形成今天的定位。 + +#### 7. 承上启下 + +但还没有完全成立的部分，也必须说清。 + +#### 8. 验收关注点 + +不要讲成个人履历。 +要讲成团队商业差异的能力底座。 + +--- + +### P21：还没有完全成立的部分 + +#### 1. 本页功能 + +建立清醒感和后续工作必要性。 + +#### 2. 页面核心结论 + +> **差异要变成销售武器，还需要产品化、证据化、标准化。** + +#### 3. 页面文字方向 + +标题： + +> **还没有完全成立的部分** + +需要补齐： + +> 可展示案例 +> 可复用模板 +> 可量化成果 +> 可复制团队能力 +> 可演示样板 +> 可交付产品包 +> 可回答反驳 + +底部金句： + +> **没有资产沉淀，差异就只能停留在我嘴里。** + +#### 4. 页面结构 / Layout + +成熟度仪表盘。 + +每个能力一条进度条： + +| 能力 | 当前状态 | +| ---- | ---- | +| 案例 | 待整理 | +| 模板 | 待产品化 | +| 成果指标 | 待量化 | +| 团队复制 | 待培养 | +| 样板演示 | 待筛选 | +| 产品包 | 待成型 | +| 反驳问答 | 待训练 | + +#### 5. 视觉资产设计 + +* 销售武器库半成品； +* 有些武器已经入库，有些还在制造； +* 成熟度仪表盘； +* 待补齐清单。 + +#### 6. 讲述关键词 + +* 不是现在不能卖； +* 是要边卖边沉淀武器； +* 销售必须知道自己手里有什么，缺什么； +* 缺的东西就是后续工作重点。 + +#### 7. 承上启下 + +最后一页，把这些缺口变成销售武器库建设路线图。 + +#### 8. 验收关注点 + +这页不要泄气，要讲成“武器库建设中”。 + +--- + +### P22：销售武器库：从立场文件到作战工具 + +#### 1. 本页功能 + +行动收束。 +把“为什么是我们”转化为后续销售工具建设路线图。 + +#### 2. 页面核心结论 + +> **销售武器库越成熟，销售越有底气。** + +#### 3. 页面文字方向 + +标题： + +> **销售武器库：从立场文件到作战工具** + +副标题： + +> **哪些已经有，哪些正在补，哪些决定我们能不能复制。** + +武器库模块： + +> 1. 一页纸定位 +> 2. 平台差异对比页 +> 3. AI 开发公司差异对比页 +> 4. 专家智能体样板库 +> 5. 案例页 +> 6. 评测页 +> 7. 客户问答库 +> 8. 标准话术卡 +> 9. 不适合客户清单 +> 10. 销售自检表 + +页面收束金句： + +> **今天先把立场讲清楚，后面把立场做成武器。** + +最终内部共识： + +> **我们不是去和平台抢工具，不是去和外包公司拼低价，也不是去证明我们什么 AI 都能做。 +> 我们要证明的是：当客户的问题进入专家经验、业务判断、组织协同和系统落地的深水区时，我们比单纯平台、普通 AI 开发和传统软件转型团队，更知道该怎么把它做成。** + +#### 4. 页面结构 / Layout + +销售武器库成熟度地图。 + +左侧：当前已有立场文件。 +中间：正在建设的销售工具。 +右侧：未来能复制的销售体系。 + +可以分三层： + +| 层级 | 工具 | 作用 | +| --- | ------------------- | ------ | +| 立场层 | 一句话定位、三句话版本、标准回答 | 让销售说得清 | +| 证明层 | 案例、样板、评测、成果数据 | 让客户信得过 | +| 作战层 | 问答库、话术卡、自检表、不适合客户清单 | 让团队能复制 | + +#### 5. 视觉资产设计 + +* 武器库墙； +* 每个工具是一件装备； +* 已有工具亮起； +* 待补工具半透明； +* 最终形成“销售作战系统”。 + +#### 6. 讲述关键词 + +* 这份 PPT 不是终点； +* 它是销售工具体系的第一块； +* 后面要把它拆成客户话术、对比页、案例页、问答库； +* 销售以后不是靠临场发挥，而是靠武器库作战。 + +#### 7. 承上启下 + +本页可以直接结束，也可以进入现场讨论： + +> 哪些销售工具最急？ +> 哪些问题客户最可能问？ +> 哪些样板最适合先整理？ + +#### 8. 验收关注点 + +最后一页必须有行动感。 +不要只收在口号，要让大家看到后续工具建设方向。 + +--- + +## 三、备份页建议 + +这套主 PPT 是 22 页，已经足够讲 30-40 分钟。 +但可以准备 5 页备份页，不主动讲，现场有人问再打开。 + +### B01：平台差异对比页 + +对比： + +| 对比项 | 大模型 / Agent 平台 | 我们 | +| ---- | --------------- | ------------------- | +| 核心能力 | 模型、工具、工作流、发布 | 场景诊断、专家模型、业务转译、校准落地 | +| 解决问题 | 怎么搭 | 该搭什么、为什么这样搭 | +| 适合场景 | 通用问答、流程自动化、工具调用 | 专家经验、业务判断、复杂组织场景 | +| 交付重点 | 平台能力 | 专家智能体与落地闭环 | +| 风险 | 工具有了但没人用 | 先验证价值再系统化 | + +--- + +### B02：AI 开发公司差异对比页 + +对比： + +| 对比项 | 普通 AI 开发公司 | 我们 | +| ---- | ----------------- | ----------------- | +| 出发点 | 客户需求 / 功能清单 | 业务困惑 / 专家能力 | +| 核心动作 | 写 Prompt、接模型、做工作流 | QPI 定性、专家抽取、智能流验证 | +| 交付物 | AI 功能、知识库、机器人 | 专家智能体、校准机制、业务闭环 | +| 成功标准 | 能跑、能回答 | 能用、好改、可持续校准 | +| 失败风险 | 演示好、落地弱 | 通过前置诊断降低失败 | + +--- + +### B03：销售标准回答 + +客户问： + +> 你们和平台有什么区别？ + +销售回答： + +> “现在很多平台都能搭智能体，这个我们不否认。平台解决的是工具问题，比如模型、知识库、工作流、插件、发布和运行。 +> +> 但企业真正难的地方，往往不是工具，而是：到底哪个场景值得做？专家经验怎么抽取？业务规则怎么转译？AI 出错后怎么纠正？怎么进入流程？怎么让员工真的用起来？ +> +> 我们的核心不是卖一个通用 AI 工具，而是帮助企业把专家能力、业务流程和组织经验，封装成可运行、可校准、可迭代的专家智能体。 +> +> 如果只是简单问答和普通自动化，客户自己用平台就可以；如果涉及管理、业务判断、专家经验和系统落地，那才是我们真正擅长的。” + +--- + +### B04：不该怎么说 + +不建议销售这样说： + +> 平台不灵活，所以选我们。 +> LLM 厂家不和我们竞争。 +> 我们比其他 AI 开发公司更懂 AI。 +> 我们什么 AI 都能做。 +> 我们有一套理论。 + +建议换成： + +> 平台在工具层很强，但不会自动替客户完成专家经验抽取、业务场景判断和持续校准。 +> 大模型厂商是上游供应商和生态伙伴，但通常不会深入每个客户的业务现场。 +> 我们不是从 AI 功能开发出发，而是从专家能力工程化出发。 +> 简单 AI 客户自己用平台就可以；复杂专家智能体才是我们的场。 +> 我们有一套从实践中形成的专家智能体建设方法。 + +--- + +### B05：最适合与不适合我们的客户 + +最适合： + +> 老板或高层真正重视 AI； +> 有一定信息化基础； +> 有数据、资料、流程或知识积累； +> 有高专家密度岗位； +> 有复杂业务判断场景； +> 愿意让专家参与共创； +> 愿意从培训、顾问、试点逐步推进。 + +不适合： + +> 只想免费听课； +> 只想套方案； +> 只比价格； +> 不愿提供资料； +> 不愿让专家参与； +> 没有项目负责人； +> 信息化基础极弱又想直接智能化； +> 只想做演示，不考虑落地； +> 要求 AI 承担不可承担的最终责任。 + +金句： + +> **我们宁可少做项目，也不能做错项目。** diff --git a/projects/2026-07-01-为什么是我们/project.md b/projects/2026-07-01-为什么是我们/project.md new file mode 100644 index 0000000..14f3610 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/project.md @@ -0,0 +1,139 @@ +# 2026-07-01-为什么是我们 + +## Status + +- Status: P01-P22 full-page image production completed via production-light child sessions. +- Medium type: 16:9 internal sales-alignment PPT. +- Output direction: full-page visual-image-led deck. +- Current phase: PPT assembly complete. +- Next phase: user visual sampling or append-only repairs if requested. +- Review default after validation: none, unless the user requests append-only repair. + +## Positioning + +This deck is the prequel / confidence-fronting deck for `2026-06-29-搭上AI这条船`. + +The previous deck answered: + +> 我们怎么上船，怎么组队，怎么训练，怎么开始干。 + +This deck answers: + +> 为什么这艘船值得上？为什么不是平台？为什么不是普通 AI 开发公司？客户凭什么选我们？ + +The deck is an internal sales cognition and confidence alignment file. It is not a customer proposal and not a full re-compression of source material. + +## Fixed Mainline + +The P1-P22 story line is fixed: + +```text +问题提出 → 市场对照 → 我们定位 → 客户选择理由 → 内部短板 → 销售武器库建设路线图 +``` + +The final portable internal consensus is: + +> 平台解决工具怎么搭，普通 AI 开发公司解决功能怎么做，我们解决专家能力怎么被抽取、封装、验证、校准，并进入客户真实业务流程。 + +## Source Hierarchy + +Primary deck authority: + +1. `intake/阶段5：P1-P22 单页设计骨架.md` +2. `intake/阶段3：PPT 总纲 v1.md` +3. `intake/阶段4：通用表达与视觉系统.md` + +Style continuity reference: + +```text +../2026-06-29-搭上AI这条船/visual-system/ +../2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png +../2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png +``` + +Backup fact-check source only: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\为什么是我们.md +``` + +Fact-check rule: + +> 原材料只作事实校验，不允许重新压缩成 PPT，不允许新增大段原文，不允许改变 P1-P22 主线。 + +The backup source has not been used to create the validation pages. It should be opened only when a factual claim in the accepted intake needs verification. + +## Visual Direction + +Continue the accepted previous deck base: + +> 深蓝黑商务底 + AI 航线 + 雷达 + 罗盘 + 金色 / 青色高亮关键词。 + +This deck should be harder and more sober than the kickoff deck: + +> 上一套是“上船”；这一套是“看清水深”。 + +Working visual sentence: + +> 深蓝黑 AI 航线作战图底板上，进入更深的业务水域：平台是工具箱，普通 AI 开发公司是施工队，我们是专家智能体的系统架构师与模具师。 + +## Validation Scope + +The user authorized two validation pages: + +| Slide | Role | Validation Target | +| --- | --- | --- | +| P01 / S-01 | Cover | Tests the harder prequel cover tone: deepwater, title, route-map base, sales confidence framing. | +| P10 / S-10 | Content anchor | Tests the core positioning page: expert capability extraction, molding, validation, calibration, and workflow entry. | + +The validation stage did not require completeness or broad quality checks. On 2026-07-01, the user confirmed P01 and P10 passed and authorized formal production. + +## Operating Defaults + +| Item | Default | +| --- | --- | +| Current line | production-light | +| After validation | production-light active | +| Running mode | prompt and generate | +| Review mode | user sample check only; no routine review file | +| Write policy | append-only; overwrite allowed: no | +| Image prompt workflow | `gpt-image-2` Advisor / host-native Mode B | +| Generated media policy | keep Markdown control files in Git; generated images are asset-layer files recorded by path | + +## Generated Validation Outputs + +| Slide | Project Image Path | Host Default Source | +| --- | --- | --- | +| S-01 | `slides/s01/s01-v1-image.png` | `C:\Users\wangq\.codex\generated_images\019f1b6b-387f-7be2-af0a-03761085cdae\ig_03b93517b169e69c016a44798e01f481918324c93b7cc1cdef.png` | +| S-10 | `slides/s10/s10-v1-image.png` | `C:\Users\wangq\.codex\generated_images\019f1b6b-387f-7be2-af0a-03761085cdae\ig_08ab80c795c4cfff016a447a1cae588191ae265e781d9dca16.png` | + +## Assembled Deck + +| Artifact | Path | Notes | +| --- | --- | --- | +| PPTX | `slides/why-us-full-page-images.pptx` | 22 slides; one full-slide image per page. | + +Assembly verification: + +- The PPTX was exported with `@oai/artifact-tool`. +- The exported PPTX was re-imported successfully with 22 slides. +- Final rendering produced 22 preview PNGs in scratch. +- `slides_test.py` passed with no overflow detected. + +## Production Packages + +Parent callback target: + +```text +019f1b6b-387f-7be2-af0a-03761085cdae +``` + +| Package | Scope | Status | Notes | +| --- | --- | --- | --- | +| package-01 | S-02 through S-09 | complete from `019f1b86-b337-7553-9084-610f0421e5e3` | 8-page ordinary production package. Handoff: `tasks/2026-07-01-production-dispatch/package-01-handoff.md`. | +| package-02 | S-11 through S-18 | complete from `019f1b87-7dd8-7e91-b50e-7f2e25dd5464` | 8-page ordinary production package. Handoff: `tasks/2026-07-01-production-dispatch/package-02-handoff.md`. | +| package-03 | S-19 through S-22 | complete from `019f1b88-4d73-79e1-bf4d-b59d7e79dfa0` | 4-page closing package. Handoff: `tasks/2026-07-01-production-dispatch/package-03-handoff.md`. | + +## Next Action + +PPT assembly is complete. Next work is user visual sampling or append-only repair for any page the user marks unusable. diff --git a/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-brief.md new file mode 100644 index 0000000..a3237c6 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-brief.md @@ -0,0 +1,61 @@ +# S-01 Slide Brief V1 + +## Page + +- Page: P01 / S-01. +- Title: 为什么是我们. +- Function: cover. +- Core conclusion: 客户的问题一旦进入 AI 深水区，就不是简单买平台、找外包能解决的。 + +## Source Basis + +Primary sources: + +- `intake/阶段5：P1-P22 单页设计骨架.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` + +Style references: + +- previous deck visual system; +- previous deck accepted cover image. + +Backup fact-check source: + +- not used. + +## Visible Text + +Main title: + +> 为什么是我们 + +Subtitle: + +> 当客户的问题进入 AI 深水区，谁来做专家智能体？ + +Bottom line: + +> 简单 AI 工具，客户可以自己做；复杂专家智能体，才是我们该做的事。 + +Small label: + +> 内部销售认知补充会 / 专家智能体销售立场文件 + +## Visual Requirements + +- 16:9 full-page visual image. +- Deep navy-black executive AI route-map base. +- Deepwater cross-section under the route map. +- Cyan route line and radar scan. +- Restrained gold lighthouse / signal point. +- Underwater abstract business-process / expert-experience networks. +- No people. +- No literal large ship as main subject. + +## Generation Notes + +- Current `gpt-image-2` mode: `B-or-C`. +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Review mode: user validation only. diff --git a/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-design.md new file mode 100644 index 0000000..189b8ca --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-design.md @@ -0,0 +1,92 @@ +# S-01 Slide Design V1 + +## Status + +- Status: validation design. +- Source page: P01. +- Page title: 为什么是我们. +- Role: cover and shared visual-base validation. +- Line: validation sample. +- Write policy: append-only; overwrite allowed: no. + +## Design Purpose + +本页验证这套前传 PPT 是否能在继承上一套视觉底盘的同时，切换到更硬、更清醒的销售立场。 + +它要一次性说明： + +1. 这不是上一套“搭上 AI 这条船”的重复动员； +2. 这次要回答“客户凭什么选我们”的信心问题； +3. 画面要从“上船”升级为“进入 AI 深水区”。 + +## Visual Concept + +画面是一张深蓝黑的 AI 深水区航线作战图。 + +底层延续上一套的数字海面、航线、雷达、罗盘、青色信号线和金色重点光，但这次海面下方要能隐约看到更复杂的业务网络、流程节点、组织判断和专家经验结构。远处仍有灯塔或航线终点，但情绪不再是兴奋出发，而是进入深水前的判断与定位。 + +主标题“为什么是我们”必须是第一视觉。副标题说明问题进入深水区后，需要回答谁来做专家智能体。画面可以保留一条船或航线，但不要让船成为主角；主角是“深水区”和“判断问题”。 + +## Text / Typography Plan + +Main title: + +> 为什么是我们 + +Subtitle: + +> 当客户的问题进入 AI 深水区，谁来做专家智能体？ + +Bottom line: + +> 简单 AI 工具，客户可以自己做；复杂专家智能体，才是我们该做的事。 + +Small label: + +> 内部销售认知补充会 / 专家智能体销售立场文件 + +Typography: + +- bold modern Chinese sans-serif; +- main title largest, white or pale-blue; +- `AI 深水区` may use cyan; +- `专家智能体` or key signal may use restrained gold; +- avoid decorative calligraphy. + +## Layout + +- Main title: center-left or center, occupying the clearest safe area. +- Subtitle: directly below title, one readable line. +- Deepwater visual: lower half, showing layered business/process/expert networks. +- Route/radar: diagonal or curved cyan path from foreground toward distant light. +- Lighthouse or port light: small, far-distance, warm-gold. +- Small label: upper-right or upper-left. +- Bottom line: bottom safe zone, not too small. + +Visual priority: + +1. 主标题； +2. 深水区层次； +3. 副标题； +4. 航线 / 雷达； +5. 底部金句。 + +## Constraints / Avoid + +Must avoid: + +- making it look like another kickoff cover; +- cute ship, literal cruise ship, pirate or fantasy ship; +- humanoid robots, AI faces, stock meeting people; +- customer proposal style; +- government report style; +- pure gradient background without route / deepwater logic; +- long text blocks or copied raw-source paragraphs. + +## Validation Focus + +User should check: + +1. Does the cover feel like the prequel to the previous deck? +2. Is it harder and more sober than the old “上船” deck? +3. Does the first read clearly answer the deck title and deepwater premise? diff --git a/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-prompt.md new file mode 100644 index 0000000..d132822 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s01/s01-v1-prompt.md @@ -0,0 +1,74 @@ +# S-01 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s01-v1-brief.md`. +- Review mode: user validation only. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P01 / S-01. +- Page family: A / Opening / Problem. +- Active style module: `visual-system/style/style-prompt-master.md`, Module A. +- Core motifs: AI 深水区, AI 航线, 雷达问题锁定, lighthouse signal. +- Main title: `为什么是我们` +- Core judgment: `客户的问题一旦进入 AI 深水区，就不是简单买平台、找外包能解决的。` +- Text complexity: low. +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Effective route: Mode B, host-native image generation. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` + - `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` +- Style reference images loaded into context: + - Image 1: previous accepted cover style, `../2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png`, role = style continuity reference only. + - Image 2: previous accepted content style, `../2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png`, role = style continuity reference only. +- Backup raw material source: not used. + +## Final Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page cover image for an internal sales-alignment PowerPoint + +Use the visible reference images only as style continuity references: deep navy-black AI maritime operation-map base, cyan route light, restrained gold signal accents, radar / compass geometry, large readable Chinese typography. Do not copy their exact layout or old text. + +Create a 16:9 full-page visual slide image for the cover page titled "为什么是我们". This is the prequel to an internal AI kickoff deck, but the mood is harder and more sober: entering AI deepwater, answering why customers should choose us. + +Scene/backdrop: deep blue-black digital sea and AI maritime route-map background, with subtle coordinate grid, compass markings, radar scan rings, and restrained navigation-map texture. Add a visible deepwater cross-section in the lower half: under the surface, show abstract business-process networks, organization nodes, expert-experience threads, decision boundaries, and workflow lines. It should feel like "AI 深水区", not a generic ocean landscape. + +Primary visual structure: a cyan glowing route line travels across the dark map and descends visually into deeper business waters. Far in the distance, show a small warm-gold lighthouse or port signal, restrained and credible. The route should imply: simple AI is shallow water; expert-agent work is deep water. + +Text (verbatim Chinese, keep large and readable): +- Main title, largest: "为什么是我们" +- Subtitle below: "当客户的问题进入 AI 深水区，谁来做专家智能体？" +- Bottom line: "简单 AI 工具，客户可以自己做；复杂专家智能体，才是我们该做的事。" +- Optional small corner label: "内部销售认知补充会 / 专家智能体销售立场文件" + +Typography: bold modern Chinese sans-serif, high contrast, white / pale-blue title. Use subtle cyan highlight for "AI 深水区" and restrained gold highlight for "专家智能体". Main title must be the first read. Avoid calligraphy and decorative fonts. + +Composition/framing: title in the center-left or strong central safe area, subtitle directly below. Deepwater layer occupies lower half without clutter. Route line and radar elements support the title and do not cross the text. Keep generous safe margins. + +Lighting/mood: cinematic executive business visual, sober confidence, internal strategy alignment, "we are entering the deepwater and clarifying our position." Not gloomy, not flashy. + +Color palette: deep navy-black, dark ocean blue, cold slate gray, cyan AI signal light, restrained warm gold, pale-blue/white title. + +Constraints: no real people, no meeting room photo, no literal large ship as hero, no cartoon ship, no pirate or fantasy ship, no humanoid robot, no AI face, no platform logos, no customer proposal style, no government red-gold style, no generic tech conference poster, no dense dashboard UI, no pure gradient background, no watermark, no logo. + +## Output Intent + +Generate `s01-v1-image.png` as the cover validation candidate. + +## Generated Output + +- Host default source: `C:\Users\wangq\.codex\generated_images\019f1b6b-387f-7be2-af0a-03761085cdae\ig_03b93517b169e69c016a44798e01f481918324c93b7cc1cdef.png` +- Project copy: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` diff --git a/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-brief.md new file mode 100644 index 0000000..01ee64c --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-brief.md @@ -0,0 +1,50 @@ +# S-02 v1 Brief + +## Task + +生产 P02 / S-02 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-02 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Support: `intake/阶段3：PPT 总纲 v1.md` +- Support: `intake/阶段4：通用表达与视觉系统.md` +- Style: `visual-system/visual-system.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Opening / Problem +- Active motifs: 雷达问题锁定, AI 深水区, route line, lighthouse +- Main title: 销售问了一个真问题 +- Core judgment: 不是大家没信心，而是“为什么是我们”必须说透。 +- Required message: sales asked a real market-facing question; this deck answers it without blaming sales. + +## Visual Requirements + +Create a 16:9 full-page internal sales-alignment slide image. Use the accepted dark AI maritime route-map style. Show a route already leaving harbor, then three radar-locked question gates ahead. The page should feel like an executive battle-map briefing, not a customer proposal. + +## Text To Render + +- `销售问了一个真问题` +- `为什么是我们，必须说透` +- `平台是不是也在做？` +- `AI 开发公司有什么区别？` +- `客户凭什么选我们？` +- `信心不是喊出来的，是把差异讲明白之后长出来的` + +## Avoid + +No platform-bashing, no developer-bashing, no cute ship cartoon, no people portraits, no dense paragraph blocks, no review file. diff --git a/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-design.md new file mode 100644 index 0000000..c67c0d9 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-design.md @@ -0,0 +1,39 @@ +# S-02 v1 Design + +## 页面定位 + +- 页面：P02 / S-02 +- 标题：销售问了一个真问题 +- 模块：问题提出 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +不是大家没信心，而是“为什么是我们”必须说透。 + +## 视觉概念 + +承接封面已经进入 AI 深水区的航线，把销售提出的问题做成雷达锁定的三道关口。画面不是批评销售，而是承认这些问题是进入真实市场前必须补上的判断。 + +左侧保留“上一套解决怎么上船”的简化航线记忆，右侧出现三个雷达目标，分别对应平台、AI 开发公司、客户选择。整体像一次作战简报的第一页：大家已经出港，前方真正的问题开始出现。 + +## 版式 + +- 顶部左侧：页码 `P02` 与主标题。 +- 中心主句：`不是大家没信心，而是“为什么是我们”必须说透。` +- 左侧：微缩航线 / 船已离港 / 启动会完成。 +- 右侧：三枚雷达锁定目标卡。 +- 底部金句：`信心不是喊出来的，是把差异讲明白之后长出来的。` + +## 页面文字 + +- 主标题：销售问了一个真问题 +- 核心句：为什么是我们，必须说透 +- 三个目标：平台是不是也在做？ / AI 开发公司有什么区别？ / 客户凭什么选我们？ +- 底部：信心不是喊出来的，是把差异讲明白之后长出来的 + +## 风格与约束 + +延续深蓝黑 AI 航线作战图、雷达环、罗盘线、青色信号光和克制金色高亮。避免做成质疑销售、会议复盘、普通问答页或卡通船。 diff --git a/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-prompt.md new file mode 100644 index 0000000..e452aee --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s02/s02-v1-prompt.md @@ -0,0 +1,82 @@ +# S-02 v1 Prompt + +## Skill Mode + +Command: + +```powershell +node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json +``` + +Result: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +- `AGENTS.md` +- `projects/2026-07-01-为什么是我们/project.md` +- `projects/2026-07-01-为什么是我们/execution-plan.md` +- `projects/2026-07-01-为什么是我们/slides/slides.md` +- `projects/2026-07-01-为什么是我们/visual-system/visual-system.md` +- `projects/2026-07-01-为什么是我们/visual-system/style/style-prompt-master.md` +- `projects/2026-07-01-为什么是我们/visual-system/motifs/motif-registry.md` +- `projects/2026-07-01-为什么是我们/intake/阶段3：PPT 总纲 v1.md` +- `projects/2026-07-01-为什么是我们/intake/阶段4：通用表达与视觉系统.md` +- `projects/2026-07-01-为什么是我们/intake/阶段5：P1-P22 单页设计骨架.md` + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as current-deck cover style continuity reference. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as current-deck content-page style continuity reference. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as previous-deck route-map style continuity reference. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as previous-deck content-page style continuity reference. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only, not edit targets. Preserve their deep navy-black AI maritime route-map language, radar rings, compass geometry, cyan route glow, restrained gold highlights, crisp Chinese title hierarchy, and executive battle-map feeling. + +Primary request: Create slide P02 titled "销售问了一个真问题". The slide must communicate: "不是大家没信心，而是“为什么是我们”必须说透。" + +Scene/backdrop: deep navy-black AI maritime operation map, route already leaving harbor, dark deepwater layers below, subtle coordinate grid, compass marks, radar scan rings, distant lighthouse signal. + +Composition/framing: 16:9 wide slide. Top-left compact page tag "P02" and large title. Left side shows a simplified memory of the previous "上船" route as a small glowing route segment. Right side shows three radar-locked question gates as luminous cards or targets. The center has the core judgment as the biggest readable line. Bottom has one gold-highlighted sentence. + +Text (verbatim, short Chinese only): +Title: "销售问了一个真问题" +Core line: "为什么是我们，必须说透" +Question targets: "平台是不是也在做？" / "AI 开发公司有什么区别？" / "客户凭什么选我们？" +Bottom line: "信心不是喊出来的，是把差异讲明白之后长出来的" + +Style/medium: cinematic executive PPT visual, business consulting one-page, dark AI navigation chart, high polish, readable Chinese sans-serif, large title and clear labels, no long paragraphs. + +Color palette: deep navy-black, dark ocean blue, cold slate gray, cyan signal light, restrained gold emphasis, white and pale blue text. + +Constraints: page must feel affirming toward sales, like a serious market-facing question has been locked by radar. Keep one big judgment, one core visual model, three question labels. No platform-bashing, no developer-bashing, no cute ship, no human portraits, no generic SaaS dashboard, no logos, no watermark, no dense unreadable text. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-brief.md new file mode 100644 index 0000000..228d7bf --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-brief.md @@ -0,0 +1,46 @@ +# S-03 v1 Brief + +## Task + +生产 P03 / S-03 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-03 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Opening / Problem +- Active motifs: 雷达问题锁定, question gates +- Main title: 三个必须回答的问题 +- Core judgment: 我们必须同时回答平台、开发公司和客户选择三个问题。 +- Required message: this page frames the whole deck around three market-facing questions. + +## Visual Requirements + +Create a dark radar-screen issue framework page. Three equal cards should be visually locked as targets. Each card should have an icon-level motif: platform/toolbox, AI developer/code blueprint, customer choice/compass. + +## Text To Render + +- `三个必须回答的问题` +- `平台是不是也在做？` +- `AI 开发公司有什么区别？` +- `客户凭什么选择我们？` +- `回答不清，就没有真正底气` + +## Avoid + +No long explanations, no customer proposal tone, no platform attack, no overloaded UI. diff --git a/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-design.md new file mode 100644 index 0000000..ae1b493 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-design.md @@ -0,0 +1,37 @@ +# S-03 v1 Design + +## 页面定位 + +- 页面：P03 / S-03 +- 标题：三个必须回答的问题 +- 模块：问题提出 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +我们必须同时回答平台、开发公司和客户选择三个问题。 + +## 视觉概念 + +本页是全套 PPT 的议题框架页。深色雷达屏上锁定三个目标，每个目标都是销售未来会被客户追问的问题。画面要像作战地图上的三枚坐标，不像普通目录页。 + +## 版式 + +- 顶部：页码 `P03` 与主标题。 +- 中心：大字核心判断。 +- 中下部：三张问题卡横排，放在雷达靶心上。 +- 底部：`这三个问题回答不清，销售就没有真正的底气。` + +## 页面文字 + +- 主标题：三个必须回答的问题 +- 卡片 1：平台是不是也在做？ +- 卡片 2：AI 开发公司有什么区别？ +- 卡片 3：客户凭什么选择我们？ +- 底部：回答不清，就没有真正底气 + +## 风格与约束 + +继续使用深蓝黑商务底、雷达扫描、罗盘线、青色信号与克制金色。卡片要少字、清楚、可复述。不要把 Dify / Coze 等平台列表放大，也不要做成竞品攻击页。 diff --git a/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-prompt.md new file mode 100644 index 0000000..b5700a5 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s03/s03-v1-prompt.md @@ -0,0 +1,64 @@ +# S-03 v1 Prompt + +## Skill Mode + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +`AGENTS.md`; `project.md`; `execution-plan.md`; `slides/slides.md`; `visual-system/visual-system.md`; `visual-system/style/style-prompt-master.md`; `visual-system/motifs/motif-registry.md`; `intake/阶段3：PPT 总纲 v1.md`; `intake/阶段4：通用表达与视觉系统.md`; `intake/阶段5：P1-P22 单页设计骨架.md`. + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +Image 1 and Image 2 are current-deck style references. Image 3 and Image 4 are previous-deck style references. All are style continuity references only. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only. Match their deep navy-black AI maritime command-map base, cyan radar glow, compass geometry, restrained gold accents, and crisp high-contrast Chinese slide typography. + +Primary request: Create slide P03 titled "三个必须回答的问题". It is the agenda / issue-framing page for the deck. + +Scene/backdrop: dark executive radar screen over an AI maritime route map, subtle deepwater texture, coordinate grid, compass marks, scanning rings. + +Composition/framing: 16:9 wide slide. Top-left page tag "P03" and title. Center top has one clear core line: "我们必须同时回答三个问题". Middle row has three large radar-target cards, evenly spaced, each with a simple icon motif. Card 1: platform/toolbox. Card 2: AI developer/code blueprint. Card 3: customer choice/compass. Use glowing target rings behind each card. + +Text (verbatim): +Title: "三个必须回答的问题" +Core line: "必须同时回答三个问题" +Card 1: "平台是不是也在做？" +Card 2: "AI 开发公司有什么区别？" +Card 3: "客户凭什么选择我们？" +Bottom line: "回答不清，就没有真正底气" + +Style/medium: cinematic executive business slide, dark AI operation dashboard, but not a generic SaaS UI. Short Chinese labels only, large readable title, card text must be legible. + +Color palette: deep navy-black, dark ocean blue, cyan signal light, restrained gold highlights, white/pale-blue text. + +Constraints: one visual model, three cards, no long paragraphs. Avoid platform-bashing, developer-bashing, logo walls, cartoon ships, portraits, dense tables, watermarks. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-brief.md new file mode 100644 index 0000000..8b52c0b --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-brief.md @@ -0,0 +1,51 @@ +# S-04 v1 Brief + +## Task + +生产 P04 / S-04 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-04 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Support: `intake/阶段3：PPT 总纲 v1.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Market Contrast +- Active motifs: 平台工具箱, tool modules, foundation +- Main title: 先承认：平台很强，也很重要 +- Core judgment: 平台是工具箱、底座和供应商之一，不是我们的敌人。 +- Required message: maturely acknowledge platform strength before defining our differentiation. + +## Visual Requirements + +Create a central glowing platform toolbox with modular capability blocks. It should feel like strong infrastructure in the same dark AI route-map world, not like an enemy. + +## Text To Render + +- `先承认：平台很强，也很重要` +- `平台是工具箱、底座和供应商之一` +- `模型调用` +- `RAG 知识库` +- `工作流编排` +- `工具调用` +- `权限日志` +- `基础评测` +- `我们不贬低平台，平台是我们的工具箱` + +## Avoid + +No logo wall, no platform-bashing, no claim that platforms are weak, no cute icons, no dense feature table. diff --git a/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-design.md new file mode 100644 index 0000000..f8b5386 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-design.md @@ -0,0 +1,36 @@ +# S-04 v1 Design + +## 页面定位 + +- 页面：P04 / S-04 +- 标题：先承认：平台很强，也很重要 +- 模块：市场对照 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +平台是工具箱、底座和供应商之一，不是我们的敌人。 + +## 视觉概念 + +本页先承认平台价值，建立成熟可信的语气。中心是一只打开的“平台工具箱”，内部是模型调用、知识库、工作流、工具调用、权限、日志、评测等能力模块。平台被画成强大的底座和工具供应，不是反派。 + +## 版式 + +- 顶部：页码 `P04` 与标题。 +- 中心：打开的发光工具箱。 +- 四周：平台能力模块。 +- 底部：`我们不贬低平台，平台是我们的工具箱。` + +## 页面文字 + +- 主标题：先承认：平台很强，也很重要 +- 核心句：平台是工具箱、底座和供应商之一 +- 能力标签：模型调用 / RAG 知识库 / 工作流编排 / 工具调用 / 权限日志 / 基础评测 +- 底部：我们不贬低平台，平台是我们的工具箱 + +## 风格与约束 + +画面要客观、成熟、可信。可以用抽象平台能力模块，不放真实 logo 墙，不制造平台对抗情绪。 diff --git a/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-prompt.md new file mode 100644 index 0000000..b683794 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s04/s04-v1-prompt.md @@ -0,0 +1,62 @@ +# S-04 v1 Prompt + +## Skill Mode + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +`AGENTS.md`; `project.md`; `execution-plan.md`; `slides/slides.md`; `visual-system/visual-system.md`; `visual-system/style/style-prompt-master.md`; `visual-system/motifs/motif-registry.md`; `intake/阶段3：PPT 总纲 v1.md`; `intake/阶段4：通用表达与视觉系统.md`; `intake/阶段5：P1-P22 单页设计骨架.md`. + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +Image 1 and Image 2 are current-deck style references. Image 3 and Image 4 are previous-deck style references. All are style continuity references only. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only. Match the dark AI route-map base, cyan signal lines, compass/radar geometry, restrained gold emphasis, and readable Chinese title hierarchy. + +Primary request: Create slide P04 titled "先承认：平台很强，也很重要". Communicate that platforms are strong tools and suppliers, not enemies. + +Scene/backdrop: deep navy-black executive AI operation map, subtle coordinate grid and route lines. A strong central "platform toolbox" sits on the map as infrastructure. + +Composition/framing: 16:9 wide slide. Top-left page tag "P04" and main title. Center: open futuristic modular toolbox / capability base, glowing cyan and gold. Around it: six compact capability modules with icon-like visuals. Bottom: one gold-highlighted stance line. + +Text (verbatim): +Title: "先承认：平台很强，也很重要" +Core line: "平台是工具箱、底座和供应商之一" +Capability labels: "模型调用" / "RAG 知识库" / "工作流编排" / "工具调用" / "权限日志" / "基础评测" +Bottom line: "我们不贬低平台，平台是我们的工具箱" + +Style/medium: executive business report slide, polished 3D/diagram hybrid, precise modular blocks, dark maritime AI navigation style, sober and mature. + +Color palette: deep navy-black, dark ocean blue, cyan glow, restrained gold highlights, white/pale-blue text. + +Constraints: platform must look powerful and useful, not weak or hostile. Avoid real logos, logo walls, platform-bashing, developer-bashing, cute cartoons, people portraits, unreadable small text, watermark. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-brief.md new file mode 100644 index 0000000..a28eb6d --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-brief.md @@ -0,0 +1,56 @@ +# S-05 v1 Brief + +## Task + +生产 P05 / S-05 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-05 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Support: `intake/阶段3：PPT 总纲 v1.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Market Contrast +- Active motifs: AI 深水区, 平台工具箱, shallow vs deep water +- Main title: 平台解决“怎么搭”，不解决“该搭什么” +- Core judgment: 平台提供工具能力，我们提供场景判断和专家能力建模。 +- Required message: platform capabilities are implementation tools; the harder question is business judgment and expert capability modeling. + +## Visual Requirements + +Create a two-sided shallow/deep contrast. Left side should feel tool-layer and structured. Right side should feel like a complex business deepwater cross-section with expert judgment nodes. + +## Text To Render + +- `平台解决“怎么搭”，不解决“该搭什么”` +- `工具怎么搭` +- `该搭什么` +- `接模型` +- `接知识库` +- `编排工作流` +- `调用工具` +- `发布日志` +- `场景价值` +- `专家经验` +- `业务规则` +- `人工裁决` +- `错误纠正` +- `先判断想法是否成立` + +## Avoid + +No long question lists, no anti-platform tone, no dense training manual, no generic dashboard panels. diff --git a/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-design.md new file mode 100644 index 0000000..6a8bb98 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-design.md @@ -0,0 +1,37 @@ +# S-05 v1 Design + +## 页面定位 + +- 页面：P05 / S-05 +- 标题：平台解决“怎么搭”，不解决“该搭什么” +- 模块：市场对照 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +平台提供工具能力，我们提供场景判断和专家能力建模。 + +## 视觉概念 + +这是本包的核心差异页。左侧是浅水工具层，回答“怎么接模型、知识库、工作流、工具、发布和日志”；右侧是业务深水区，回答“哪个场景值得做、专家经验在哪里、业务规则怎么转译、哪些结果必须人工裁决、AI 出错后怎么纠正”。 + +## 版式 + +- 左右对比，左浅右深。 +- 中间有明显的浅水 / 深水分界线。 +- 左侧标题：`工具怎么搭` +- 右侧标题：`该搭什么` +- 底部金句：`平台默认帮助客户实现想法，我们先判断想法是否成立。` + +## 页面文字 + +- 主标题：平台解决“怎么搭”，不解决“该搭什么” +- 核心句：工具能力 vs 场景判断 +- 左侧标签：接模型 / 接知识库 / 编排工作流 / 调用工具 / 发布日志 +- 右侧标签：场景价值 / 专家经验 / 业务规则 / 人工裁决 / 错误纠正 + +## 风格与约束 + +要让销售能一眼复述“平台解决怎么搭，我们解决该搭什么”。右侧深水区要明显比左侧更复杂，但不要堆字。 diff --git a/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-prompt.md new file mode 100644 index 0000000..f996bae --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s05/s05-v1-prompt.md @@ -0,0 +1,64 @@ +# S-05 v1 Prompt + +## Skill Mode + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +`AGENTS.md`; `project.md`; `execution-plan.md`; `slides/slides.md`; `visual-system/visual-system.md`; `visual-system/style/style-prompt-master.md`; `visual-system/motifs/motif-registry.md`; `intake/阶段3：PPT 总纲 v1.md`; `intake/阶段4：通用表达与视觉系统.md`; `intake/阶段5：P1-P22 单页设计骨架.md`. + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +Image 1 and Image 2 are current-deck style references. Image 3 and Image 4 are previous-deck style references. All are style continuity references only. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only. Match their dark navy AI maritime operation-map style, deepwater cross-section language, cyan route glow, radar/compass geometry, restrained gold highlights, and readable Chinese text hierarchy. + +Primary request: Create slide P05 titled "平台解决“怎么搭”，不解决“该搭什么”". This is a core market-contrast slide. + +Scene/backdrop: a dark AI deepwater cross-section split from shallow tool layer to deeper business layer. Left side is the platform tool layer. Right side is business deepwater with hidden expert experience, business rules, responsibility boundaries, and calibration signals. + +Composition/framing: 16:9 wide slide. Top-left page tag "P05" and title. Left panel labeled "工具怎么搭" with five clean module blocks. Right panel labeled "该搭什么" with five deeper judgment nodes embedded under the waterline. A clear vertical / diagonal boundary line shows shallow-to-deep transition. Bottom has one highlighted judgment line. + +Text (verbatim): +Title: "平台解决“怎么搭”，不解决“该搭什么”" +Left heading: "工具怎么搭" +Left labels: "接模型" / "接知识库" / "编排工作流" / "调用工具" / "发布日志" +Right heading: "该搭什么" +Right labels: "场景价值" / "专家经验" / "业务规则" / "人工裁决" / "错误纠正" +Bottom line: "先判断想法是否成立" + +Style/medium: polished executive PPT visual, consulting-style comparison page, cinematic AI maritime map, diagrammatic but not generic dashboard. + +Color palette: deep navy-black, dark ocean blue, cyan tool signals, restrained gold for the right-side core judgment, white/pale-blue text. + +Constraints: the slide must make the contrast instantly repeatable: platform = how to build, us = what should be built. Keep text short and readable. Avoid platform-bashing, logo walls, humanoid robots, stock people, cute ships, long paragraphs, watermark. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-brief.md new file mode 100644 index 0000000..d46cf67 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-brief.md @@ -0,0 +1,50 @@ +# S-06 v1 Brief + +## Task + +生产 P06 / S-06 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-06 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Support: `intake/阶段4：通用表达与视觉系统.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Market Contrast +- Active motifs: 数字工厂, 精密模具 +- Main title: 平台像工厂，我们像模具师 +- Core judgment: 工厂提供生产能力，模具决定生产什么、精度在哪里、能不能稳定产出。 +- Required message: platform and us are not enemies; platform provides capacity, our value is expert-capability mold precision. + +## Visual Requirements + +Create a left-to-right industrial metaphor: digital factory -> precision mold -> stable expert-agent output. + +## Text To Render + +- `平台像工厂，我们像模具师` +- `平台工厂` +- `生产能力` +- `精密模具` +- `专家模型` +- `校准` +- `稳定产出` +- `没有平台跑不起来；只有平台，也可能做出无效智能` + +## Avoid + +No platform humiliation, no real human workers, no cartoon factory, no excessive machinery detail that hides the judgment. diff --git a/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-design.md new file mode 100644 index 0000000..e802b29 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-design.md @@ -0,0 +1,35 @@ +# S-06 v1 Design + +## 页面定位 + +- 页面：P06 / S-06 +- 标题：平台像工厂，我们像模具师 +- 模块：市场对照 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +工厂提供生产能力，模具决定生产什么、精度在哪里、能不能稳定产出。 + +## 视觉概念 + +用低阻抗隐喻讲清平台与我们的关系。左侧是大型数字工厂和流水线，代表平台的生产能力；中间是精密模具剖面，代表专家能力建模；右侧是稳定产出的专家智能体能力模块。 + +## 版式 + +- 左：`平台工厂` +- 中：`精密模具` +- 右：`稳定产出` +- 底部：`没有平台跑不起来；只有平台，也可能做出无效智能。` + +## 页面文字 + +- 主标题：平台像工厂，我们像模具师 +- 核心句：生产能力 vs 关键精度 +- 标签：机器 / 流水线 / 模具结构 / 专家模型 / 校准 / 稳定产出 + +## 风格与约束 + +工厂必须强大，模具必须精密，二者是协作关系。不要出现真实工人或人物肖像，不要把平台画成落后机器。 diff --git a/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-prompt.md new file mode 100644 index 0000000..8434bc6 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s06/s06-v1-prompt.md @@ -0,0 +1,61 @@ +# S-06 v1 Prompt + +## Skill Mode + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +`AGENTS.md`; `project.md`; `execution-plan.md`; `slides/slides.md`; `visual-system/visual-system.md`; `visual-system/style/style-prompt-master.md`; `visual-system/motifs/motif-registry.md`; `intake/阶段3：PPT 总纲 v1.md`; `intake/阶段4：通用表达与视觉系统.md`; `intake/阶段5：P1-P22 单页设计骨架.md`. + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +Image 1 and Image 2 are current-deck style references. Image 3 and Image 4 are previous-deck style references. All are style continuity references only. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only. Match their dark AI maritime map, radar/compass geometry, cyan signal lines, restrained gold highlights, strong Chinese title typography, and executive slide polish. + +Primary request: Create slide P06 titled "平台像工厂，我们像模具师". Communicate: factory capacity is necessary, but precision mold determines what is produced and whether it is stable. + +Scene/backdrop: deep navy-black AI operation map blended with a futuristic digital factory and precision mold cutaway. Keep it abstract and executive, not literal workshop photography. + +Composition/framing: 16:9 wide slide. Top-left page tag "P06" and title. Left third: large powerful digital factory / production line labeled "平台工厂" and "生产能力". Center: glowing precision mold cutaway labeled "精密模具" and "专家模型", with calibration grid. Right third: clean stable output modules labeled "稳定产出". Bottom has a sober gold-highlighted warning line. + +Text (verbatim): +Title: "平台像工厂，我们像模具师" +Labels: "平台工厂" / "生产能力" / "精密模具" / "专家模型" / "校准" / "稳定产出" +Bottom line: "没有平台跑不起来；只有平台，也可能做出无效智能" + +Style/medium: polished cinematic business diagram, executive consulting slide, dark AI maritime route-map plus industrial precision metaphor, readable Chinese sans-serif. + +Color palette: deep navy-black, slate blue, cyan technical glow, restrained gold for mold and key sentence, white/pale-blue text. + +Constraints: the factory must look strong and useful, the mold must look precise and central. No platform-bashing, no human portraits, no cartoon factory, no logo wall, no generic robot, no dense paragraphs, no watermark. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-brief.md new file mode 100644 index 0000000..4674509 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-brief.md @@ -0,0 +1,55 @@ +# S-07 v1 Brief + +## Task + +生产 P07 / S-07 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-07 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Market Contrast +- Active motifs: AI 深水区, shallow vs deep water +- Main title: 简单场景，客户自己用平台就可以 +- Core judgment: 我们不是什么 AI 都抢，简单 AI 工具客户自己做就可以。 +- Required message: professional boundary-setting; simple AI is not our field, complex expert agents are. + +## Visual Requirements + +Create a layered shallow-water vs deepwater page. Shallow layer has lightweight platform-use cases. Deep layer has complex expert-agent conditions. + +## Text To Render + +- `简单场景，客户自己用平台就可以` +- `客户自己做` +- `我们的场` +- `简单问答` +- `文档摘要` +- `周报生成` +- `普通客服` +- `内部检索` +- `高专家密度` +- `高业务语境` +- `高判断复杂度` +- `高组织协同` +- `高校准需求` +- `复杂专家智能体，才是我们的场` + +## Avoid + +No contempt for simple scenarios, no overclaiming, no cartoon ocean, no long paragraphs. diff --git a/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-design.md new file mode 100644 index 0000000..d3f8cca --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-design.md @@ -0,0 +1,35 @@ +# S-07 v1 Design + +## 页面定位 + +- 页面：P07 / S-07 +- 标题：简单场景，客户自己用平台就可以 +- 模块：市场对照 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +我们不是什么 AI 都抢，简单 AI 工具客户自己做就可以。 + +## 视觉概念 + +本页主动筛场景，建立专业边界。画面用浅水区 / 深水区分层：浅水区放简单问答、摘要、周报、普通客服、内部检索等轻量场景；深水区放高专家密度、高业务语境、高判断复杂度、高组织协同、高校准需求。 + +## 版式 + +- 上层：浅水区，标题 `客户自己做` +- 下层：深水区，标题 `我们的场` +- 中央：航线从浅水驶向深水，但在浅水处留下明确分界。 +- 底部金句：`简单 AI，不必找我们；复杂专家智能体，才是我们的场。` + +## 页面文字 + +- 主标题：简单场景，客户自己用平台就可以 +- 浅水标签：简单问答 / 文档摘要 / 周报生成 / 普通客服 / 内部检索 +- 深水标签：高专家密度 / 高业务语境 / 高判断复杂度 / 高组织协同 / 高校准需求 + +## 风格与约束 + +要显得清醒和专业，不是退缩。不要把简单场景画得垃圾化；它们只是适合客户自己处理。 diff --git a/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-prompt.md new file mode 100644 index 0000000..7e89afc --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-prompt.md @@ -0,0 +1,64 @@ +# S-07 v1 Prompt + +## Skill Mode + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +`AGENTS.md`; `project.md`; `execution-plan.md`; `slides/slides.md`; `visual-system/visual-system.md`; `visual-system/style/style-prompt-master.md`; `visual-system/motifs/motif-registry.md`; `intake/阶段3：PPT 总纲 v1.md`; `intake/阶段4：通用表达与视觉系统.md`; `intake/阶段5：P1-P22 单页设计骨架.md`. + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +Image 1 and Image 2 are current-deck style references. Image 3 and Image 4 are previous-deck style references. All are style continuity references only. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only. Match the dark AI deepwater operation-map style, cyan route glow, compass/radar geometry, restrained gold highlights, and crisp Chinese slide text. + +Primary request: Create slide P07 titled "简单场景，客户自己用平台就可以". Communicate a professional boundary: we do not compete for every AI scenario; complex expert-agent work is our field. + +Scene/backdrop: dark ocean cross-section in the AI maritime route-map world. Upper shallow-water layer contains lightweight AI tool use cases. Lower deepwater layer contains complex expert-agent conditions and business network nodes. + +Composition/framing: 16:9 wide slide. Top-left page tag "P07" and title. Upper half labeled "客户自己做" with five lightweight use-case chips. Lower half labeled "我们的场" with five glowing deepwater capability conditions. A route line starts in shallow water and descends toward the deep layer. Bottom has a strong gold/cyan line. + +Text (verbatim): +Title: "简单场景，客户自己用平台就可以" +Upper heading: "客户自己做" +Upper labels: "简单问答" / "文档摘要" / "周报生成" / "普通客服" / "内部检索" +Lower heading: "我们的场" +Lower labels: "高专家密度" / "高业务语境" / "高判断复杂度" / "高组织协同" / "高校准需求" +Bottom line: "复杂专家智能体，才是我们的场" + +Style/medium: executive business slide, cinematic AI deepwater diagram, clear comparison, readable Chinese sans-serif, high contrast. + +Color palette: deep navy-black, dark ocean blue, cyan signal light for route and simple tools, restrained gold for deepwater expert-agent field. + +Constraints: make the boundary feel sober and professional, not dismissive. Avoid saying simple tools are bad. No cute ship, no people portraits, no generic robot, no dense paragraphs, no watermark. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-brief.md new file mode 100644 index 0000000..3856fd3 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-brief.md @@ -0,0 +1,55 @@ +# S-08 v1 Brief + +## Task + +生产 P08 / S-08 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-08 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Support: `intake/阶段3：PPT 总纲 v1.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Our Positioning +- Active motifs: 专家智能体岗位卡, tool-to-role transition +- Main title: 我们做的不是通用 AI 助手 +- Core judgment: 普通 AI 助手是工具，专家智能体是有岗位职责的数字员工。 +- Required message: separate common AI assistant from expert agent. + +## Visual Requirements + +Create a left-right transition from ordinary AI tools to a role-bound expert-agent employee card. Do not use humanoid robots. + +## Text To Render + +- `我们做的不是通用 AI 助手` +- `普通 AI 助手` +- `专家智能体` +- `从工具到岗位` +- `聊天窗口` +- `知识库问答` +- `Prompt 模板` +- `API 封装` +- `岗位职责` +- `责任边界` +- `业务流程` +- `持续校准` +- `会回答，不等于会承担岗位职责` + +## Avoid + +No humanoid robots, no mockery of simple AI apps, no dense paragraphs, no generic SaaS dashboard. diff --git a/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-design.md new file mode 100644 index 0000000..362b052 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-design.md @@ -0,0 +1,36 @@ +# S-08 v1 Design + +## 页面定位 + +- 页面：P08 / S-08 +- 标题：我们做的不是通用 AI 助手 +- 模块：我们定位 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +普通 AI 助手是工具，专家智能体是有岗位职责的数字员工。 + +## 视觉概念 + +从市场常见“智能体”概念中切出我们的定义。左侧是普通 AI 工具堆叠：聊天窗口、知识库、Prompt 卡、API 和工作流；右侧是专家智能体岗位卡，有岗位职责、责任边界、业务流程和校准机制。 + +## 版式 + +- 左侧：`普通 AI 助手` +- 右侧：`专家智能体` +- 中间箭头：`从工具到岗位` +- 底部金句：`会回答，不等于会承担岗位职责。` + +## 页面文字 + +- 主标题：我们做的不是通用 AI 助手 +- 左侧标签：聊天窗口 / 知识库问答 / Prompt 模板 / API 封装 +- 右侧标签：岗位职责 / 责任边界 / 业务流程 / 持续校准 +- 底部：会回答，不等于会承担岗位职责 + +## 风格与约束 + +右侧岗位卡要有重量，像企业数字员工档案，不要画成人形机器人。左侧工具堆叠要克制，不要显得低级或嘲讽。 diff --git a/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-prompt.md new file mode 100644 index 0000000..604d9ef --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s08/s08-v1-prompt.md @@ -0,0 +1,65 @@ +# S-08 v1 Prompt + +## Skill Mode + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +`AGENTS.md`; `project.md`; `execution-plan.md`; `slides/slides.md`; `visual-system/visual-system.md`; `visual-system/style/style-prompt-master.md`; `visual-system/motifs/motif-registry.md`; `intake/阶段3：PPT 总纲 v1.md`; `intake/阶段4：通用表达与视觉系统.md`; `intake/阶段5：P1-P22 单页设计骨架.md`. + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +Image 1 and Image 2 are current-deck style references. Image 3 and Image 4 are previous-deck style references. All are style continuity references only. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only. Match their dark navy AI operation-map style, cyan route glow, compass/radar geometry, restrained gold highlights, and crisp Chinese slide text. + +Primary request: Create slide P08 titled "我们做的不是通用 AI 助手". The slide must separate ordinary AI assistant tools from expert agents with job responsibilities. + +Scene/backdrop: deep navy-black executive AI route-map environment, subtle grid and compass lines. The visual metaphor is "from tool to role", not robots. + +Composition/framing: 16:9 wide slide. Top-left page tag "P08" and title. Left panel: compact stack of ordinary AI tool cards labeled "普通 AI 助手". Right panel: large premium digital employee role card labeled "专家智能体", with responsibility boundary and workflow lines. Center arrow: "从工具到岗位". Bottom has a strong readable judgment line. + +Text (verbatim): +Title: "我们做的不是通用 AI 助手" +Left heading: "普通 AI 助手" +Left labels: "聊天窗口" / "知识库问答" / "Prompt 模板" / "API 封装" +Center arrow: "从工具到岗位" +Right heading: "专家智能体" +Right labels: "岗位职责" / "责任边界" / "业务流程" / "持续校准" +Bottom line: "会回答，不等于会承担岗位职责" + +Style/medium: polished executive PPT content page, consulting-style comparison, futuristic but sober, no humanoid robots, readable Chinese sans-serif. + +Color palette: deep navy-black, dark ocean blue, cyan for tool signals and transition, restrained gold for expert-agent role card and bottom judgment. + +Constraints: right-side role card must feel enterprise-grade and responsible, not a chatbot. Left side should look useful but limited, not mocked. Avoid human portraits, humanoid robots, cartoon assistants, logo walls, long paragraphs, watermark. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-brief.md new file mode 100644 index 0000000..c7d7ceb --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-brief.md @@ -0,0 +1,52 @@ +# S-09 v1 Brief + +## Task + +生产 P09 / S-09 页面图。 + +## Scope + +- Project: `projects/2026-07-01-为什么是我们` +- Slide: S-09 +- Version: v1 +- Line: production-light +- Review: none +- Overwrite allowed: no + +## Source Authority + +- Primary: `intake/阶段5：P1-P22 单页设计骨架.md` +- Support: `intake/阶段3：PPT 总纲 v1.md` +- Style: `visual-system/style/style-prompt-master.md` +- Motif: `visual-system/motifs/motif-registry.md` + +Backup fact-check source was not opened or used. + +## Page Requirements + +- Page family: Our Positioning +- Active motifs: 专家智能体岗位卡, expert capability rings, calibration +- Main title: 什么是专家智能体 +- Core judgment: 专家智能体是在具体岗位、场景、流程和责任边界中工作的数字员工。 +- Required message: define expert agent without making it universal or vague. + +## Visual Requirements + +Create a central model: digital employee card in the middle, four inner anchors and four outer expert capabilities around it. + +## Text To Render + +- `什么是专家智能体` +- `具体岗位` +- `具体场景` +- `具体流程` +- `责任边界` +- `专家视角` +- `专家判断` +- `专家表达` +- `持续校准` +- `有岗位职责的数字员工` + +## Avoid + +No long paragraph definition, no humanoid robot, no generic chatbot, no overclaim that it can do everything. diff --git a/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-design.md new file mode 100644 index 0000000..88149f6 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-design.md @@ -0,0 +1,37 @@ +# S-09 v1 Design + +## 页面定位 + +- 页面：P09 / S-09 +- 标题：什么是专家智能体 +- 模块：我们定位 +- 运行线：production-light +- Review：none +- Overwrite allowed：no + +## 核心判断 + +专家智能体是在具体岗位、场景、流程和责任边界中工作的数字员工。 + +## 视觉概念 + +建立核心概念。中心是“专家智能体”岗位卡，内圈是岗位、场景、流程、边界，外圈是专家视角、专家判断、专家表达、持续校准。画面要像给销售一个可复述的定义模型。 + +## 版式 + +- 顶部：页码 `P09` 与主标题。 +- 中心：专家智能体数字员工卡。 +- 内环：岗位 / 场景 / 流程 / 边界。 +- 外环：专家视角 / 专家判断 / 专家表达 / 持续校准。 +- 底部金句：`普通 AI 助手是会说话的工具；专家智能体是有岗位职责的数字员工。` + +## 页面文字 + +- 主标题：什么是专家智能体 +- 核心句：在岗位、场景、流程和责任边界中工作 +- 内环：岗位 / 场景 / 流程 / 边界 +- 外环：专家视角 / 专家判断 / 专家表达 / 持续校准 + +## 风格与约束 + +不要把定义做成一整段长文。用模型拆解概念，让销售可以按四个内环和四个外环复述。 diff --git a/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-prompt.md new file mode 100644 index 0000000..34cfb33 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s09/s09-v1-prompt.md @@ -0,0 +1,63 @@ +# S-09 v1 Prompt + +## Skill Mode + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native. Prompt is saved first, then passed to host `image_gen`. Garden generation scripts are not used. + +## Template / Reference Files Read + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +## Project Sources Read + +`AGENTS.md`; `project.md`; `execution-plan.md`; `slides/slides.md`; `visual-system/visual-system.md`; `visual-system/style/style-prompt-master.md`; `visual-system/motifs/motif-registry.md`; `intake/阶段3：PPT 总纲 v1.md`; `intake/阶段4：通用表达与视觉系统.md`; `intake/阶段5：P1-P22 单页设计骨架.md`. + +Fact-check source status: not opened; no factual claim required backup verification. + +## Reference Image Roles + +Image 1 and Image 2 are current-deck style references. Image 3 and Image 4 are previous-deck style references. All are style continuity references only. + +## Final Host-Native Prompt + +```text +Use case: productivity-visual / infographic-diagram. +Asset type: 16:9 full-page internal sales-alignment PowerPoint slide image. +Input images: Image 1, Image 2, Image 3, and Image 4 are style continuity references only. Match their dark navy AI maritime operation-map style, cyan route glow, compass/radar geometry, restrained gold highlights, precision content-page layout, and readable Chinese typography. + +Primary request: Create slide P09 titled "什么是专家智能体". Define expert agent as a role-bound digital employee working in a specific position, scenario, workflow, and responsibility boundary. + +Scene/backdrop: deep navy-black AI route-map environment with subtle coordinate grid, compass geometry, and expert capability signal network. No humanoid robot. + +Composition/framing: 16:9 wide slide. Top-left page tag "P09" and title. Center: premium digital employee profile / role card labeled "专家智能体". Around it: four inner ring anchors: specific position, scenario, workflow, responsibility boundary. Outer ring: expert perspective, expert judgment, expert expression, continuous calibration. Use cyan ring lines and gold highlights to show hierarchy. Bottom has one concise definition line. + +Text (verbatim): +Title: "什么是专家智能体" +Center: "专家智能体" +Inner ring: "具体岗位" / "具体场景" / "具体流程" / "责任边界" +Outer ring: "专家视角" / "专家判断" / "专家表达" / "持续校准" +Bottom line: "有岗位职责的数字员工" + +Style/medium: executive PPT concept model, business consulting diagram, futuristic but sober, dark AI maritime command-map style, readable Chinese sans-serif. + +Color palette: deep navy-black, dark ocean blue, cyan signal rings, restrained gold for center role card and key line, white/pale-blue text. + +Constraints: do not use long paragraphs. The definition must be decomposed into the four inner anchors and four outer capabilities. Avoid humanoid robots, generic chatbot UI, claims of universal ability, logo walls, cute ships, watermark. +``` diff --git a/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-brief.md new file mode 100644 index 0000000..3f7552e --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-brief.md @@ -0,0 +1,65 @@ +# S-10 Slide Brief V1 + +## Page + +- Page: P10 / S-10. +- Title: 我们是谁：专家智能体的系统架构师与模具师. +- Function: positioning reveal. +- Core conclusion: 我们帮助企业把人脑里的专家能力变成组织可复用的智能能力。 + +## Source Basis + +Primary sources: + +- `intake/阶段5：P1-P22 单页设计骨架.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` + +Style references: + +- previous deck visual system; +- previous deck accepted cover and content images. + +Backup fact-check source: + +- not used. + +## Visible Text + +Title: + +> 我们是谁：专家智能体的系统架构师与模具师 + +Core judgment: + +> 把人脑里的专家能力，变成组织可复用的智能能力 + +Positioning phrase: + +> 专家能力工程化 + +Pipeline labels: + +> 抽取 / 封装 / 验证 / 校准 / 进入流程 + +Optional contrast tags: + +> 不是平台 / 不是外包 / 不是只写提示词 + +## Visual Requirements + +- 16:9 full-page visual image. +- Deep navy-black AI route-map base. +- Left-to-right transformation model. +- Left: tacit expert capability and experience network. +- Center: precision mold / architecture engine / calibration module. +- Right: reusable expert agent modules entering real workflow. +- Cyan path lines and restrained gold highlights. +- No people, no robot mascot, no code-wall hero. + +## Generation Notes + +- Current `gpt-image-2` mode: `B-or-C`. +- Effective route: Mode B, host-native image generation. +- Garden expected: no. +- Review mode: user validation only. diff --git a/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-design.md new file mode 100644 index 0000000..c8a9abb --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-design.md @@ -0,0 +1,102 @@ +# S-10 Slide Design V1 + +## Status + +- Status: validation design. +- Source page: P10. +- Page title: 我们是谁：专家智能体的系统架构师与模具师. +- Role: first content anchor validation. +- Line: validation sample. +- Write policy: append-only; overwrite allowed: no. + +## Design Purpose + +P10 是全套 PPT 的定位核心页。它不能只是漂亮地说“我们很专业”，而要让销售带走一个可复述的判断： + +> 我们帮助企业把人脑里的专家能力，变成组织可复用的智能能力。 + +本页要验证这套视觉系统能否承载“专家能力工程化”这种硬判断，而不是只会做航线氛围。 + +## Visual Concept + +画面是一个“专家能力工程化模具舱”。 + +左侧是人脑里的专家能力：不是人物肖像，而是抽象的经验云团、隐性判断光点、业务语境片段、案例碎片和组织经验网络。中间是我们的角色：系统架构师与模具师，用精密模具、工程剖面、校准仪表和结构化管线表示。右侧是组织可复用的专家智能体能力：岗位卡、流程接入线、可校准智能体模块、客户业务流程节点。 + +核心流程必须清楚： + +```text +专家经验 → 抽取 → 封装 → 验证 → 校准 → 进入流程 +``` + +画面要像深蓝黑 AI 航线作战图里的“核心加工舱 / 模具舱”，不是工厂广告，不是程序员写代码，也不是普通系统架构图。 + +## Text / Typography Plan + +Title: + +> 我们是谁：专家智能体的系统架构师与模具师 + +Core judgment: + +> 把人脑里的专家能力，变成组织可复用的智能能力 + +Positioning label: + +> 专家能力工程化 + +Pipeline labels: + +> 抽取 / 封装 / 验证 / 校准 / 进入流程 + +Optional contrast labels: + +> 不是平台 +> 不是外包 +> 不是只写提示词 + +Typography: + +- title at top, large but not crowding; +- core judgment should be the strongest center text; +- pipeline labels short and readable; +- avoid too many long Chinese lines inside the diagram. + +## Layout + +Recommended composition: + +- Left third: abstract expert capability cloud and tacit knowledge nodes. +- Center third: precision mold / architecture engine / calibration instrument. +- Right third: reusable expert agent modules connected to business workflow. +- Center line: cyan-gold pipeline from left to right. +- Bottom or central label: `专家能力工程化`. + +Visual priority: + +1. core judgment; +2. left-to-right engineering pipeline; +3. title; +4. mold / calibration visual; +5. optional contrast tags. + +## Constraints / Avoid + +Must avoid: + +- concrete portraits of experts; +- generic humanoid robots; +- code wall / programmer worship; +- platform logo wall; +- ordinary SaaS dashboard; +- treating us as a low-price outsourcing team; +- adding claims not in the accepted skeleton; +- stuffing the raw material into the page. + +## Validation Focus + +User should check: + +1. Does this page make our positioning clear enough? +2. Does it visually explain extraction, encapsulation, validation, calibration, and workflow entry? +3. Does it feel continuous with the previous deck while being harder and more analytical? diff --git a/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-prompt.md new file mode 100644 index 0000000..abb9b43 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s10/s10-v1-prompt.md @@ -0,0 +1,79 @@ +# S-10 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s10-v1-brief.md`. +- Review mode: user validation only. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P10 / S-10. +- Page family: C / Our Positioning. +- Active style module: `visual-system/style/style-prompt-master.md`, Module C. +- Core motifs: 专家能力工程化管线, 精密模具, 专家智能体岗位卡, workflow entry. +- Main title: `我们是谁：专家智能体的系统架构师与模具师` +- Core judgment: `我们帮助企业把人脑里的专家能力，变成组织可复用的智能能力。` +- Text complexity: medium. +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Effective route: Mode B, host-native image generation. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` + - `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` +- Style reference images loaded into context: + - Image 1: previous accepted cover style, `../2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png`, role = style continuity reference only. + - Image 2: previous accepted content style, `../2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png`, role = style continuity reference only. +- Backup raw material source: not used. + +## Final Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page content slide image for an internal sales-alignment PowerPoint + +Use the visible reference images only as style continuity references: deep navy-black AI maritime operation-map base, cyan glowing route lines, restrained gold highlights, radar / compass geometry, and large readable Chinese typography. Do not copy their old page content. + +Create a 16:9 full-page visual slide image for Page P10 titled "我们是谁：专家智能体的系统架构师与模具师". This is the core positioning page of the deck. It must feel weighty, precise, and analytical: our role is not platform, not low-price outsourcing, not just prompt writing. Our role is expert capability engineering. + +Scene/backdrop: deep navy-black executive AI route-map background with subtle coordinate grid, radar rings, compass geometry, dark ocean-chart texture, and deepwater business-layer hints. Keep the accepted previous deck base, but make it more sober and technical-business. + +Primary visual model: a left-to-right transformation pipeline. +- Left third: abstract "人脑里的专家能力" shown as a luminous tacit-knowledge cloud, business judgment nodes, experience fragments, workflow rules, and hidden expert decision threads. No human portraits. +- Center third: "系统架构师与模具师" represented by a precision mold / engineering cutaway / calibration engine: gold-edged mold frame, cyan circuitry, measurement grid, calibration dials, structured model core. +- Right third: "组织可复用的智能能力" shown as expert-agent role cards and modular digital-worker capability blocks entering a real business workflow line. +- Across the center, show a clear cyan-gold pipeline with five readable labels: "抽取", "封装", "验证", "校准", "进入流程". + +Text (verbatim Chinese, keep readable): +- Top title: "我们是谁：专家智能体的系统架构师与模具师" +- Core judgment, large central line: "把人脑里的专家能力，变成组织可复用的智能能力" +- Positioning phrase near the center engine: "专家能力工程化" +- Pipeline labels: "抽取" / "封装" / "验证" / "校准" / "进入流程" +- Optional small contrast tags, if space allows: "不是平台" / "不是外包" / "不是只写提示词" + +Typography: bold modern Chinese sans-serif, high contrast, white or pale-blue. Use cyan for active pipeline labels and restrained gold for "专家能力工程化" or the mold core. Main title and core judgment must be legible. + +Composition/framing: title at top safe area, core judgment centered above or across the pipeline. Three-part left-center-right model should be visually obvious. Do not crowd the page with paragraphs. Leave enough negative space around key text. + +Lighting/mood: cinematic executive business visual, sober confidence, precise engineering, deepwater business expertise. The page should look like a strategic capability diagram, not a software dashboard. + +Color palette: deep navy-black, dark slate blue, cyan AI signal, restrained warm gold, pale-blue/white typography. + +Constraints: no real people, no expert portraits, no humanoid robots, no AI faces, no code wall as hero, no platform logo wall, no generic SaaS dashboard, no customer proposal look, no government-report red-gold style, no cartoon ship, no literal factory worker, no dense paragraphs, no watermark, no logo. + +## Output Intent + +Generate `s10-v1-image.png` as the content anchor validation candidate. + +## Generated Output + +- Host default source: `C:\Users\wangq\.codex\generated_images\019f1b6b-387f-7be2-af0a-03761085cdae\ig_08ab80c795c4cfff016a447a1cae588191ae265e781d9dca16.png` +- Project copy: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` diff --git a/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-brief.md new file mode 100644 index 0000000..bb53d8b --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-brief.md @@ -0,0 +1,72 @@ +# S-11 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +拆掉“你们是不是就是写 Prompt”的误解，把销售认知从模型调用提升到专家能力工程化。 + +## First Read + +只会调用模型，不等于会做专家智能体。 + +## Risk Class + +core motif / PPT page / comparison diagram + +## Reference Plan + +- Active style module: Module C / Our Positioning. +- Core motif: 专家能力工程化管线 + 精密模具。 +- Reference images: current deck S-01 and S-10, previous deck S-01 and S-10, all as style continuity references only. +- Character references: none. + +## Visual Requirements + +Use a left/right comparison. Left side: shallow AI performance layer. Right side: expert-agent engineering layer. The central boundary should make the shift from “can answer” to “can take responsibility” legible. + +## Character Handling + +No visible identity or character continuity required. Avoid human portraits. + +## Composition / Scale + +Full-page 16:9. Large title at top, two balanced panels, central boundary, bottom judgment bar. + +## Light / Color / Texture + +Deep navy-black executive map base, cyan route lines, gold highlights on the engineering layer, subtle radar rings and coordinate grid. + +## Forbidden Drift + +No platform-bashing, no developer-bashing, no generic SaaS dashboard, no stock meeting scene, no humanoid robots, no long copied source paragraphs. + +## Acceptance Checklist + +- Title and core judgment readable. +- Left side clearly reads as surface-level actions. +- Right side clearly reads as engineered expert capability. +- Bottom gold sentence present or visually reserved. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save final prompt before calling host `image_gen`. Copy generated image into `slides/s11/s11-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-design.md new file mode 100644 index 0000000..906e3e2 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-design.md @@ -0,0 +1,63 @@ +# S-11 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P11 / S-11 only + +## Design Purpose + +本页是 PPT 内容页，需要单独记录面向人的页面设计意图、文本层级和后期可调整区域。任务级授权允许继续写 brief、prompt 并生成图片，不再单独等待设计确认。 + +## Discussion Summary + +本页用于拆掉“你们是不是就是写 Prompt”的误解。语气要坚定但不贬低 Prompt，强调 Prompt 是入口，专家能力工程化才是客户真正购买的能力。 + +## Visual Concept + +左右对比：左侧是浅层“AI 表演层”，用聊天框、Prompt 卡片、小舞台和工具调用图标表示；右侧是深层“工程化层”，用专家模型核心、责任边界、评测仪表盘、流程接入线表示。中间用一条发光边界线写出“能回答 → 能负责”。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 延续深蓝黑商务底、AI 航线作战图、雷达 / 罗盘线、青色信号和克制金色高亮。 +- 页面主视觉必须体现从“写提示词”到“专家能力工程化”的层级差异。 +- 不出现人物肖像，不做客户提案风，不做炫酷但无业务逻辑的科技背景。 + +## Text / Typography Plan + +- 主标题：不是写提示词，而是专家能力工程化 +- 核心判断：只会调用模型，不等于会做专家智能体 +- 左侧短标签：角色设定、提示词、接模型、工具调用、输出结果 +- 右侧短标签：岗位职责、依据判断、能力边界、人工介入、解释校准、进入流程 +- 底部金句：如果只写一个提示词，那是 AI 表演，不是专家能力工程化 + +## Layout / Safe Areas + +- 顶部标题安全区高度约 14%-18%。 +- 左右主体各占约 42%，中间分界线约 8%-10%。 +- 底部金句放在深色半透明条中，避免贴边。 + +## Color Guidance + +- 左侧灰蓝低亮度，表示浅层工具动作。 +- 右侧青色与金色更强，表示专家能力工程化主路径。 +- 字体以白色 / 浅蓝为主，关键词使用金色。 + +## Post-Production Notes + +如图片中文字局部不够准确，后续 PPT 装配可覆盖标题和关键标签；生成图仍需保留清晰的左右对比和工程剖面结构。 + +## Constraints / Avoid + +- 不把 Prompt 说成无价值。 +- 不出现平台或开发公司 logo。 +- 不使用长段正文。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-prompt.md new file mode 100644 index 0000000..6bb23eb --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-prompt.md @@ -0,0 +1,60 @@ +# S-11 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s11/s11-v1-image.png` + +## Based On Brief + +`slides/s11/s11-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `visual-system/style/style-prompt-master.md`, `visual-system/motifs/motif-registry.md`, `intake/阶段3：PPT 总纲 v1.md`, `intake/阶段4：通用表达与视觉系统.md`, `intake/阶段5：P1-P22 单页设计骨架.md`. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1, Image 2, Image 3, and Image 4 only as style continuity references: dark navy-black executive AI maritime operation map, subtle coordinate grid, radar scan rings, compass geometry, cyan route glow, restrained gold highlights, serious deepwater business-analysis mood. Do not copy their exact layout. + +Page: P11 / S-11. Main title, large and readable in bold modern Chinese sans-serif: "不是写提示词，而是专家能力工程化". Core judgment under the title: "只会调用模型，不等于会做专家智能体". + +Design a left/right comparison. Left panel is the low-lit surface "表演层": a small stage-like platform, chat window fragments, prompt cards, model API icon, tool-call blocks. Use muted gray-blue. Short labels only: "角色设定", "提示词", "接模型", "工具调用", "输出结果". + +Right panel is the brighter deep engineering layer "工程化层": a precision expert-model core inside a technical cutaway, responsibility boundary grid, evaluation dashboard, calibration gauge, workflow-entry line. Use cyan and restrained gold. Short labels only: "岗位职责", "依据判断", "能力边界", "人工介入", "解释校准", "进入流程". + +Between the panels place a glowing vertical boundary line with the readable transition label: "能回答 → 能负责". Add a bottom dark translucent judgment bar with gold emphasis: "如果只写一个提示词，那是 AI 表演，不是专家能力工程化". + +Keep one big judgment, one core diagram, and short labels. Avoid long paragraphs, logos, watermarks, human portraits, robots, stock meeting photos, customer proposal style, cyberpunk neon overload, and decorative ocean scenes with no business logic. + +## Negative / Avoid + +Do not make Prompt look worthless; do not attack platforms or developers; do not use long copied source text; do not add brand logos. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s11/s11-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-brief.md new file mode 100644 index 0000000..c66f93a --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-brief.md @@ -0,0 +1,72 @@ +# S-12 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +通过双流程对比讲清我们与普通 AI 开发公司的区别。 + +## First Read + +前者做 AI 功能开发，后者做专家能力工程化。 + +## Risk Class + +core motif / PPT page / process comparison + +## Reference Plan + +- Active style module: Module C / Our Positioning. +- Core motif: 专家能力工程化管线 + 精密模具 + workflow line. +- Reference images: four loaded style continuity references. +- Character references: none. + +## Visual Requirements + +Left path should feel like a conventional AI feature development pipeline. Right path should feel like diagnostic deepwater exploration plus expert capability engineering. + +## Character Handling + +No character identity. Avoid literal workers or portraits. + +## Composition / Scale + +Two-column process map, readable header, central contrast label, bottom judgment strip. + +## Light / Color / Texture + +Deep navy-black map base, cyan route line, restrained gold on key decision and validation nodes. + +## Forbidden Drift + +No developer-company bashing, no “we are万能”, no crowded tiny process text, no generic dashboard, no logos. + +## Acceptance Checklist + +- Two paths are visibly different. +- Right path starts from problem nature, not feature request. +- Key labels are short. +- Title and core judgment readable. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save prompt first; generate with host image tool; copy final image to `slides/s12/s12-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-design.md new file mode 100644 index 0000000..f8868cb --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-design.md @@ -0,0 +1,63 @@ +# S-12 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P12 / S-12 only + +## Design Purpose + +本页是流程对比页，承接 P11，帮助销售用一张图讲清普通 AI 开发公司路径与我们的路径差异。 + +## Discussion Summary + +页面不贬低开发公司，重点是“出发点不同”：普通路径从功能开始，我们从问题性质、专家经验和智能流验证开始。 + +## Visual Concept + +双流程图。左侧是短、直、偏工程交付的 AI 功能开发流水线；右侧是分层的深水区探测与专家能力工程化路线。中间用“AI 功能开发 vs 专家能力工程化”作为视觉分割。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 保持深蓝黑航线作战图背景。 +- 左侧流程收敛、灰蓝、机械流水线感。 +- 右侧流程分层、青金高亮、包含探测 / 抽取 / 定义 / 验证 / 校准 / 系统化。 + +## Text / Typography Plan + +- 主标题：普通 AI 开发公司的路径 vs 我们的路径 +- 核心判断：前者做 AI 功能开发，后者做专家能力工程化 +- 左侧节点：需求、功能清单、选模型、Prompt、RAG / 工作流、上线调试 +- 右侧节点：业务困惑、QPI 判断、该不该做 AI、专家抽取、岗位定义、智能流验证、试点校准、系统化建设 +- 底部金句：普通路径从功能开始，我们从问题性质开始 + +## Layout / Safe Areas + +- 顶部标题区清晰保留。 +- 左右两条路线并排，右侧可以更长但必须分层减密。 +- 底部金句留出完整安全区。 + +## Color Guidance + +- 左侧灰蓝与白，低对比度。 +- 右侧青色路径与金色关键节点。 +- 统一使用白色 / 浅蓝标题文字。 + +## Post-Production Notes + +如果节点文字细节不完全准确，后续可覆盖；主图必须保留“短功能流水线 vs 深水诊断路线”的结构。 + +## Constraints / Avoid + +- 不说别人不会开发。 +- 不塞入完整长流程原文。 +- 不生成客户版销售提案风。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-prompt.md new file mode 100644 index 0000000..9426935 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s12/s12-v1-prompt.md @@ -0,0 +1,54 @@ +# S-12 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s12/s12-v1-image.png` + +## Based On Brief + +`slides/s12/s12-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: `SKILL.md`, `references/prompt-writing.md`, `references/slides-and-visual-docs/visual-report-page.md`, `references/slides-and-visual-docs/dense-explainer-slides.md`, `references/slides-and-visual-docs/educational-diagram-slide.md`, and system `imagegen/SKILL.md`. +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `visual-system/style/style-prompt-master.md`, `visual-system/motifs/motif-registry.md`, and the three accepted intake files. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1-4 as style continuity references only: dark navy-black executive AI route-map base, radar rings, compass geometry, deepwater business layers, cyan signal paths, restrained gold key markers, sober analytical tone. + +Page: P12 / S-12. Main title, large readable Chinese: "普通 AI 开发公司的路径 vs 我们的路径". Core judgment: "前者做 AI 功能开发，后者做专家能力工程化". + +Make a dual-process comparison. Left column is "普通 AI 开发路径": a short straight gray-blue development pipeline with compact nodes labeled "需求", "功能清单", "选模型", "Prompt", "RAG / 工作流", "上线调试". It should look capable but shallow, like an engineering conveyor. + +Right column is "我们的路径": a deeper layered route through an AI deepwater operation map, with brighter cyan path and gold decision markers. Nodes: "业务困惑", "QPI 判断", "该不该做 AI", "专家抽取", "岗位定义", "智能流验证", "试点校准", "系统化建设". Use small probe-route visuals, a precision mold core, and workflow-entry line. + +In the center add a strong contrast label: "AI 功能开发 vs 专家能力工程化". Bottom judgment bar: "普通路径从功能开始，我们从问题性质开始". + +Keep the page rigorous, readable, and not overcrowded. Use one title, one core judgment, two process lanes, and short labels only. Avoid logos, watermarks, developer-bashing, platform-bashing, generic SaaS dashboards, humanoid robots, stock meeting people, and long paragraphs. + +## Negative / Avoid + +Do not imply ordinary AI developers are incapable; show a different starting logic. Do not overload the right path with tiny unreadable text. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s12/s12-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-brief.md new file mode 100644 index 0000000..57aadab --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-brief.md @@ -0,0 +1,72 @@ +# S-13 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +破除错误竞争思路，进入客户选择理由模块。 + +## First Read + +我们不和平台抢工具，不和外包拼低价。 + +## Risk Class + +PPT page / customer choice / contrast map + +## Reference Plan + +- Active style module: Module D / Customer Choice. +- Core motif: AI 深水区 + 决策罗盘 / route checkpoints. +- Reference images: four loaded style continuity references. +- Character references: none. + +## Visual Requirements + +Show the wrong competition lane as shallow and gray. Show the right value lane as a luminous route into business deepwater. + +## Character Handling + +No human portraits. No literal customer meeting scene. + +## Composition / Scale + +Asymmetric contrast: left shallow trap, right deepwater route. Bottom statement ties the page together. + +## Light / Color / Texture + +Deep blue-black with cyan route and gold confidence markers. Left side muted and low saturation. + +## Forbidden Drift + +No real platform logo wall, no price-war advertisement, no “we are biggest/cheapest/万能”, no customer proposal styling. + +## Acceptance Checklist + +- The three wrong competition modes are visible but de-emphasized. +- The four true value reasons are prominent. +- Deepwater route motif is clear. +- Main title and core judgment readable. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save prompt first; generate with host image tool; copy final image to `slides/s13/s13-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-design.md new file mode 100644 index 0000000..928915b --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-design.md @@ -0,0 +1,63 @@ +# S-13 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P13 / S-13 only + +## Design Purpose + +本页进入“客户为什么选择我们”模块，先建立正确竞争姿态，避免销售把自己拖进拼平台、拼低价、拼万能。 + +## Discussion Summary + +页面要让销售记住：我们不是最大平台、最低价格或万能 AI 团队；客户选择我们，是因为我们能进入业务深水区。 + +## Visual Concept + +左侧是错误竞争方式的浅滩：平台墙、价格牌、万能功能清单，整体灰暗。右侧是正确价值理由的深水航道：场景判断、专家抽取、智能流验证、持续校准四个发光航标，路线绕开价格战浅滩进入深水区。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 深蓝黑作战图底板，左浅右深。 +- 左侧“拼平台 / 拼低价 / 拼万能”必须显得不稳妥。 +- 右侧“场景判断 / 专家抽取 / 智能流验证 / 持续校准”必须是主视觉。 + +## Text / Typography Plan + +- 主标题：客户选择我们，不是因为我们最大或最便宜 +- 核心判断：我们不和平台抢工具，不和外包拼低价 +- 左侧三不：最大平台、最低价格、什么都做 +- 右侧四是：场景判断、专家抽取、智能流验证、持续校准 +- 底部金句：客户选择我们，是因为我们能进业务深水区 + +## Layout / Safe Areas + +- 左侧约 40%，右侧约 50%，中间用航道转向连接。 +- 顶部标题与底部金句保持大字号。 +- 右侧关键价值理由保持可读。 + +## Color Guidance + +- 左侧灰色、低亮度、浅滩感。 +- 右侧青色路线与金色航标。 +- 深水区使用更深的蓝黑剖面。 + +## Post-Production Notes + +如果模型生成的左侧 logo 墙出现具体品牌，后续应视为不可用并 append-only 修复；本版 prompt 明确禁止真实 logo。 + +## Constraints / Avoid + +- 不出现真实平台 logo。 +- 不显得我们在攻击平台或外包。 +- 不使用价格战营销海报风。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-prompt.md new file mode 100644 index 0000000..d350216 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s13/s13-v1-prompt.md @@ -0,0 +1,54 @@ +# S-13 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s13/s13-v1-image.png` + +## Based On Brief + +`slides/s13/s13-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: `SKILL.md`, `prompt-writing.md`, `visual-report-page.md`, `dense-explainer-slides.md`, `educational-diagram-slide.md`, and system `imagegen/SKILL.md`. +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `style-prompt-master.md`, `motif-registry.md`, and the three accepted intake files. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1-4 as style continuity references only: sober dark navy-black AI maritime operation map, radar and compass overlays, glowing cyan route lines, restrained gold confidence markers, deepwater business cross-section. + +Page: P13 / S-13. Main title, large readable Chinese: "客户选择我们，不是因为我们最大或最便宜". Core judgment: "我们不和平台抢工具，不和外包拼低价". + +Build an asymmetric contrast map. Left side is a gray shallow-water trap labeled "错误竞争方式", with three muted warning tiles: "最大平台", "最低价格", "什么都做". Use abstract price tags, anonymous platform-block wall with no real logos, and overloaded feature-list cards. It should look like a risky shallow route, not an enemy. + +Right side is the main value route into AI deepwater, with a luminous cyan path and four gold/cyan checkpoints: "场景判断", "专家抽取", "智能流验证", "持续校准". Show the route bypassing the shallow trap and entering a structured deep business layer with subtle workflow lines. + +Bottom judgment bar, readable: "客户选择我们，是因为我们能进业务深水区". + +Keep the tone mature and internal. Do not attack platforms or outsourcing teams. Avoid real brand logos, watermarks, human portraits, stock meetings, customer proposal style, cheap advertisement style, cyberpunk neon overload, and long text blocks. + +## Negative / Avoid + +No real logos; no platform-bashing; no low-price marketing style; no claim that we are biggest, cheapest, or万能. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s13/s13-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-brief.md new file mode 100644 index 0000000..ddd8228 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-brief.md @@ -0,0 +1,72 @@ +# S-14 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +说明客户选择我们的第一个理由：我们能判断该不该做 AI。 + +## First Read + +选对方向，是 AI 项目最重要的第一步。 + +## Risk Class + +PPT page / decision compass / customer choice + +## Reference Plan + +- Active style module: Module D / Customer Choice. +- Core motif: 决策罗盘. +- Reference images: four loaded style continuity references. +- Character references: none. + +## Visual Requirements + +Make the decision compass the primary visual. It should show judgment before implementation, not a generic AI hype diagram. + +## Character Handling + +No people. No customer portraits. + +## Composition / Scale + +Central compass, four axis labels, wrong route vs right route, bottom judgment bar. + +## Light / Color / Texture + +Deep navy-black map base, cyan compass geometry, gold key route, muted red/gray wrong path. + +## Forbidden Drift + +No AI trend lecture, no generic four-quadrant consulting slide, no dense customer-mistake text, no platform conflict. + +## Acceptance Checklist + +- Center question “该不该做 AI？” visible. +- Four judgment axes visible. +- Wrong route vs right route understood. +- Title and core judgment readable. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save prompt first; generate with host image tool; copy final image to `slides/s14/s14-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-design.md new file mode 100644 index 0000000..d964f9f --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-design.md @@ -0,0 +1,64 @@ +# S-14 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P14 / S-14 only + +## Design Purpose + +本页是客户选择理由 1，强调我们能先帮客户判断“该不该做 AI”，而不是客户说什么就接什么。 + +## Discussion Summary + +页面要把“方向判断”做成可视化罗盘：AI 项目前最重要的一步不是马上开发，而是判断场景、组织、信息化基础和权力结构是否适合进入智能化。 + +## Visual Concept + +中心是决策罗盘“该不该做 AI？”，四个方向轴分别是场景价值、组织认知、信息化基础、权力结构。画面同时呈现错误航线和正确航线，像进入 AI 深水区前的入海检查站。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 深蓝黑作战图底板，罗盘 / 雷达 / 航线是主视觉。 +- 用检查站和航线偏差表现“方向错了，后面越努力越浪费”。 +- 不出现客户会议或人物头像。 + +## Text / Typography Plan + +- 主标题：我们能帮客户判断“该不该做 AI” +- 核心判断：选对方向，是 AI 项目最重要的第一步 +- 中心：该不该做 AI？ +- 四轴：场景价值、组织认知、信息化基础、权力结构 +- 路径选项：培训、顾问、试点、系统 +- 底部金句：方向错了，后面越努力越浪费 + +## Layout / Safe Areas + +- 中央罗盘占画面核心 45%-55%。 +- 四周短标签环绕，避免密集文字。 +- 错误航线与正确航线用颜色区分。 + +## Color Guidance + +- 罗盘主线用青色。 +- 正确路径用青金高亮。 +- 错误路径用低饱和红 / 灰色警示，避免过度刺眼。 + +## Post-Production Notes + +后期可覆盖个别小标签；罗盘结构和“先判断方向”的主视觉必须保留。 + +## Constraints / Avoid + +- 不把页面做成普通咨询四象限。 +- 不出现过多客户误区原文。 +- 不暗示客户都不懂 AI。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-prompt.md new file mode 100644 index 0000000..094ecd8 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s14/s14-v1-prompt.md @@ -0,0 +1,54 @@ +# S-14 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s14/s14-v1-image.png` + +## Based On Brief + +`slides/s14/s14-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: `SKILL.md`, `prompt-writing.md`, `visual-report-page.md`, `dense-explainer-slides.md`, `educational-diagram-slide.md`, and system `imagegen/SKILL.md`. +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `style-prompt-master.md`, `motif-registry.md`, and the three accepted intake files. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1-4 as style continuity references only: dark navy-black AI maritime route map, radar rings, compass lines, deepwater cross-section, cyan signal glow, restrained gold highlights, sober internal judgment mood. + +Page: P14 / S-14. Main title in large readable Chinese: "我们能帮客户判断“该不该做 AI”". Core judgment: "选对方向，是 AI 项目最重要的第一步". + +Make a large central decision compass labeled "该不该做 AI？". Around it place four clean axis labels: "场景价值", "组织认知", "信息化基础", "权力结构". Add an "入海检查站" motif before the deepwater zone. + +Show two routes: a muted red/gray wrong route that starts from anxiety and goes directly toward heavy development, bending toward risk markers; and a cyan/gold correct route that passes through short waypoints "培训", "顾问", "试点", "系统" before entering the deepwater AI route. The correct route should look deliberate and professional. + +Bottom judgment bar: "方向错了，后面越努力越浪费". + +Keep text sparse and readable. Use modern bold Chinese sans-serif, white/pale-blue text, gold emphasis for the key route. Avoid a generic consulting quadrant, AI hype lecture, stock meeting people, human portraits, logos, watermarks, customer proposal style, and long paragraphs. + +## Negative / Avoid + +Do not imply all customers are naive; do not make it look like a generic four-quadrant chart; do not overload text. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s14/s14-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-brief.md new file mode 100644 index 0000000..7df00d0 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-brief.md @@ -0,0 +1,72 @@ +# S-15 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +说明客户选择我们的第二个理由：我们站在管理、信息化和 AI 的交叉处。 + +## First Read + +我们的差异来自管理咨询、信息化落地和 AI 智能化方法论的交叉能力。 + +## Risk Class + +PPT page / customer choice / capability intersection + +## Reference Plan + +- Active style module: Module D / Customer Choice. +- Core motif: 决策罗盘 + route checkpoints. +- Reference images: four loaded style continuity references. +- Character references: none. + +## Visual Requirements + +Show the intersection as a capability map, not a resume. The center should clearly represent expert-agent landing capability. + +## Character Handling + +No people. Avoid founder or personal-history framing. + +## Composition / Scale + +Central three-circle intersection, surrounding short labels, bottom development route and judgment bar. + +## Light / Color / Texture + +Deep navy-black, cyan and gold highlights, restrained executive diagram texture. + +## Forbidden Drift + +No biography display, no generic white Venn chart, no customer proposal style, no excessive credentials. + +## Acceptance Checklist + +- Three capability lines visible. +- Center “专家智能体落地能力” is the first visual read. +- Bottom gold sentence present or reserved. +- Title and core judgment readable. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save prompt first; generate with host image tool; copy final image to `slides/s15/s15-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-design.md new file mode 100644 index 0000000..d138b72 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-design.md @@ -0,0 +1,64 @@ +# S-15 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P15 / S-15 only + +## Design Purpose + +本页是客户选择理由 2，说明我们的差异来自管理咨询、信息化落地和 AI 智能化方法论的交叉能力，而不是单点技术能力。 + +## Discussion Summary + +页面不能做成个人履历展示，也不能变成泛泛的能力列表。核心是三条能力线在深水区交叉，形成专家智能体落地能力。 + +## Visual Concept + +三圆交叉图与航线结构结合。三个圆分别是“管理咨询”“信息化落地”“AI 智能化”，中心交叉区是“专家智能体落地能力 / 深水区判断能力”。下方可以有一条小型发展脉络航线：管理咨询 → 信息化 → AI 学习 → 方法论 → 智能化转型。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 深蓝黑商务底，罗盘 / 航线 / 雷达线延续。 +- 三圆交叉必须是主视觉，中心高亮。 +- 不出现具体人物、头像或履历墙。 + +## Text / Typography Plan + +- 主标题：我们同时懂管理、信息化和 AI +- 核心判断：我们的差异来自管理咨询、信息化落地和 AI 智能化方法论的交叉能力 +- 三圆标签：管理咨询、信息化落地、AI 智能化 +- 中心标签：专家智能体落地能力 +- 辅助标签：深水区判断、业务流程、系统边界、人机协作 +- 底部金句：很多团队只站在一个点上，我们站在三条线的交叉处 + +## Layout / Safe Areas + +- 顶部标题区清晰。 +- 三圆交叉位于画面中心偏上。 +- 底部脉络线和金句留出安全区。 + +## Color Guidance + +- 三圆用不同但克制的青蓝、金色、冷白边线。 +- 中心交叉区使用金色高亮。 +- 背景保持深蓝黑，不转为彩色商业图表。 + +## Post-Production Notes + +如小标签不够准确，后期可覆盖；三条能力线交叉的结构必须保留。 + +## Constraints / Avoid + +- 不做个人简历页。 +- 不做普通 Venn 图白底风。 +- 不暗示单一技术能力足够。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-prompt.md new file mode 100644 index 0000000..ecf3b66 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s15/s15-v1-prompt.md @@ -0,0 +1,52 @@ +# S-15 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s15/s15-v1-image.png` + +## Based On Brief + +`slides/s15/s15-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: `SKILL.md`, `prompt-writing.md`, `visual-report-page.md`, `dense-explainer-slides.md`, `educational-diagram-slide.md`, and system `imagegen/SKILL.md`. +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `style-prompt-master.md`, `motif-registry.md`, and the three accepted intake files. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1-4 as style continuity references only: dark navy-black executive route map, compass geometry, radar rings, cyan signal lines, restrained gold highlights, deepwater analytical atmosphere. + +Page: P15 / S-15. Main title in large readable Chinese: "我们同时懂管理、信息化和 AI". Core judgment: "我们的差异来自管理咨询、信息化落地和 AI 智能化方法论的交叉能力". + +Design a central three-circle intersection map, integrated into the dark AI maritime operation map rather than a white Venn diagram. Three large overlapping rings: "管理咨询", "信息化落地", "AI 智能化". The center intersection glows in restrained gold and cyan with the label: "专家智能体落地能力". Around the center add small labels: "深水区判断", "业务流程", "系统边界", "人机协作". + +Add a subtle bottom route timeline: "管理咨询 → 信息化 → AI 学习 → 方法论 → 智能化转型". Bottom judgment bar: "很多团队只站在一个点上，我们站在三条线的交叉处". + +Keep the page sober and company-level, not a personal resume. Avoid portraits, biography walls, stock meetings, generic SaaS dashboards, logos, watermarks, bright colorful Venn chart style, and long paragraphs. Text should be short, high contrast, and readable. + +## Negative / Avoid + +No personal profile page; no white-background Venn chart; no claims of万能 expertise. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s15/s15-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-brief.md new file mode 100644 index 0000000..50df4ae --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-brief.md @@ -0,0 +1,72 @@ +# S-16 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +说明客户选择我们的第三个理由：我们能抽取专家经验，而不是只上传资料。 + +## First Read + +不是把资料塞给 AI，而是把专家能力教给 AI。 + +## Risk Class + +PPT page / iceberg model / expert experience extraction + +## Reference Plan + +- Active style module: Module D / Customer Choice. +- Core motif: 经验冰山 + 专家能力工程化管线. +- Reference images: four loaded style continuity references. +- Character references: none. + +## Visual Requirements + +Make the iceberg logic unmistakable: documents above water, tacit expert judgment below water, extraction pipeline to expert agent. + +## Character Handling + +No visible identity. Avoid literal old master portrait. + +## Composition / Scale + +Large iceberg on left/center, pipeline on right, bottom judgment bar. + +## Light / Color / Texture + +Dark deepwater layers, cyan knowledge points, gold extraction path. + +## Forbidden Drift + +No generic RAG product marketing, no document-upload-as-success message, no warm cartoon style, no long source paragraphs. + +## Acceptance Checklist + +- Waterline split is clear. +- Underwater expert judgment layer is richer than document layer. +- Extraction pipeline is visible. +- Title and core judgment readable. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save prompt first; generate with host image tool; copy final image to `slides/s16/s16-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-design.md new file mode 100644 index 0000000..9413ef0 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-design.md @@ -0,0 +1,64 @@ +# S-16 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P16 / S-16 only + +## Design Purpose + +本页是客户选择理由 3，说明专家智能体不是把资料上传给 AI，而是把隐性专家判断抽取成可用能力。 + +## Discussion Summary + +页面用冰山图讲清“文档只是表层，专家判断在水下”。避免把页面做成普通知识库宣传图。 + +## Visual Concept + +冰山剖面。水面上是文档、资料、知识库；水面下是经验、判断、反例、取舍、边界、潜规则。右侧有抽取管线：隐性经验 → 显性模型 → 专家智能体。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 深蓝黑海面和深水剖面必须明显。 +- 水下经验层应比水面文档层更丰富、更有价值。 +- 不出现具象老师傅人物，不做温情插画。 + +## Text / Typography Plan + +- 主标题：我们能抽取专家经验，而不是只上传资料 +- 核心判断：不是把资料塞给 AI，而是把专家能力教给 AI +- 水面上：文档、资料、知识库 +- 水面下：经验、判断、反例、取舍、边界、潜规则 +- 右侧管线：隐性经验 → 显性模型 → 专家智能体 +- 底部金句：文档是知识的影子，专家判断才是能力本体 + +## Layout / Safe Areas + +- 左中区域放冰山剖面。 +- 右侧放抽取管线。 +- 标题与底部金句保留清晰安全区。 + +## Color Guidance + +- 水面上冷白 / 浅蓝。 +- 水下深蓝，经验节点用青色光点。 +- 管线关键节点用金色。 + +## Post-Production Notes + +后期可重排标签；必须保留“水面文档 / 水下判断 / 管线抽取”的三段结构。 + +## Constraints / Avoid + +- 不把知识库问答等同于专家智能体。 +- 不出现人物脸或真实员工形象。 +- 不塞入大量经验清单。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-prompt.md new file mode 100644 index 0000000..080e035 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-prompt.md @@ -0,0 +1,54 @@ +# S-16 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s16/s16-v1-image.png` + +## Based On Brief + +`slides/s16/s16-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: `SKILL.md`, `prompt-writing.md`, `visual-report-page.md`, `dense-explainer-slides.md`, `educational-diagram-slide.md`, and system `imagegen/SKILL.md`. +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `style-prompt-master.md`, `motif-registry.md`, and the three accepted intake files. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1-4 as style continuity references only: dark navy-black AI maritime operation map, deepwater cross-section, radar/compass overlays, cyan signal light, restrained gold highlights, sober business judgment tone. + +Page: P16 / S-16. Main title in large readable Chinese: "我们能抽取专家经验，而不是只上传资料". Core judgment: "不是把资料塞给 AI，而是把专家能力教给 AI". + +Create a strong iceberg cross-section. Above the waterline show a small visible layer with documents and knowledge-base blocks labeled "文档", "资料", "知识库". Below the waterline show a much larger, richer deep layer made of glowing expert-judgment nodes labeled "经验", "判断", "反例", "取舍", "边界", "潜规则". Make the underwater layer feel valuable and difficult to extract. + +On the right, add a cyan/gold extraction pipeline with three clear stages: "隐性经验" → "显性模型" → "专家智能体". The pipeline should connect to the underwater nodes and become a structured expert-agent core. + +Bottom judgment bar: "文档是知识的影子，专家判断才是能力本体". + +Keep the style serious and technical, not cute or warm. No human portraits, no literal old craftsman, no generic RAG marketing page, no logos, no watermarks, no stock office scenes, no long paragraphs. Text should be short and readable. + +## Negative / Avoid + +Do not make document upload look sufficient. Do not use a friendly cartoon iceberg. Do not show identifiable people. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s16/s16-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-brief.md new file mode 100644 index 0000000..3341955 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-brief.md @@ -0,0 +1,72 @@ +# S-17 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +说明客户选择我们的第四个理由：先验证智能流，再投入系统建设。 + +## First Read + +很多 AI 项目失败，是因为太早开发。 + +## Risk Class + +PPT page / route comparison / validation path + +## Reference Plan + +- Active style module: Module D / Customer Choice. +- Core motif: 智能流试航. +- Reference images: four loaded style continuity references. +- Character references: none. + +## Visual Requirements + +Show a wrong heavy-build route and a correct validation route. The validation route should feel like disciplined engineering, not hesitation. + +## Character Handling + +No people. No literal customer team photo. + +## Composition / Scale + +Two horizontal routes, upper risk route and lower validated route, with bottom judgment bar. + +## Light / Color / Texture + +Deepwater map base, cyan validated path, gold decision points, muted risk red for wrong route. + +## Forbidden Drift + +No waterfall project-management chart, no cute ship, no implication of weak development capability, no dense paragraph text. + +## Acceptance Checklist + +- Upper route shows too-early heavy development risk. +- Lower route shows minimum intelligent flow validation. +- “先跑通价值” is first-read or bottom-read. +- Title and core judgment readable. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save prompt first; generate with host image tool; copy final image to `slides/s17/s17-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-design.md new file mode 100644 index 0000000..666429b --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-design.md @@ -0,0 +1,63 @@ +# S-17 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P17 / S-17 only + +## Design Purpose + +本页是客户选择理由 4，强调先验证智能流，再决定是否投入系统建设，避免太早进入重开发。 + +## Discussion Summary + +页面要把“先跑通价值，再投入开发”讲成专业方法，不要让人误解为开发能力不足或试试看。 + +## Visual Concept + +双路线图。上方是错误的重开发路线：需求一来就做页面、接口、知识库、Prompt、系统，最后触礁。下方是正确的智能流验证路线：专家 + AI 工具先跑最小智能流，经过试点、反馈、校准，再系统化建设。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 深水航线作战图背景。 +- 上方错误路线要有风险标记但不夸张。 +- 下方正确路线要显得稳健、专业、可复制。 + +## Text / Typography Plan + +- 主标题：我们先验证智能流，再投入系统建设 +- 核心判断：很多 AI 项目失败，是因为太早开发 +- 上方错误路径：需求、页面、接口、知识库、Prompt、系统、没人用 +- 下方正确路径：专家 + AI 工具、最小智能流、试点、反馈、校准、系统化 +- 底部金句：先跑通价值，再投入开发 + +## Layout / Safe Areas + +- 上下两条路线图，错误路径占上方 35%，正确路径占下方 45%。 +- 标题和底部金句保留大字号。 +- 路线方向从左到右。 + +## Color Guidance + +- 错误路径用灰蓝和低饱和红色风险点。 +- 正确路径用青色与金色。 +- 背景保持深蓝黑。 + +## Post-Production Notes + +如果路线节点文字需要覆盖，保留上下路线和触礁 / 试航的主视觉即可。 + +## Constraints / Avoid + +- 不让页面显得“先试试是因为不会开发”。 +- 不做项目管理甘特图。 +- 不使用卡通船。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-prompt.md new file mode 100644 index 0000000..63fb04e --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s17/s17-v1-prompt.md @@ -0,0 +1,54 @@ +# S-17 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s17/s17-v1-image.png` + +## Based On Brief + +`slides/s17/s17-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: `SKILL.md`, `prompt-writing.md`, `visual-report-page.md`, `dense-explainer-slides.md`, `educational-diagram-slide.md`, and system `imagegen/SKILL.md`. +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `style-prompt-master.md`, `motif-registry.md`, and the three accepted intake files. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1-4 as style continuity references only: dark navy-black AI maritime operation map, deepwater business cross-section, radar and compass overlays, cyan route glow, restrained gold highlights, serious internal decision tone. + +Page: P17 / S-17. Main title in large readable Chinese: "我们先验证智能流，再投入系统建设". Core judgment: "很多 AI 项目失败，是因为太早开发". + +Make two horizontal route maps. Upper route is the wrong heavy-development path, muted gray-blue with restrained red risk markers. It starts from "需求" and moves through "页面", "接口", "知识库", "Prompt", "系统", ending at "没人用" near a subtle reef / warning marker. It should look risky but not cartoonish. + +Lower route is the correct validation path, brighter cyan and gold, disciplined and professional. It starts with "专家 + AI 工具", then "最小智能流", "试点", "反馈", "校准", "系统化". Show a small probe route validating value before a larger engineering vessel enters deepwater, but keep the visual abstract and business-like. + +Bottom judgment bar: "先跑通价值，再投入开发". + +Keep text sparse and readable. Avoid project-management Gantt chart style, cute ships, stock people, customer proposal style, logos, watermarks, long paragraphs, and any implication that validation is due to weak development capability. + +## Negative / Avoid + +Do not make this feel like hesitation or inability to develop. Do not use cartoon ships. Do not overload node text. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s17/s17-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-brief.md new file mode 100644 index 0000000..221c805 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-brief.md @@ -0,0 +1,72 @@ +# S-18 Slide Brief V1 + +## Status + +- Line: production-light +- Running mode: prompt and generate +- Review mode: none +- Version: v1 +- Overwrite allowed: no + +## Source Basis + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +## Slide Function + +说明客户选择我们的第五个理由：AI 出错后能够发现、解释、纠正、沉淀并持续迭代。 + +## First Read + +AI 出错后，要能被发现、解释、纠正和沉淀。 + +## Risk Class + +PPT page / calibration loop / customer choice + +## Reference Plan + +- Active style module: Module D / Customer Choice. +- Core motif: 校准闭环. +- Reference images: four loaded style continuity references. +- Character references: none. + +## Visual Requirements + +Make the calibration loop the primary visual. The page should communicate controllability and continuous improvement. + +## Character Handling + +No people. No operator portrait. + +## Composition / Scale + +Central loop with seven nodes, surrounding five capability badges, bottom judgment bar. + +## Light / Color / Texture + +Deep navy-black system map, cyan loop, gold calibration highlights, subtle red error capture markers. + +## Forbidden Drift + +No claim that AI never fails, no generic operations dashboard, no long failure list, no stock people. + +## Acceptance Checklist + +- Calibration loop is clear. +- Five “可...” capabilities are visible. +- The page answers “AI 错了怎么办”. +- Title and core judgment readable. +- No review file produced. + +## Prompt Handoff + +Use GPT Image 2 Advisor / host-native Mode B. Save prompt first; generate with host image tool; copy final image to `slides/s18/s18-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-design.md new file mode 100644 index 0000000..1236dae --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-design.md @@ -0,0 +1,64 @@ +# S-18 Slide Design V1 + +## Status + +- Line: production-light +- Review mode: none +- Version: v1 +- Overwrite allowed: no +- Scope: P18 / S-18 only + +## Design Purpose + +本页是客户选择理由 5，回答客户对 AI 效果和错误处理的担心：我们不只追求能跑，还追求好改。 + +## Discussion Summary + +页面应强调纠错机制和校准机制，而不是承诺 AI 永不出错。视觉上使用闭环图、仪表盘、反馈槽、校准旋钮和版本迭代曲线。 + +## Visual Concept + +中心闭环：AI 输出 → 专家审查 → 用户反馈 → 错误解释 → 修正记录 → 模型 / 流程 / 规则校准 → 再次输出。环外放五个能力标签：可发现、可解释、可纠正、可沉淀、可迭代。 + +## Image Base Requirements + +- 16:9 full-page visual slide image. +- 深蓝黑作战图底板，中心校准闭环必须清晰。 +- 画面要像可靠系统的校准控制台，不像普通 dashboard。 +- 不出现“AI 永不出错”的暗示。 + +## Text / Typography Plan + +- 主标题：我们不只追求能跑，还追求好改 +- 核心判断：AI 出错后，要能被发现、解释、纠正和沉淀 +- 闭环节点：AI 输出、专家审查、用户反馈、错误解释、修正记录、规则校准、再次输出 +- 五个能力：可发现、可解释、可纠正、可沉淀、可迭代 +- 底部金句：普通 AI 开发交付结果，我们交付结果，同时交付纠错机制和校准机制 + +## Layout / Safe Areas + +- 中央闭环占画面主体。 +- 五个能力标签沿环外分布。 +- 右侧或下方放校准仪表 / 版本曲线。 +- 底部金句保持可读。 + +## Color Guidance + +- 主闭环用青色。 +- 纠错 / 校准关键节点用金色。 +- 风险 / 错误标记用低饱和红色，不抢主视觉。 + +## Post-Production Notes + +如果底部金句过长，后期可覆盖为短句；中心闭环和五个能力标签必须保留。 + +## Constraints / Avoid + +- 不承诺 AI 不犯错。 +- 不做普通运维 dashboard。 +- 不使用大段错误案例文字。 +- 不写 review 文件。 + +## Confirmation Gate + +已由任务级指令授权完整链路：design -> brief -> prompt -> host image generation。 diff --git a/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-prompt.md new file mode 100644 index 0000000..eb00201 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s18/s18-v1-prompt.md @@ -0,0 +1,54 @@ +# S-18 Slide Prompt V1 + +## Status + +- Prompt saved before generation. +- Line: production-light +- Review mode: none +- Output image: `slides/s18/s18-v1-image.png` + +## Based On Brief + +`slides/s18/s18-v1-brief.md` + +## Reference Inputs + +- Image 1: `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 2: `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. +- Image 3: `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` as style continuity reference, not edit target. +- Image 4: `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` as style continuity reference, not edit target. + +## Operation Notes + +- Use the loaded reference images only for visual continuity. +- Do not call Garden generation scripts. +- Backup fact-check source was not opened or used; no factual claim needed verification. + +## Advisor / Host-Native Record + +- Skill mode command: `node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json` +- Mode result: `B-or-C`; recommendation: `host-or-advisor`; Garden disabled; API key absent; effective path: Mode B because host `image_gen` is available. +- Skill/template files read: `SKILL.md`, `prompt-writing.md`, `visual-report-page.md`, `dense-explainer-slides.md`, `educational-diagram-slide.md`, and system `imagegen/SKILL.md`. +- Project files actually read: `AGENTS.md`, `project.md`, `execution-plan.md`, `slides/slides.md`, `visual-system/visual-system.md`, `style-prompt-master.md`, `motif-registry.md`, and the three accepted intake files. + +## Final Prompt + +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Use Image 1-4 as style continuity references only: dark navy-black executive AI maritime operation map, subtle coordinate grid, radar/compass overlays, cyan signal paths, restrained gold highlights, serious deepwater business-system tone. + +Page: P18 / S-18. Main title in large readable Chinese: "我们不只追求能跑，还追求好改". Core judgment: "AI 出错后，要能被发现、解释、纠正和沉淀". + +Create a central calibration loop, like a reliable expert-agent control system rather than a generic dashboard. Loop nodes in order: "AI 输出" → "专家审查" → "用户反馈" → "错误解释" → "修正记录" → "规则校准" → "再次输出". Use cyan loop lines and restrained gold on the calibration nodes. + +Around the loop place five capability badges: "可发现", "可解释", "可纠正", "可沉淀", "可迭代". Add subtle visual details: feedback slot, calibration knob, version iteration curve, captured error marker entering a structured data layer. + +Bottom judgment bar: "交付纠错机制和校准机制". If space allows, include smaller text: "不是只交付能跑的结果". + +Keep the page sober, technical, and reassuring. Do not imply AI never fails. Avoid generic operations dashboard, stock office people, human portraits, robots, logos, watermarks, long paragraphs, and bright cyberpunk neon overload. + +## Negative / Avoid + +Do not promise zero errors. Do not make a generic monitoring dashboard. Do not use long failure text. + +## Output Intent + +Copy host-generated image to `projects/2026-07-01-为什么是我们/slides/s18/s18-v1-image.png`. diff --git a/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-brief.md new file mode 100644 index 0000000..8c02498 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-brief.md @@ -0,0 +1,67 @@ +# S-19 Slide Brief V1 + +## Page + +- Page: P19 / S-19. +- Title: 我们的商业差异成立，但不是天然成立. +- Function: sober internal judgment. +- Core conclusion: 差异必须靠案例、工具、流程、评测和团队复制能力证明。 + +## Source Basis + +Primary sources: + +- `intake/阶段5：P1-P22 单页设计骨架.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` + +Control and style sources: + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` + +Backup fact-check source: + +- not used. + +## Visible Text + +Title: + +> 我们的商业差异成立，但不是天然成立 + +Core judgment: + +> 差异不是喊出来的，必须被证明 + +Evidence labels: + +> 案例 / 工具 / 流程 / 评测 / 复制 + +Status labels: + +> 有基础 / 待补齐 / 需产品化 + +Bottom line: + +> 清醒的信心，比盲目的信心更值钱 + +## Visual Requirements + +- 16:9 full-page visual image. +- Deep navy-black AI route-map and deepwater business atmosphere. +- Five evidence-chain lighthouses / pillars along a route. +- Mixed maturity states: some lit, some under construction. +- Cyan route signal and restrained gold proof highlights. +- No review file for production-light. + +## Generation Notes + +- Current `gpt-image-2` mode: `B-or-C`. +- Effective route: Mode B, host-native image generation. +- Garden scripts: not used. +- Reference images: style continuity only, not edit targets. diff --git a/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-design.md new file mode 100644 index 0000000..0556790 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-design.md @@ -0,0 +1,70 @@ +# S-19 Slide Design V1 + +## Status + +- Status: production-light design. +- Source page: P19. +- Page title: 我们的商业差异成立，但不是天然成立. +- Line: production-light. +- Review: none. +- Write policy: append-only; overwrite allowed: no. + +## Design Purpose + +S-19 是内部清醒页。前面已经讲清“客户为什么选择我们”，这一页必须把销售从过度自信拉回到可证明的作战状态： + +> 差异不是喊出来的，必须靠案例、工具、流程、评测和团队复制能力证明。 + +本页要保留信心，但信心来自证据链，不来自口号。 + +## Visual Concept + +画面是“AI 深水航道上的五座证据链灯塔”。左侧是一个尚未完全点亮的“商业差异”核心标记，右侧沿着深水航道排列五座灯塔 / 证明支柱： + +- 案例 +- 工具 +- 流程 +- 评测 +- 复制 + +灯塔状态不完全相同：有些已经亮起，有些正在建设，有些显示“需产品化”。整体是销售作战图里的证据链，不是庆功页。 + +## Text / Typography Plan + +Title: + +> 我们的商业差异成立，但不是天然成立 + +Core judgment: + +> 差异不是喊出来的，必须被证明 + +Support labels: + +> 案例 / 工具 / 流程 / 评测 / 复制 + +Status labels: + +> 有基础 / 待补齐 / 需产品化 + +Bottom line: + +> 清醒的信心，比盲目的信心更值钱 + +Typography should use bold modern Chinese sans-serif, high-contrast white and pale blue, with restrained gold for the proof chain. + +## Layout + +- Top safe area: title. +- Left third: “商业差异” signal marker, partially connected to the route map. +- Right two thirds: five evidence lighthouses / proof pillars on the route line. +- Bottom band: short gold-white closing line. +- Background: deep navy-black AI maritime route map with radar and compass geometry. + +## Constraints / Avoid + +- Do not imply every proof is already complete. +- Do not bash platforms or AI development companies. +- Do not turn the page into a dense dashboard. +- Do not add raw source paragraphs. +- Do not use cartoon ships, humanoid robots, real people, or brand logos. diff --git a/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-prompt.md new file mode 100644 index 0000000..2d2d7d4 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s19/s19-v1-prompt.md @@ -0,0 +1,87 @@ +# S-19 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s19-v1-brief.md`. +- Line: production-light. +- Review: none. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P19 / S-19. +- Page family: E / Sober Judgment. +- Active style module: `visual-system/style/style-prompt-master.md`, Module E. +- Core motif: 证据链灯塔. +- Main title: `我们的商业差异成立，但不是天然成立` +- Core judgment: `差异不是喊出来的，必须靠案例、工具、流程、评测和团队复制能力证明。` +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Effective route: Mode B because host `image_gen` is available. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\infographics\bento-grid-infographic.md` + - `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` +- Project source files read: + - `project.md` + - `execution-plan.md` + - `slides/slides.md` + - `visual-system/visual-system.md` + - `visual-system/style/style-prompt-master.md` + - `visual-system/motifs/motif-registry.md` + - `intake/阶段3：PPT 总纲 v1.md` + - `intake/阶段4：通用表达与视觉系统.md` + - `intake/阶段5：P1-P22 单页设计骨架.md` +- Style reference images loaded into context: + - Image 1: current deck accepted cover, `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png`, role = style continuity reference only. + - Image 2: current deck accepted P10, `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png`, role = style continuity reference only. + - Image 3: previous deck accepted cover, `projects/2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png`, role = style continuity reference only. + - Image 4: previous deck accepted P10, `projects/2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png`, role = style continuity reference only. +- Backup raw material source: not used. + +## Final Host-Native Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page content slide image for an internal sales-alignment PowerPoint + +Use the visible reference images only as style continuity references: deep navy-black AI maritime operation map, cyan glowing route lines, radar and compass geometry, deepwater business-layer texture, restrained gold highlights, and large readable Chinese typography. Do not edit the reference images and do not copy their old page content. + +Create a 16:9 full-page visual slide image for Page P19 titled "我们的商业差异成立，但不是天然成立". This is a sober internal judgment page, not a celebration page. The page must communicate: our commercial difference is real, but it must be proved by evidence. + +Scene/backdrop: deep navy-black executive AI route-map background, dark ocean-chart grid, subtle coordinate lines, radar scan rings, compass marks, deepwater business layers under the route. Mood: clear confidence, not overclaiming. + +Primary visual model: an evidence-chain route in the AI deepwater zone. +- Left third: a strong but not fully completed signal marker labeled "商业差异". +- Right two thirds: five lighthouses / proof pillars standing along a glowing cyan-gold route through dark water. +- Each lighthouse represents one proof category: "案例", "工具", "流程", "评测", "复制". +- Show mixed maturity states: some lighthouses lit, some half-built, some with scaffold or calibration marks. +- Add small status tags near pillars: "有基础", "待补齐", "需产品化". + +Text (verbatim Chinese, keep readable): +- Top title: "我们的商业差异成立，但不是天然成立" +- Core judgment: "差异不是喊出来的，必须被证明" +- Five evidence labels: "案例" / "工具" / "流程" / "评测" / "复制" +- Small status labels: "有基础" / "待补齐" / "需产品化" +- Bottom line: "清醒的信心，比盲目的信心更值钱" + +Typography: bold modern Chinese sans-serif, high contrast, white or pale blue for title, cyan for active route and evidence line, restrained gold for proof highlights. Title and core judgment must be readable. + +Composition/framing: title in top safe area; left-to-right reading order; five proof pillars visually balanced; bottom line in a clean footer band. Keep diagram readable and avoid dense paragraphs. + +Lighting/mood: cinematic executive business slide, sober internal calibration, precision evidence chain, deepwater operation map. + +Color palette: deep navy-black, dark slate blue, cyan signal light, restrained warm gold, pale-blue/white typography. + +Constraints: no platform-bashing, no developer-company-bashing, no claim that all proof is complete, no customer proposal look, no government red-gold style, no humanoid robots, no concrete portraits, no platform logo wall, no generic SaaS dashboard, no cartoon ship, no pirate or fantasy ship, no dense long text, no watermark, no logo. + +## Output Intent + +Generate `s19-v1-image.png` and copy the final image into `projects/2026-07-01-为什么是我们/slides/s19/`. diff --git a/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-brief.md new file mode 100644 index 0000000..1d4f6a2 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-brief.md @@ -0,0 +1,63 @@ +# S-20 Slide Brief V1 + +## Page + +- Page: P20 / S-20. +- Title: 已经成立的部分. +- Function: build justified confidence. +- Core conclusion: 我们已经具备回答“为什么是我们”的基础。 + +## Source Basis + +Primary sources: + +- `intake/阶段5：P1-P22 单页设计骨架.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` + +Control and style sources: + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` + +Backup fact-check source: + +- not used. + +## Visible Text + +Title: + +> 已经成立的部分 + +Core judgment: + +> 我们已经具备回答“为什么是我们”的基础 + +Foundation labels: + +> AI 学习 / 培训经验 / 管理咨询 / 信息化落地 / 智能体实践 / 方法论抽象 / 团队雏形 + +Bottom line: + +> 不是从零开始，而是汇到一条新航线 + +## Visual Requirements + +- 16:9 full-page visual image. +- Deep navy-black AI route-map base. +- Capability foundation / ship keel cutaway. +- Seven labeled foundation modules supporting a central expert-agent business capability. +- Cyan signal lines and restrained gold confidence accents. +- No review file for production-light. + +## Generation Notes + +- Current `gpt-image-2` mode: `B-or-C`. +- Effective route: Mode B, host-native image generation. +- Garden scripts: not used. +- Reference images: style continuity only, not edit targets. diff --git a/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-design.md new file mode 100644 index 0000000..caf0221 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-design.md @@ -0,0 +1,68 @@ +# S-20 Slide Design V1 + +## Status + +- Status: production-light design. +- Source page: P20. +- Page title: 已经成立的部分. +- Line: production-light. +- Review: none. +- Write policy: append-only; overwrite allowed: no. + +## Design Purpose + +S-20 接在 S-19 后面，负责建立底气。它要说明“为什么是我们”不是空中楼阁，而是由长期积累汇合成的新能力。 + +核心不是个人履历展示，而是团队商业差异的能力底座。 + +## Visual Concept + +画面是“专家智能体商业能力的船体剖面 / 能力龙骨”。底部是七块发光龙骨模块，托起上方的“专家智能体商业能力”航行结构。 + +七块龙骨分别是： + +- AI 学习 +- 培训经验 +- 管理咨询 +- 信息化落地 +- 智能体实践 +- 方法论抽象 +- 团队雏形 + +这些积累从不同方向汇入同一条新航线，形成对“为什么是我们”的基础回答。 + +## Text / Typography Plan + +Title: + +> 已经成立的部分 + +Core judgment: + +> 我们已经具备回答“为什么是我们”的基础 + +Seven support labels: + +> AI 学习 / 培训经验 / 管理咨询 / 信息化落地 / 智能体实践 / 方法论抽象 / 团队雏形 + +Bottom line: + +> 不是从零开始，而是汇到一条新航线 + +Typography should match accepted S-01 / S-10: large readable title, compact short labels, cyan route signal, gold confidence accents. + +## Layout + +- Top: page title and core judgment. +- Center: ship-body / capability-platform cutaway. +- Bottom: seven keel-rib modules, each labeled and connected. +- Background: same deep AI route-map base with subtle radar/compass. +- Visual focus: foundation and accumulated capability, not biography. + +## Constraints / Avoid + +- Do not turn this into a personal resume page. +- Do not show literal staff portraits. +- Do not use generic corporate stock imagery. +- Do not add external facts or unverified claims. +- Keep labels short and readable. diff --git a/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-prompt.md new file mode 100644 index 0000000..9936d5b --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s20/s20-v1-prompt.md @@ -0,0 +1,87 @@ +# S-20 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s20-v1-brief.md`. +- Line: production-light. +- Review: none. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P20 / S-20. +- Page family: E / Sober Judgment. +- Active style module: `visual-system/style/style-prompt-master.md`, Module E. +- Core motif: 成熟度仪表盘 / 能力底座. +- Main title: `已经成立的部分` +- Core judgment: `我们已经具备回答“为什么是我们”的基础。` +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Effective route: Mode B because host `image_gen` is available. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\infographics\bento-grid-infographic.md` + - `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` +- Project source files read: + - `project.md` + - `execution-plan.md` + - `slides/slides.md` + - `visual-system/visual-system.md` + - `visual-system/style/style-prompt-master.md` + - `visual-system/motifs/motif-registry.md` + - `intake/阶段3：PPT 总纲 v1.md` + - `intake/阶段4：通用表达与视觉系统.md` + - `intake/阶段5：P1-P22 单页设计骨架.md` +- Style reference images loaded into context: + - Image 1: current deck accepted cover, role = style continuity reference only. + - Image 2: current deck accepted P10, role = style continuity reference only. + - Image 3: previous deck accepted cover, role = style continuity reference only. + - Image 4: previous deck accepted P10, role = style continuity reference only. +- Backup raw material source: not used. + +## Final Host-Native Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page content slide image for an internal sales-alignment PowerPoint + +Use the visible reference images only as style continuity references: deep navy-black AI maritime operation map, cyan glowing route lines, restrained gold highlights, radar / compass geometry, dark executive slide atmosphere, and large readable Chinese typography. Do not edit the reference images and do not copy their old page content. + +Create a 16:9 full-page visual slide image for Page P20 titled "已经成立的部分". This page builds justified confidence after a sober judgment page. It must show that the answer to "为什么是我们" already has a real foundation, without turning into a personal resume. + +Scene/backdrop: deep navy-black AI route-map background, subtle coordinate grid, radar rings, compass marks, dark ocean-chart and deepwater business-layer texture. Cyan route signals and restrained gold highlights. + +Primary visual model: a capability foundation / ship-body cutaway. +- Bottom layer: seven glowing keel-rib modules forming the structural base of a professional vessel / capability platform. +- Each keel module has one short Chinese label: "AI 学习", "培训经验", "管理咨询", "信息化落地", "智能体实践", "方法论抽象", "团队雏形". +- The seven modules feed upward through cyan signal lines into a central upper structure labeled "专家智能体商业能力". +- The upper structure should look like a sober AI navigation vessel / operational capability platform, not a literal cute ship. +- The route map should imply different past accumulations converging into one new AI route. + +Text (verbatim Chinese, keep readable): +- Top title: "已经成立的部分" +- Core judgment: "我们已经具备回答“为什么是我们”的基础" +- Seven labels: "AI 学习" / "培训经验" / "管理咨询" / "信息化落地" / "智能体实践" / "方法论抽象" / "团队雏形" +- Central label: "专家智能体商业能力" +- Bottom line: "不是从零开始，而是汇到一条新航线" + +Typography: bold modern Chinese sans-serif, high contrast. Use white/pale blue for main text, cyan for signal lines, restrained gold for the foundation confidence markers. Title and core judgment must be legible. + +Composition/framing: title and judgment in top safe area; large central capability cutaway; seven base modules along lower third, evenly spaced and readable; bottom line in a clean footer band. + +Lighting/mood: sober confidence, accumulated capability, executive business strategy, precise technical-operation map. + +Color palette: deep navy-black, dark slate blue, cyan AI signal, restrained warm gold, pale-blue/white typography. + +Constraints: no personal biography layout, no real portraits, no stock meeting photos, no humanoid robots, no platform logo wall, no generic SaaS dashboard, no bright cyberpunk overload, no government red-gold style, no cartoon ship, no dense long text, no watermark, no logo. + +## Output Intent + +Generate `s20-v1-image.png` and copy the final image into `projects/2026-07-01-为什么是我们/slides/s20/`. diff --git a/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-brief.md new file mode 100644 index 0000000..70eb117 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-brief.md @@ -0,0 +1,69 @@ +# S-21 Slide Brief V1 + +## Page + +- Page: P21 / S-21. +- Title: 还没有完全成立的部分. +- Function: build clear view of gaps and next work. +- Core conclusion: 差异要变成销售武器，还需要产品化、证据化、标准化。 + +## Source Basis + +Primary sources: + +- `intake/阶段5：P1-P22 单页设计骨架.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` + +Control and style sources: + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` + +Backup fact-check source: + +- not used. + +## Visible Text + +Title: + +> 还没有完全成立的部分 + +Core judgment: + +> 差异要变成销售武器，还需要产品化、证据化、标准化 + +Maturity labels: + +> 案例：待整理 +> 模板：待产品化 +> 成果指标：待量化 +> 团队复制：待培养 +> 样板演示：待筛选 +> 产品包：待成型 +> 反驳问答：待训练 + +Bottom line: + +> 没有资产沉淀，差异就只能停留在我嘴里 + +## Visual Requirements + +- 16:9 full-page visual image. +- Half-built sales arsenal wall plus maturity dashboard. +- Deep navy-black operation-map base. +- Progress bars / status chips should be readable but compact. +- Mood: clear-eyed work-in-progress, not defeat. +- No review file for production-light. + +## Generation Notes + +- Current `gpt-image-2` mode: `B-or-C`. +- Effective route: Mode B, host-native image generation. +- Garden scripts: not used. +- Reference images: style continuity only, not edit targets. diff --git a/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-design.md new file mode 100644 index 0000000..3aac486 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-design.md @@ -0,0 +1,62 @@ +# S-21 Slide Design V1 + +## Status + +- Status: production-light design. +- Source page: P21. +- Page title: 还没有完全成立的部分. +- Line: production-light. +- Review: none. +- Write policy: append-only; overwrite allowed: no. + +## Design Purpose + +S-21 负责把“还缺什么”讲清楚，同时不能泄气。它要传达： + +> 差异要变成销售武器，还需要产品化、证据化、标准化。 + +本页的情绪是“武器库建设中”，不是“我们还不行”。 + +## Visual Concept + +画面是“销售武器库半成品 + 成熟度仪表盘”。深色作战室里，一面武器库墙正在建设，部分装备已经入库亮起，部分还是蓝图、半透明轮廓或制造中状态。右侧或中部是成熟度仪表盘，列出七项待补齐能力。 + +## Text / Typography Plan + +Title: + +> 还没有完全成立的部分 + +Core judgment: + +> 差异要变成销售武器，还需要产品化、证据化、标准化 + +Maturity labels: + +> 案例：待整理 +> 模板：待产品化 +> 成果指标：待量化 +> 团队复制：待培养 +> 样板演示：待筛选 +> 产品包：待成型 +> 反驳问答：待训练 + +Bottom line: + +> 没有资产沉淀，差异就只能停留在我嘴里 + +## Layout + +- Top: title and core judgment. +- Left / center: half-built sales arsenal wall. +- Right: maturity dashboard with seven progress bars. +- Bottom: sober gold-white closing line. +- Use cyan for work-in-progress signal, gold for assets already lit. + +## Constraints / Avoid + +- Do not make the page feel defeated. +- Do not imply the business difference is false. +- Do not add unapproved tasks beyond the accepted skeleton. +- Do not use excessive tiny text. +- Do not create a review file. diff --git a/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-prompt.md new file mode 100644 index 0000000..a06749c --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s21/s21-v1-prompt.md @@ -0,0 +1,92 @@ +# S-21 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s21-v1-brief.md`. +- Line: production-light. +- Review: none. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P21 / S-21. +- Page family: E / Sober Judgment. +- Active style module: `visual-system/style/style-prompt-master.md`, Module E. +- Core motif: 成熟度仪表盘. +- Main title: `还没有完全成立的部分` +- Core judgment: `差异要变成销售武器，还需要产品化、证据化、标准化。` +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Effective route: Mode B because host `image_gen` is available. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\infographics\bento-grid-infographic.md` + - `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` +- Project source files read: + - `project.md` + - `execution-plan.md` + - `slides/slides.md` + - `visual-system/visual-system.md` + - `visual-system/style/style-prompt-master.md` + - `visual-system/motifs/motif-registry.md` + - `intake/阶段3：PPT 总纲 v1.md` + - `intake/阶段4：通用表达与视觉系统.md` + - `intake/阶段5：P1-P22 单页设计骨架.md` +- Style reference images loaded into context: + - Image 1: current deck accepted cover, role = style continuity reference only. + - Image 2: current deck accepted P10, role = style continuity reference only. + - Image 3: previous deck accepted cover, role = style continuity reference only. + - Image 4: previous deck accepted P10, role = style continuity reference only. +- Backup raw material source: not used. + +## Final Host-Native Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page content slide image for an internal sales-alignment PowerPoint + +Use the visible reference images only as style continuity references: deep navy-black AI maritime operation map, cyan glowing route lines, restrained gold highlights, radar / compass geometry, dark executive slide atmosphere, and large readable Chinese typography. Do not edit the reference images and do not copy their old page content. + +Create a 16:9 full-page visual slide image for Page P21 titled "还没有完全成立的部分". This is a sober but action-oriented work-in-progress page. It should not feel defeated. It should feel like a sales arsenal is being built into productized, evidence-backed, repeatable tools. + +Scene/backdrop: deep navy-black executive AI operation-room background, route-map grid, radar rings, compass marks, subtle deepwater layers. Use cyan signal lines and restrained gold highlights. + +Primary visual model: half-built sales arsenal wall plus maturity dashboard. +- Left / center: a dark sales arsenal wall under construction. Some equipment/tool slots are lit and solid; others are translucent blueprints, outlines, or under-construction components. +- Right side: a clean maturity dashboard with seven compact progress bars or status rows. +- The dashboard should be readable and visually structured, but not a generic SaaS dashboard. +- The whole page should communicate: the difference exists, but it must become assets. + +Text (verbatim Chinese, keep readable): +- Top title: "还没有完全成立的部分" +- Core judgment: "差异要变成销售武器，还需要产品化、证据化、标准化" +- Maturity rows: + "案例：待整理" + "模板：待产品化" + "成果指标：待量化" + "团队复制：待培养" + "样板演示：待筛选" + "产品包：待成型" + "反驳问答：待训练" +- Bottom line: "没有资产沉淀，差异就只能停留在我嘴里" + +Typography: bold modern Chinese sans-serif, high contrast. Use white/pale blue for title and core judgment, cyan for in-progress lines, restrained gold for completed or important asset markers. Keep all Chinese labels short and legible. + +Composition/framing: title and judgment in top safe area; arsenal wall as the large visual anchor; dashboard on the right or lower right with clear row spacing; bottom line in a clean footer band. Avoid cramming too much small text. + +Lighting/mood: clear-eyed internal calibration, sales asset construction, sober confidence, workbench-to-arsenal progression. + +Color palette: deep navy-black, dark slate blue, cyan AI signal, restrained warm gold, pale-blue/white typography. + +Constraints: no defeated mood, no implication that the business difference is fake, no customer proposal look, no government red-gold style, no humanoid robots, no real people, no platform logo wall, no dense paragraphs, no overly generic SaaS dashboard, no cartoon weapons, no literal violence, no watermark, no logo. + +## Output Intent + +Generate `s21-v1-image.png` and copy the final image into `projects/2026-07-01-为什么是我们/slides/s21/`. diff --git a/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-brief.md b/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-brief.md new file mode 100644 index 0000000..3d429e8 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-brief.md @@ -0,0 +1,71 @@ +# S-22 Slide Brief V1 + +## Page + +- Page: P22 / S-22. +- Title: 销售武器库：从立场文件到作战工具. +- Function: action close and roadmap. +- Core conclusion: 销售武器库越成熟，销售越有底气。 + +## Source Basis + +Primary sources: + +- `intake/阶段5：P1-P22 单页设计骨架.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` + +Control and style sources: + +- `project.md` +- `execution-plan.md` +- `slides/slides.md` +- `visual-system/visual-system.md` +- `visual-system/style/style-prompt-master.md` +- `visual-system/motifs/motif-registry.md` + +Backup fact-check source: + +- not used. + +## Visible Text + +Title: + +> 销售武器库：从立场文件到作战工具 + +Subtitle: + +> 哪些已经有，哪些正在补，哪些决定我们能不能复制 + +Core judgment: + +> 销售武器库越成熟，销售越有底气 + +Layer labels: + +> 立场层 / 证明层 / 作战层 + +Tool labels: + +> 一页纸定位 / 平台差异 / 开发公司差异 / 样板库 / 案例页 / 评测页 / 问答库 / 话术卡 / 不适合客户 / 自检表 + +Bottom line: + +> 今天先把立场讲清楚，后面把立场做成武器 + +## Visual Requirements + +- 16:9 full-page visual image. +- Sales arsenal maturity map. +- Left-to-right transformation: stance file -> tools -> repeatable system. +- Three layers: position, proof, operation. +- Deep navy-black operation-map base with cyan/gold signal system. +- No review file for production-light. + +## Generation Notes + +- Current `gpt-image-2` mode: `B-or-C`. +- Effective route: Mode B, host-native image generation. +- Garden scripts: not used. +- Reference images: style continuity only, not edit targets. diff --git a/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-design.md b/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-design.md new file mode 100644 index 0000000..888f2f7 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-design.md @@ -0,0 +1,73 @@ +# S-22 Slide Design V1 + +## Status + +- Status: production-light design. +- Source page: P22. +- Page title: 销售武器库：从立场文件到作战工具. +- Line: production-light. +- Review: none. +- Write policy: append-only; overwrite allowed: no. + +## Design Purpose + +S-22 是行动收束页。它要把整套“为什么是我们”的立场，转成后续可建设、可复用、可训练的销售工具体系。 + +核心判断： + +> 销售武器库越成熟，销售越有底气。 + +## Visual Concept + +画面是“销售武器库成熟度地图”。左侧是一份已经亮起的立场文件，中间是正在建设的销售工具区，右侧是未来可复制的销售作战系统。 + +三层结构： + +- 立场层：一句话定位、三句话版本、标准回答 +- 证明层：案例、样板、评测、成果数据 +- 作战层：问答库、话术卡、自检表、不适合客户清单 + +每个工具像一件装备或卡片入库，已具备的亮起，待补齐的半透明。 + +## Text / Typography Plan + +Title: + +> 销售武器库：从立场文件到作战工具 + +Subtitle: + +> 哪些已经有，哪些正在补，哪些决定我们能不能复制 + +Core judgment: + +> 销售武器库越成熟，销售越有底气 + +Layer labels: + +> 立场层 / 证明层 / 作战层 + +Tool labels: + +> 一页纸定位 / 平台差异 / 开发公司差异 / 样板库 / 案例页 / 评测页 / 问答库 / 话术卡 / 不适合客户 / 自检表 + +Bottom line: + +> 今天先把立场讲清楚，后面把立场做成武器 + +## Layout + +- Top: title, subtitle, core judgment. +- Left: current stance file, glowing. +- Center: sales tools under construction. +- Right: repeatable sales operating system. +- Three horizontal layers or stacked bands: 立场层 / 证明层 / 作战层. +- Background: deep navy-black operation map and arsenal wall. + +## Constraints / Avoid + +- Do not make it look militaristic or violent. +- Do not use literal weapons as the main subject; use business tool cards / equipment metaphor. +- Do not include long final-consensus paragraph in the image. +- Do not turn the page into a task checklist only. +- Keep action energy and visual closure. diff --git a/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-prompt.md b/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-prompt.md new file mode 100644 index 0000000..d83748e --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/s22/s22-v1-prompt.md @@ -0,0 +1,91 @@ +# S-22 Slide Prompt V1 + +## Status + +- Status: ready for host-native generation. +- Based on brief: `s22-v1-brief.md`. +- Line: production-light. +- Review: none. +- Garden/API expected: no. + +## Reference Inputs + +- Page: P22 / S-22. +- Page family: F / Sales Arsenal. +- Active style module: `visual-system/style/style-prompt-master.md`, Module F. +- Core motif: 销售武器库. +- Main title: `销售武器库：从立场文件到作战工具` +- Core judgment: `销售武器库越成熟，销售越有底气。` +- Generation path note: host-native / Advisor; Garden expected: no. + +## Operation Notes + +- `gpt-image-2` mode check result: `B-or-C`, recommendation `host-or-advisor`. +- Effective route: Mode B because host `image_gen` is available. +- Skill/template files used: + - `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` + - `C:\Users\wangq\.agents\skills\gpt-image-2\references\infographics\bento-grid-infographic.md` + - `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` +- Project source files read: + - `project.md` + - `execution-plan.md` + - `slides/slides.md` + - `visual-system/visual-system.md` + - `visual-system/style/style-prompt-master.md` + - `visual-system/motifs/motif-registry.md` + - `intake/阶段3：PPT 总纲 v1.md` + - `intake/阶段4：通用表达与视觉系统.md` + - `intake/阶段5：P1-P22 单页设计骨架.md` +- Style reference images loaded into context: + - Image 1: current deck accepted cover, role = style continuity reference only. + - Image 2: current deck accepted P10, role = style continuity reference only. + - Image 3: previous deck accepted cover, role = style continuity reference only. + - Image 4: previous deck accepted P10, role = style continuity reference only. +- Backup raw material source: not used. + +## Final Host-Native Prompt + +Use case: productivity-visual +Asset type: 16:9 full-page closing slide image for an internal sales-alignment PowerPoint + +Use the visible reference images only as style continuity references: deep navy-black AI maritime operation map, cyan glowing route lines, restrained gold highlights, radar / compass geometry, dark executive slide atmosphere, and large readable Chinese typography. Do not edit the reference images and do not copy their old page content. + +Create a 16:9 full-page visual slide image for Page P22 titled "销售武器库：从立场文件到作战工具". This is the action close page. It should convert the deck's stance into a reusable sales-tool roadmap. + +Scene/backdrop: deep navy-black executive AI operation map, subtle coordinate grid, radar rings, compass marks, route lines, dark arsenal-wall / command-room feeling. Use cyan signal lines and restrained gold highlights. + +Primary visual model: sales arsenal maturity map, not literal violence. +- Left third: a glowing "立场文件" / positioning document as the starting asset. +- Middle third: a structured wall of business tool cards under construction. +- Right third: an integrated "销售作战系统" / repeatable sales system, shown as a navigation console, map layer, and reusable toolkit. +- Organize the tools into three clear horizontal layers or stacked bands: + 1. "立场层" with "一页纸定位", "三句话版本", "标准回答" + 2. "证明层" with "案例页", "样板库", "评测页", "成果数据" + 3. "作战层" with "问答库", "话术卡", "自检表", "不适合客户" +- Some tools are lit as already started, some are semi-transparent as next-build assets. + +Text (verbatim Chinese, keep readable): +- Top title: "销售武器库：从立场文件到作战工具" +- Subtitle: "哪些已经有，哪些正在补，哪些决定我们能不能复制" +- Core judgment: "销售武器库越成熟，销售越有底气" +- Layer labels: "立场层" / "证明层" / "作战层" +- Tool labels: "一页纸定位" / "平台差异" / "开发公司差异" / "样板库" / "案例页" / "评测页" / "问答库" / "话术卡" / "不适合客户" / "自检表" +- Bottom line: "今天先把立场讲清楚，后面把立场做成武器" + +Typography: bold modern Chinese sans-serif, high contrast. Use white/pale blue for title and subtitle, cyan for roadmap connections, restrained gold for the strongest sales-confidence markers. Keep text short and legible. + +Composition/framing: title in top safe area; left-to-right transformation should be obvious; three layer bands should be readable; bottom line in footer. This should feel like a polished internal strategy close, not a checklist page. + +Lighting/mood: action-oriented, sober, confident, operational. The deck ends with a roadmap to reusable sales assets. + +Color palette: deep navy-black, dark slate blue, cyan AI signal, restrained warm gold, pale-blue/white typography. + +Constraints: no literal guns or violent weapons, no military propaganda feeling, no customer proposal look, no government red-gold style, no humanoid robots, no concrete portraits, no platform logo wall, no dense final-consensus paragraph, no generic SaaS dashboard, no cartoon ship, no watermark, no logo. + +## Output Intent + +Generate `s22-v1-image.png` and copy the final image into `projects/2026-07-01-为什么是我们/slides/s22/`. diff --git a/projects/2026-07-01-为什么是我们/slides/slides.md b/projects/2026-07-01-为什么是我们/slides/slides.md new file mode 100644 index 0000000..10f22aa --- /dev/null +++ b/projects/2026-07-01-为什么是我们/slides/slides.md @@ -0,0 +1,55 @@ +# Slides Status + +## Status Legend + +| Status | Meaning | +| --- | --- | +| `pending` | No slide artifacts yet. | +| `validation-generated` | Validation artifacts and image generated; waiting for user check. | +| `production-pass` | Accepted as production-pass output. | +| `in-production` | Assigned to a production child session. | +| `repair-needed` | User requested append-only retry. | + +## Current Validation Scope + +| Slide | Page Title | Role | Current Version | Status | Notes | +| --- | --- | --- | --- | --- | --- | +| S-01 | 为什么是我们 | Cover validation | v1 | production-pass | User confirmed validation pass. Image: `slides/s01/s01-v1-image.png`. | +| S-10 | 我们是谁：专家智能体的系统架构师与模具师 | Content anchor validation | v1 | production-pass | User confirmed validation pass. Image: `slides/s10/s10-v1-image.png`. | + +## Full Page List + +| Slide | Page Title | Module | Status | Active Version | +| --- | --- | --- | --- | --- | +| S-01 | 为什么是我们 | 问题提出 | production-pass | v1 | +| S-02 | 销售问了一个真问题 | 问题提出 | production-pass | v1 | +| S-03 | 三个必须回答的问题 | 问题提出 | production-pass | v1 | +| S-04 | 先承认：平台很强，也很重要 | 市场对照 | production-pass | v1 | +| S-05 | 平台解决“怎么搭”，不解决“该搭什么” | 市场对照 | production-pass | v1 | +| S-06 | 平台像工厂，我们像模具师 | 市场对照 | production-pass | v1 | +| S-07 | 简单场景，客户自己用平台就可以 | 市场对照 | production-pass | v1 | +| S-08 | 我们做的不是通用 AI 助手 | 我们定位 | production-pass | v1 | +| S-09 | 什么是专家智能体 | 我们定位 | production-pass | v1 | +| S-10 | 我们是谁：专家智能体的系统架构师与模具师 | 我们定位 | production-pass | v1 | +| S-11 | 不是写提示词，而是专家能力工程化 | 我们定位 | production-pass | v1 | +| S-12 | 普通 AI 开发公司的路径 vs 我们的路径 | 我们定位 | production-pass | v1 | +| S-13 | 客户选择我们，不是因为我们最大或最便宜 | 客户为什么选择我们 | production-pass | v1 | +| S-14 | 我们能帮客户判断“该不该做 AI” | 客户为什么选择我们 | production-pass | v1 | +| S-15 | 我们同时懂管理、信息化和 AI | 客户为什么选择我们 | production-pass | v1 | +| S-16 | 我们能抽取专家经验，而不是只上传资料 | 客户为什么选择我们 | production-pass | v1 | +| S-17 | 我们先验证智能流，再投入系统建设 | 客户为什么选择我们 | production-pass | v1 | +| S-18 | 我们不只追求能跑，还追求好改 | 客户为什么选择我们 | production-pass | v1 | +| S-19 | 我们的商业差异成立，但不是天然成立 | 清醒判断 | production-pass | v1 | +| S-20 | 已经成立的部分 | 清醒判断 | production-pass | v1 | +| S-21 | 还没有完全成立的部分 | 清醒判断 | production-pass | v1 | +| S-22 | 销售武器库：从立场文件到作战工具 | 销售武器库建设路线图 | production-pass | v1 | + +## Production Rule After Validation + +If S-01 and S-10 pass, remaining production starts from the next pending pages. Repairs use append-only `vN` versions and never overwrite accepted artifacts. + +## Assembled Deck + +| Artifact | Path | Status | +| --- | --- | --- | +| PPTX | `slides/why-us-full-page-images.pptx` | assembled; 22 slides; one full-page image per slide | diff --git a/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/dispatch-ledger.md b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/dispatch-ledger.md new file mode 100644 index 0000000..a2b12df --- /dev/null +++ b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/dispatch-ledger.md @@ -0,0 +1,32 @@ +# Production Dispatch Ledger + +## Parent + +- Parent thread id: `019f1b6b-387f-7be2-af0a-03761085cdae` +- Project: `projects/2026-07-01-为什么是我们` +- Line: production-light +- Review: none +- Overwrite allowed: no +- User authorization: P01 and P10 validation images passed; produce remaining pages in packages of 8. + +## Packages + +| Package | Scope | Child Thread | Status | Handoff | +| --- | --- | --- | --- | --- | +| package-01 | S-02 through S-09 | `019f1b86-b337-7553-9084-610f0421e5e3` | complete | `tasks/2026-07-01-production-dispatch/package-01-handoff.md` | +| package-02 | S-11 through S-18 | `019f1b87-7dd8-7e91-b50e-7f2e25dd5464` | complete | `tasks/2026-07-01-production-dispatch/package-02-handoff.md` | +| package-03 | S-19 through S-22 | `019f1b88-4d73-79e1-bf4d-b59d7e79dfa0` | complete | `tasks/2026-07-01-production-dispatch/package-03-handoff.md` | + +## Child Session Requirements + +Each child session must: + +- read `AGENTS.md` first; +- use explicit UTF-8 for local Markdown / text reads; +- use `gpt-image-2` Skill workflow and run mode check; +- treat raw material as fact-check only; +- preserve P1-P22 mainline; +- write append-only `sNN-v1-design.md`, `sNN-v1-brief.md`, `sNN-v1-prompt.md`, and `sNN-v1-image.png` for assigned pages; +- copy host-generated images into the project slide folders; +- not create `sNN-v1-review.md`; +- write compact handoff and callback to the parent as final action. diff --git a/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-01-handoff.md b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-01-handoff.md new file mode 100644 index 0000000..f19addd --- /dev/null +++ b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-01-handoff.md @@ -0,0 +1,103 @@ +# package-01 Handoff + +## Status + +- Status: complete +- Project: `projects/2026-07-01-为什么是我们` +- Scope: S-02 through S-09 / P02-P09 +- Line: production-light +- Review: none +- Overwrite allowed: no +- Topology: direct production-light child session; no Agent/SubAgent workers used. + +## Resolved Versions + +| Slide | Version | Status | +| --- | --- | --- | +| S-02 | v1 | production-pass | +| S-03 | v1 | production-pass | +| S-04 | v1 | production-pass | +| S-05 | v1 | production-pass | +| S-06 | v1 | production-pass | +| S-07 | v1 | production-pass | +| S-08 | v1 | production-pass | +| S-09 | v1 | production-pass | + +## Created Files + +For each slide S-02 through S-09, these append-only v1 files were created: + +- `slides/sNN/sNN-v1-design.md` +- `slides/sNN/sNN-v1-brief.md` +- `slides/sNN/sNN-v1-prompt.md` +- `slides/sNN/sNN-v1-image.png` + +No `sNN-v1-review.md` files were created. + +## Image Paths + +| Slide | Project image path | +| --- | --- | +| S-02 | `projects/2026-07-01-为什么是我们/slides/s02/s02-v1-image.png` | +| S-03 | `projects/2026-07-01-为什么是我们/slides/s03/s03-v1-image.png` | +| S-04 | `projects/2026-07-01-为什么是我们/slides/s04/s04-v1-image.png` | +| S-05 | `projects/2026-07-01-为什么是我们/slides/s05/s05-v1-image.png` | +| S-06 | `projects/2026-07-01-为什么是我们/slides/s06/s06-v1-image.png` | +| S-07 | `projects/2026-07-01-为什么是我们/slides/s07/s07-v1-image.png` | +| S-08 | `projects/2026-07-01-为什么是我们/slides/s08/s08-v1-image.png` | +| S-09 | `projects/2026-07-01-为什么是我们/slides/s09/s09-v1-image.png` | + +## Host Generated Sources + +Original generated images were left in place under: + +`C:\Users\wangq\.codex\generated_images\019f1b86-b337-7553-9084-610f0421e5e3\` + +Copied source files: + +- S-02: `ig_0d61e9cfe41baa09016a447ef7fa3081988b2c5409b92c4ec6.png` +- S-03: `ig_0e5ed2d21c3fe7a7016a447f630a0c8199a2410f0e80b9d2e1.png` +- S-04: `ig_070c5416cba6a057016a447ff22518819184b97e810185eb53.png` +- S-05: `ig_0b40419b4faaa21a016a44806224048191b85de051e2fe73d3.png` +- S-06: `ig_040c372674772d35016a44812f72548191a7b0ee4ff674e22e.png` +- S-07: `ig_0434f5ffe3f5e1c6016a4481af6af48191bf3bd53ec0137186.png` +- S-08: `ig_056afc99954634a7016a448228fdfc8191aafb76c8919808fa.png` +- S-09: `ig_07d265c0bd175e79016a4482aea4b48191b86daec9f74db09d.png` + +## Mode Check Result + +Command: + +```powershell +node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json +``` + +Result: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: Mode B host-native because host `image_gen` was available. Garden generation scripts were not used. + +## Status File Update + +`slides/slides.md` was re-read immediately before editing. Only S-02 through S-09 rows were changed to `production-pass | v1`. Other package rows were not touched. + +## Narrow Checks + +Fresh narrow check result: all expected S-02 through S-09 v1 design, brief, prompt, and image files exist; all eight PNGs opened successfully as readable images; no S-02 through S-09 review files exist. + +PNG dimensions reported by the narrow check: 1672x941 for each image. + +## Problems + +None. diff --git a/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-02-handoff.md b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-02-handoff.md new file mode 100644 index 0000000..01e552b --- /dev/null +++ b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-02-handoff.md @@ -0,0 +1,88 @@ +# Package 02 Handoff + +## Status + +- Status: complete +- Scope: S-11 through S-18 / P11-P18 +- Line: production-light +- Topology: direct-child; no Agent/SubAgent +- Running mode: prompt and generate +- Review mode: none +- Write policy: append-only; overwrite allowed: no +- `slides/slides.md`: S-11 through S-18 updated to `production-pass | v1` + +## Resolved Versions + +| Slide | Version | +| --- | --- | +| S-11 | v1 | +| S-12 | v1 | +| S-13 | v1 | +| S-14 | v1 | +| S-15 | v1 | +| S-16 | v1 | +| S-17 | v1 | +| S-18 | v1 | + +## Created Files + +| Slide | Files | +| --- | --- | +| S-11 | `slides/s11/s11-v1-design.md`; `slides/s11/s11-v1-brief.md`; `slides/s11/s11-v1-prompt.md`; `slides/s11/s11-v1-image.png` | +| S-12 | `slides/s12/s12-v1-design.md`; `slides/s12/s12-v1-brief.md`; `slides/s12/s12-v1-prompt.md`; `slides/s12/s12-v1-image.png` | +| S-13 | `slides/s13/s13-v1-design.md`; `slides/s13/s13-v1-brief.md`; `slides/s13/s13-v1-prompt.md`; `slides/s13/s13-v1-image.png` | +| S-14 | `slides/s14/s14-v1-design.md`; `slides/s14/s14-v1-brief.md`; `slides/s14/s14-v1-prompt.md`; `slides/s14/s14-v1-image.png` | +| S-15 | `slides/s15/s15-v1-design.md`; `slides/s15/s15-v1-brief.md`; `slides/s15/s15-v1-prompt.md`; `slides/s15/s15-v1-image.png` | +| S-16 | `slides/s16/s16-v1-design.md`; `slides/s16/s16-v1-brief.md`; `slides/s16/s16-v1-prompt.md`; `slides/s16/s16-v1-image.png` | +| S-17 | `slides/s17/s17-v1-design.md`; `slides/s17/s17-v1-brief.md`; `slides/s17/s17-v1-prompt.md`; `slides/s17/s17-v1-image.png` | +| S-18 | `slides/s18/s18-v1-design.md`; `slides/s18/s18-v1-brief.md`; `slides/s18/s18-v1-prompt.md`; `slides/s18/s18-v1-image.png` | + +## Image Paths + +- `projects/2026-07-01-为什么是我们/slides/s11/s11-v1-image.png` +- `projects/2026-07-01-为什么是我们/slides/s12/s12-v1-image.png` +- `projects/2026-07-01-为什么是我们/slides/s13/s13-v1-image.png` +- `projects/2026-07-01-为什么是我们/slides/s14/s14-v1-image.png` +- `projects/2026-07-01-为什么是我们/slides/s15/s15-v1-image.png` +- `projects/2026-07-01-为什么是我们/slides/s16/s16-v1-image.png` +- `projects/2026-07-01-为什么是我们/slides/s17/s17-v1-image.png` +- `projects/2026-07-01-为什么是我们/slides/s18/s18-v1-image.png` + +## Mode Check Result + +Command: + +```powershell +node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json +``` + +Result: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: effective Mode B / host-native because host `image_gen` is available. Garden scripts were not called. + +## Narrow Checks + +- Expected `design`, `brief`, `prompt`, and `image` files exist for S-11 through S-18. +- All eight copied PNG files opened successfully. +- No `sNN-v1-review.md` files were created. +- No visual/instruction review was performed, per `review: none`. + +## Problems + +- None. + +## Parent Summary + +Package-02 is complete. S-11 through S-18 have append-only v1 design, brief, prompt, and image artifacts; `slides/slides.md` now records them as `production-pass | v1`; no user decision is needed from this child session. diff --git a/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-03-handoff.md b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-03-handoff.md new file mode 100644 index 0000000..747550f --- /dev/null +++ b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-production-dispatch/package-03-handoff.md @@ -0,0 +1,95 @@ +# Package 03 Handoff + +## Status + +- Status: complete. +- Scope: S-19 through S-22 / P19-P22. +- Line: production-light. +- Review: none. +- Overwrite allowed: no. +- Topology: direct production-light child session; no Agent/SubAgent workers used. + +## Mode Check + +Command: + +```powershell +node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json +``` + +Result: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: + +- Effective route: Mode B, host-native `image_gen`. +- Garden generation scripts were not used. +- Prompt files were saved before image generation. + +## Created Files + +S-19: + +- `projects/2026-07-01-为什么是我们/slides/s19/s19-v1-design.md` +- `projects/2026-07-01-为什么是我们/slides/s19/s19-v1-brief.md` +- `projects/2026-07-01-为什么是我们/slides/s19/s19-v1-prompt.md` +- `projects/2026-07-01-为什么是我们/slides/s19/s19-v1-image.png` + +S-20: + +- `projects/2026-07-01-为什么是我们/slides/s20/s20-v1-design.md` +- `projects/2026-07-01-为什么是我们/slides/s20/s20-v1-brief.md` +- `projects/2026-07-01-为什么是我们/slides/s20/s20-v1-prompt.md` +- `projects/2026-07-01-为什么是我们/slides/s20/s20-v1-image.png` + +S-21: + +- `projects/2026-07-01-为什么是我们/slides/s21/s21-v1-design.md` +- `projects/2026-07-01-为什么是我们/slides/s21/s21-v1-brief.md` +- `projects/2026-07-01-为什么是我们/slides/s21/s21-v1-prompt.md` +- `projects/2026-07-01-为什么是我们/slides/s21/s21-v1-image.png` + +S-22: + +- `projects/2026-07-01-为什么是我们/slides/s22/s22-v1-design.md` +- `projects/2026-07-01-为什么是我们/slides/s22/s22-v1-brief.md` +- `projects/2026-07-01-为什么是我们/slides/s22/s22-v1-prompt.md` +- `projects/2026-07-01-为什么是我们/slides/s22/s22-v1-image.png` + +Updated: + +- `projects/2026-07-01-为什么是我们/slides/slides.md` rows S-19 through S-22 to `production-pass` / `v1`. + +## Image Paths + +| Slide | Project image | Host default source | +| --- | --- | --- | +| S-19 | `projects/2026-07-01-为什么是我们/slides/s19/s19-v1-image.png` | `C:\Users\wangq\.codex\generated_images\019f1b88-4d73-79e1-bf4d-b59d7e79dfa0\ig_0e3cfa33b4aec791016a447ec02c6881919afb843caf2763ef.png` | +| S-20 | `projects/2026-07-01-为什么是我们/slides/s20/s20-v1-image.png` | `C:\Users\wangq\.codex\generated_images\019f1b88-4d73-79e1-bf4d-b59d7e79dfa0\ig_0e3cfa33b4aec791016a447f45eaf881919209d49e8991d387.png` | +| S-21 | `projects/2026-07-01-为什么是我们/slides/s21/s21-v1-image.png` | `C:\Users\wangq\.codex\generated_images\019f1b88-4d73-79e1-bf4d-b59d7e79dfa0\ig_0e3cfa33b4aec791016a447f9e77748191a614bc79f92b6076.png` | +| S-22 | `projects/2026-07-01-为什么是我们/slides/s22/s22-v1-image.png` | `C:\Users\wangq\.codex\generated_images\019f1b88-4d73-79e1-bf4d-b59d7e79dfa0\ig_0e3cfa33b4aec791016a447ff437e0819180a69e88a0a18609.png` | + +## Narrow Checks + +- Required design / brief / prompt / image files exist. +- Project-copied PNGs opened successfully: + - S-19: 1672x941 + - S-20: 1672x941 + - S-21: 1672x941 + - S-22: 1672x941 + +## Problems + +- None blocking. +- Note: other package sessions were generating images concurrently under the shared `generated_images` root, so package-03 images were selected by page title before copying. diff --git a/projects/2026-07-01-为什么是我们/tasks/2026-07-01-validation-p01-p10/task-plan.md b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-validation-p01-p10/task-plan.md new file mode 100644 index 0000000..1f6940f --- /dev/null +++ b/projects/2026-07-01-为什么是我们/tasks/2026-07-01-validation-p01-p10/task-plan.md @@ -0,0 +1,37 @@ +# Validation Task Plan: P01 and P10 + +## Scope + +Generate validation artifacts and images for: + +- P01 / S-01: cover. +- P10 / S-10: positioning anchor page. + +## Constraints + +- Use the accepted P1-P22 skeleton as page authority. +- Use the previous deck only as style continuity reference. +- Use the original raw material only for fact checking; not needed for this validation run. +- Do not rewrite the page mainline. +- Do not create routine review files. +- Overwrite allowed: no. + +## Artifacts + +For each validation page: + +- `sNN-v1-design.md` +- `sNN-v1-brief.md` +- `sNN-v1-prompt.md` +- `sNN-v1-image.png` after host generation and workspace copy + +## Completion Surface + +The user checks Design and images together. If both pass, enter production-light. + +## Generated Outputs + +| Slide | Image | +| --- | --- | +| S-01 | `projects/2026-07-01-为什么是我们/slides/s01/s01-v1-image.png` | +| S-10 | `projects/2026-07-01-为什么是我们/slides/s10/s10-v1-image.png` | diff --git a/projects/2026-07-01-为什么是我们/visual-system/motifs/motif-registry.md b/projects/2026-07-01-为什么是我们/visual-system/motifs/motif-registry.md new file mode 100644 index 0000000..4d220e2 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/visual-system/motifs/motif-registry.md @@ -0,0 +1,63 @@ +# Motif Registry + +## Global Motif Rule + +All motifs serve the same prequel metaphor: + +> 从“上船”进入“看清水深”：平台给工具，开发公司做功能，我们把专家能力工程化并送入真实业务流程。 + +The deck should feel like a dark AI maritime operation map with business-depth diagrams, not a literal ship story. + +## Active Motifs + +| Motif | Visual Treatment | Meaning | Default Pages | +| --- | --- | --- | --- | +| AI 深水区 | Dark ocean cross-section, layered business networks under the surface | Customer problems become difficult below the visible tool layer | P01, P05, P07, P13 | +| 雷达问题锁定 | Radar screen with three targets / gates | Sales must answer platform, AI developers, and customer-choice questions | P02-P03 | +| 平台工具箱 | Open modular toolbox / capability blocks | Platforms are strong tools and suppliers, not enemies | P04-P05 | +| 数字工厂 | Large technical factory / production line | Platform production capacity | P06 | +| 精密模具 | Mold cutaway, calibration grid, expert model core | Our role in shaping expert capability | P06, P10-P12 | +| 专家智能体岗位卡 | Digital employee profile / responsibility card | Expert agent as role-bound digital worker | P08-P09 | +| 专家能力工程化管线 | Extraction -> encapsulation -> validation -> calibration -> workflow entry | The deck's core differentiation | P10-P12 | +| 决策罗盘 | Compass with business, informationization, AI, organization axes | Direction judgment before selling a system | P14-P15 | +| 经验冰山 | Above-water documents, underwater judgment and tacit knowledge | Expert experience is deeper than uploaded documents | P16 | +| 智能流试航 | Probe boat / route test before heavy build | Validate value before system construction | P17 | +| 校准闭环 | Output -> expert review -> correction -> rules / process update | Not just runnable, but modifiable | P18 | +| 证据链灯塔 | Five lighthouses / pillars | Difference must be proved by cases, tools, process, evaluation, replication | P19 | +| 成熟度仪表盘 | Arsenal progress board / maturity bars | Clear view of what exists and what is missing | P20-P21 | +| 销售武器库 | Arsenal wall with positioning, cases, QA, templates, evaluation cards | Turn stance into reusable sales tools | P22 | + +## Page-Family Mapping + +| Family | Pages | Primary Motifs | Secondary Motifs | +| --- | --- | --- | --- | +| Opening / Problem | P01-P03 | AI 深水区, 雷达问题锁定 | route line, lighthouse | +| Market Contrast | P04-P07 | 平台工具箱, 数字工厂, 精密模具 | shallow/deep water | +| Our Positioning | P08-P12 | 专家智能体岗位卡, 专家能力工程化管线, 精密模具 | workflow line | +| Customer Choice | P13-P18 | 决策罗盘, 经验冰山, 智能流试航, 校准闭环 | route checkpoints | +| Sober Judgment | P19-P21 | 证据链灯塔, 成熟度仪表盘 | construction signals | +| Sales Arsenal | P22 | 销售武器库 | map layers | + +## Motif Constraints + +Use: + +- abstract route maps, radar rings, compass geometry, deepwater layers, precision mold cutaways; +- restrained executive cinematic lighting; +- cyan for active signals and AI route lines; +- gold for positioning, evidence, and key confidence points. + +Avoid: + +- cute ship cartoons; +- literal workshop workers or portraits; +- humanoid robots; +- random SaaS dashboard panels; +- platform logo walls as the main subject; +- decorative ocean scenes with no business logic. + +## Text Label Rule + +- 2-8 Chinese characters preferred. +- One title + one core judgment + 3-5 labels for most pages. +- Compress source lists before prompt construction. diff --git a/projects/2026-07-01-为什么是我们/visual-system/style/style-prompt-master.md b/projects/2026-07-01-为什么是我们/visual-system/style/style-prompt-master.md new file mode 100644 index 0000000..09dc982 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/visual-system/style/style-prompt-master.md @@ -0,0 +1,184 @@ +# Style Prompt Master + +## Status + +- Document status: validation-stage style base. +- Project: `2026-07-01-为什么是我们`. +- Purpose: reusable style prompt master for P01/P10 validation and later production. +- Generation status: P01/P10 authorized by user; remaining production waits for validation pass. + +## Skill Mode Record + +Mode check command: + +```powershell +node C:\Users\wangq\.agents\skills\gpt-image-2\scripts\check-mode.js --json +``` + +Result: + +```json +{ + "mode": "B-or-C", + "recommendation": "host-or-advisor", + "garden_mode_enabled": false, + "has_api_key": false, + "base_url": "https://api.openai.com/v1", + "model": "gpt-image-2", + "env_flag_value": "(unset)" +} +``` + +Interpretation: + +- Use `gpt-image-2` as prompt-engineering workflow. +- Effective path is Mode B because host `image_gen` is available. +- Do not call Garden generation scripts. +- Save prompts before generation. + +## Skill Template / Reference Basis + +Skill files read for this validation run: + +- `C:\Users\wangq\.agents\skills\gpt-image-2\SKILL.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\prompt-writing.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\dense-explainer-slides.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\visual-report-page.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\slides-and-visual-docs\educational-diagram-slide.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\poster-and-campaigns\campaign-kv.md` +- `C:\Users\wangq\.agents\skills\gpt-image-2\references\typography-and-text-layout\title-safe-poster.md` +- `C:\Users\wangq\.codex\skills\.system\imagegen\SKILL.md` + +Template adaptation: + +- `dense-explainer-slides.md` informs high-density but readable page logic. +- `visual-report-page.md` informs sober business credibility. +- `educational-diagram-slide.md` informs P10's extraction / validation process model. +- `campaign-kv.md` informs cross-page visual continuity. +- `title-safe-poster.md` informs cover-title safety and large Chinese judgment text. + +## Project Sources Actually Used + +- `project.md` +- `execution-plan.md` +- `visual-system/visual-system.md` +- `visual-system/motifs/motif-registry.md` +- `intake/阶段3：PPT 总纲 v1.md` +- `intake/阶段4：通用表达与视觉系统.md` +- `intake/阶段5：P1-P22 单页设计骨架.md` + +Previous deck references used for style continuity: + +- `../2026-06-29-搭上AI这条船/visual-system/visual-system.md` +- `../2026-06-29-搭上AI这条船/visual-system/style/style-prompt-master.md` +- `../2026-06-29-搭上AI这条船/visual-system/motifs/motif-registry.md` +- `../2026-06-29-搭上AI这条船/slides/s01/s01-v1-image.png` +- `../2026-06-29-搭上AI这条船/slides/s10/s10-v1-image.png` + +Backup source recorded but not used for generation: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\为什么是我们.md +``` + +## Global Style Kernel + +Every page prompt should inherit this kernel unless validation changes the visual system. + +Core visual definition: + +> Deep navy-black executive background, AI maritime route-map atmosphere, deepwater business-layer cutaway, radar glow, compass geometry, precision mold / toolbox / evidence motifs, cyan signal light and restrained gold highlights. + +Chinese working definition: + +> 深蓝黑商务底，AI 航线作战图，深水区业务剖面，雷达与罗盘光效，工具箱 / 工厂 / 模具师 / 证据链母题，青色和金色信号高亮。 + +Default prompt kernel: + +```text +Create a 16:9 full-page visual slide image for an internal sales-alignment PowerPoint. Deep navy-black executive business background, AI maritime route-map atmosphere, deepwater business-layer cutaway, radar scan rings, compass lines, subtle coordinate grid, cyan signal light and restrained gold highlights. The page should feel like a sober AI deepwater operation map: clear market judgment, expert capability engineering, and sales confidence. It is a prequel to an internal AI kickoff deck, harder and more analytical than a mobilization cover. Not a customer proposal, not a training manual, not a generic SaaS dashboard. +``` + +Default text handling: + +```text +Include only short, large, high-contrast Chinese slide text: one main title, one core judgment, and a few short labels. Use bold modern Chinese sans-serif. Main title and core judgment must be readable. Avoid long paragraphs. +``` + +Default negative drift: + +```text +Avoid platform-bashing, developer-bashing, customer proposal style, government-report style, dense training manual, cute cartoon ship, pirate or fantasy ship, cyberpunk neon overload, generic tech dashboard UI, humanoid robots, stock-photo meeting people, concrete portraits, decorative ocean scenes with no business logic, unreadable dense text, logos, watermarks. +``` + +## Page-Family Modules + +### Module A: Opening / Problem + +Use for P01-P03. + +```text +Opening problem page. Use the dark AI route-map base from the previous deck, but move the emotion from "boarding excitement" to "entering AI deepwater". Show route lines, radar targets, deepwater layers, and distant lighthouse signals. The page must feel like a sales confidence prequel: we are here to answer why customers should choose us. +``` + +### Module B: Market Contrast + +Use for P04-P07. + +```text +Market contrast page. Show platforms as strong toolbox / factory / infrastructure capacity, while the deeper layer asks what should be built and how expert judgment becomes reliable capability. Keep the tone mature: platform is partner and tool, not enemy. +``` + +### Module C: Our Positioning + +Use for P08-P12. + +```text +Positioning page. Show expert agents as role-bound digital workers, and our role as system architect and mold maker for expert capability. Use extraction, encapsulation, validation, calibration, and workflow-entry pipeline. Keep the page weighty and memorable, not decorative. +``` + +### Module D: Customer Choice + +Use for P13-P18. + +```text +Customer-choice page. Use route judgment, compass, iceberg, validation route, and calibration loop. The page should prove why customers choose us without claiming we are biggest, cheapest, or万能. +``` + +### Module E: Sober Judgment + +Use for P19-P21. + +```text +Sober internal judgment page. Show evidence chain, maturity dashboard, and partially built lighthouses / arsenal. The mood is clear confidence, not overclaiming. +``` + +### Module F: Sales Arsenal + +Use for P22. + +```text +Action close page. Show sales arsenal maturity map: positioning layer, proof layer, and operating layer. The page should convert the deck's stance into reusable sales tools. +``` + +## Per-Page Prompt Requirements + +Every `sNN-vN-prompt.md` should include: + +- Page and version. +- Page family and active module. +- Core motif from `visual-system/motifs/motif-registry.md`. +- Main title from the accepted skeleton. +- Core judgment from the accepted skeleton. +- Skill mode and template/reference path record. +- Source files actually read. +- Reference image roles if any. +- Fact-check source status. +- Final host-native prompt. + +Rules: + +- Do not generate from the raw material source. +- Do not change P1-P22 order or main conclusions. +- Do not add long source excerpts. +- Do not generate images before user-authorized page scope. diff --git a/projects/2026-07-01-为什么是我们/visual-system/visual-system.md b/projects/2026-07-01-为什么是我们/visual-system/visual-system.md new file mode 100644 index 0000000..d6fb0a9 --- /dev/null +++ b/projects/2026-07-01-为什么是我们/visual-system/visual-system.md @@ -0,0 +1,156 @@ +# Visual System + +## Source State + +This file adapts the accepted visual base from `2026-06-29-搭上AI这条船` to the new prequel deck `2026-07-01-为什么是我们`. + +Status: + +- Validation-stage visual system. +- P01 is the cover sample. +- P10 is the first content anchor sample. + +Primary source files: + +- `../intake/阶段5：P1-P22 单页设计骨架.md` +- `../intake/阶段3：PPT 总纲 v1.md` +- `../intake/阶段4：通用表达与视觉系统.md` + +Style continuity references: + +- `../../2026-06-29-搭上AI这条船/visual-system/visual-system.md` +- `../../2026-06-29-搭上AI这条船/visual-system/style/style-prompt-master.md` +- accepted old images `s01-v1-image.png` and `s10-v1-image.png` + +Backup fact-check source only: + +```text +C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\OPC销售\为什么是我们.md +``` + +Do not use the backup source to rewrite the deck structure. + +## Current Visual Definition + +> 深蓝黑商务底 + AI 航线作战图 + 深水区剖面 + 雷达 / 罗盘 / 工具箱 / 工厂 / 模具师 / 销售武器库母题 + 青色与金色信号高亮。 + +Working visual sentence: + +> 这不是一张重新动员大家上船的图，而是一张进入 AI 深水区前的市场判断和销售作战图。 + +Continuity rule: + +> 保留上一套的深蓝黑 AI 航线底板和青金高亮，但情绪从“兴奋上船”切换为“硬判断、深水区、证据链、销售立场”。 + +## Deck Tone + +The tone should hold four feelings: + +1. 清醒：承认平台强，也承认普通 AI 开发公司存在。 +2. 坚定：我们的定位不是平台、不是外包，而是专家能力工程化。 +3. 专业：敢于说简单 AI 客户自己做，复杂专家智能体才是我们的场。 +4. 行动：差异最终要沉淀成销售武器库。 + +Language direction: + +> 自己人口吻 + 公司化判断 + 战前校准感。 + +Avoid turning it into: + +- customer-facing proposal; +- founder biography deck; +- AI trend lecture; +- dense internal manual; +- another copy of the previous kickoff deck. + +## Format Rules + +- Output page: 16:9 full-page visual image. +- Page text may be embedded in the image. +- Minor small-text defects are acceptable for validation, but the page title and core judgment must be readable. +- Each page keeps one big judgment, one core visual model, and three to five short support labels. +- Do not copy long source paragraphs into images. +- If image text fails but the visual base is strong, later PPT assembly may use text overlays. + +## Palette + +Base: + +- deep navy-black; +- dark ocean blue; +- cold slate gray; +- near-black executive background. + +Signal: + +- cyan / blue-green for AI signals, route lines, radar, active judgment paths; +- restrained gold / warm amber for key commitments, evidence, positioning, and sales confidence; +- white / pale blue for readable titles. + +Avoid: + +- bright cyberpunk neon; +- government red-gold; +- cheerful training-course pastel; +- clean white SaaS proposal style; +- luxury black-gold with no route-map logic. + +## Page Families + +| Family | Pages | Function | Primary Motifs | +| --- | --- | --- | --- | +| A Opening / Problem | P01-P03 | Establish why this deck exists and the three sales questions. | deepwater route, radar targets, question gates | +| B Market Contrast | P04-P07 | Acknowledge platforms and define the first boundary. | toolbox, factory, mold, shallow vs deep water | +| C Our Positioning | P08-P12 | Define expert agents and our role. | digital employee card, expert capability mold, engineering cutaway | +| D Customer Choice | P13-P18 | Explain why customers choose us. | decision compass, three-line crossing, iceberg, validation route, calibration loop | +| E Sober Judgment | P19-P21 | Show the difference is real but must be proved. | evidence chain, lighthouse pillars, maturity dashboard | +| F Sales Arsenal | P22 | Turn positioning into reusable sales tools. | arsenal wall, navigation map, proof layer, action layer | + +## Text Rendering Policy + +- Prefer short Chinese labels of 2-8 characters. +- Use page title + one core judgment + 3-5 short labels. +- Avoid long sentence clusters inside diagrams. +- Do not overfill P10 with every phrase from the source. P10 must focus on: + - 专家能力; + - 抽取; + - 封装; + - 验证; + - 校准; + - 进入真实流程. + +## Forbidden Drift + +Avoid: + +- platform-bashing; +- developer-company-bashing; +- claiming we can do all AI; +- generic humanoid robots; +- literal cute ships; +- pirate / fantasy ship; +- stock meeting photos; +- customer proposal deck; +- dense dashboard UI; +- unrelated futuristic city; +- large blocks of copied source material. + +## Validation Questions + +For P01: + +1. Does the page feel like the prequel to the previous deck, not a duplicate? +2. Does “AI 深水区 / 为什么是我们” read before decoration? +3. Is the cover harder and more sober than the kickoff deck? + +For P10: + +1. Does the page make our positioning clear without needing a long explanation? +2. Can sales take away “专家能力工程化” as the first read? +3. Does the visual model show extraction, molding, validation, calibration, and workflow entry? + +## Sample Adjustment Rule + +- Common base problem: update this file and `visual-system/style/style-prompt-master.md`. +- Page-specific issue: update only the relevant `slides/sNN/sNN-vN-*` artifacts. +- Use append-only versions for repairs.