55 lines
3.6 KiB
Markdown
55 lines
3.6 KiB
Markdown
# 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`.
|