video-workbench/projects/2026-07-01-为什么是我们/slides/s07/s07-v1-prompt.md

3.6 KiB
Raw Blame History

S-07 v1 Prompt

Skill Mode

{
  "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3PPT 总纲 v1.md; intake/阶段4通用表达与视觉系统.md; intake/阶段5P1-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

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.