video-workbench/projects/2026-07-01-为什么是我们/slides/s16/s16-v1-prompt.md

3.3 KiB
Raw Permalink Blame History

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.