video-workbench/projects/2026-07-01-为什么是我们/slides/s11/s11-v1-prompt.md

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.