# 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.
```