image-poster

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Image Poster Skill

Produce one finished image asset per turn unless the user asks for variations. Image generation rewards a tight, structured prompt — your job is to assemble that prompt from the user's brief, then dispatch.

每次生成一张成品图像资产，除非用户要求变体。图像生成需要精准、结构化的提示词——你的任务是根据用户的需求整理出提示词，然后执行生成。

Resource map

资源映射

image-poster/
├── SKILL.md         ← you're reading this
└── example.html     ← what the resulting card looks like in Examples

image-poster/
├── SKILL.md         ← 你正在阅读的文件
└── example.html     ← 示例中最终卡片的效果展示

Workflow

工作流

Step 0 — Read the project metadata

步骤0 — 读取项目元数据

The active project carries

imageModel

imageAspect

, and (optional)

imageStyle

notes. Use them as the upstream model + canvas + style anchor; only ask the user to fill them in if they're marked

(unknown — ask)

当前项目包含

imageModel

、

imageAspect

和（可选）

imageStyle

信息。将它们作为上游模型、画布尺寸和风格基准；仅当这些信息标记为

(unknown — ask)

时，才需要询问用户补充。

Step 1 — Compose the prompt

步骤1 — 编写提示词

Plan in this exact order before calling any tool:

Subject + composition — what is in the frame, where, at what scale; eye-line and crop.
Lighting + mood — natural / studio / moody; warm / cool; key plus rim plus fill; time of day if outdoor.
Palette + textures — hex anchors when the user gave a brand palette; otherwise a 3-word mood tag (e.g. "muted ochre + ink").
Camera / lens — only if the user wants photographic realism ("85mm portrait, shallow DOF") or a specific film stock.
What to avoid — common AI-slop patterns ("no extra fingers, no warped text, no logo placeholders").

在调用任何工具前，严格按照以下顺序规划：

主体与构图 —— 画面中有什么、位置在哪里、比例如何；视线方向和裁剪范围。
光线与氛围 —— 自然光/影棚光/氛围感光线；暖色调/冷色调；主光+轮廓光+补光；若为户外场景则需说明时间。
配色与纹理 —— 如果用户提供了品牌配色，使用十六进制色值；否则使用3词风格标签（例如“柔和赭石+墨色”）。
相机/镜头 —— 仅当用户需要照片级写实效果（如“85mm人像镜头，浅景深”）或特定胶片类型时添加。
避坑项 —— 常见AI生成缺陷（如“无多余手指、无扭曲文字、无Logo占位符”）。

Step 2 — Dispatch via the media contract

步骤2 — 通过媒体协议执行生成

Use the unified dispatcher — do not call upstream provider APIs by hand. Run from your shell tool:

bash

node "$OD_BIN" media generate \
  --project "$OD_PROJECT_ID" \
  --surface image \
  --model "<imageModel from metadata>" \
  --aspect "<imageAspect from metadata>" \
  --output "<short-descriptive-name>.png" \
  --prompt "<the full assembled prompt from Step 1>"

The command prints one line of JSON:

{"file": {"name": "...", ...}}

. The daemon writes the bytes into the project folder; the FileViewer picks it up automatically.

使用统一调度器——不要手动调用上游提供商API。在Shell工具中运行以下命令：

bash

node "$OD_BIN" media generate \
  --project "$OD_PROJECT_ID" \
  --surface image \
  --model "<imageModel from metadata>" \
  --aspect "<imageAspect from metadata>" \
  --output "<short-descriptive-name>.png" \
  --prompt "<the full assembled prompt from Step 1>"

该命令会输出一行JSON：

{"file": {"name": "...", ...}}

。守护进程会将文件写入项目文件夹，FileViewer会自动识别并展示。

Step 3 — Hand off

步骤3 — 交付结果

Reply with a one-paragraph summary of the prompt you used and the filename returned by the dispatcher (e.g. I generated
hero-poster.png
with
gpt-image-2
at 1:1.). Do not emit an

<artifact>

tag.

回复一段包含所用提示词摘要和调度器返回文件名的内容（例如：我使用
gpt-image-2
生成了
hero-poster.png
，比例为1:1。）。不要输出

<artifact>

标签。

Hard rules

硬性规则

One image per turn unless asked for variations.
Honor
```
imageAspect
```
exactly — the upstream cost is the same; matching the aspect avoids a re-render.
No filler typography in the image itself unless the user asked for in-frame text. Real copy beats lorem.
Save every render — never describe an image without producing the file. The user expects something to open in the file viewer.

每次生成一张图像，除非用户要求变体。
严格遵循
```
imageAspect
```
比例——上游生成成本一致，匹配比例可避免重新生成。
除非用户要求画面内添加文字，否则图像中不要包含填充性文字。真实文案优于占位文本。
保存每次生成的结果——切勿只描述图像而不生成文件。用户期望能在文件查看器中打开成品。