agentleFS
different-ai-studiodifferent-ai-studio/teamclaw/skills/image-gen/SKILL.md

image-gen

Skill128 starsChanged 2 months agoMITView on GitHub

生成图片:配图、插图、海报、头像、示意图、Logo 草稿、封面、banner。触发词:画一张、画个、生成图片、生成一张图、做张图、做个图、配图、出图、生图、AI 绘图、image、draw、illustration、poster。仅从零生成,不做已有图片的编辑或修改。

48 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use spotify, trello and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • QuixiAISkill

    spotify

    Search Spotify, inspect current playback and devices, and control playback with explicit approval

    Also in 3 projects that use this

  • QuixiAISkill

    trello

    List Trello boards, lists, and cards and create or update cards with explicit approval

    Also in 3 projects that use this

  • AnthropicSkill

    daily-briefing

    Morning rundown - today's meetings with account context, opps closing soon with stale flags, waiting customer emails, and the day's top actions. Use when the user says "daily briefing", "daily brief", "morning briefing", "what's my day", "what's on my plate today", "prep my day", "start my day", "morning rundown", or on a schedule.

    Also in 3 projects that use this

  • silvainfmSkill

    paid-ads

    When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.

    Also in 3 projects that use this

  • AnthropicSkill

    weather

    The optional standing status report ("the weather"): compile open incidents, build health, merge-queue stats, and deploy lag into one always-current report page, and post to the channel only when a defined event fires. Use when the weather routine fires, or when someone asks to run/update the weather report.

    Also in 3 projects that use this

  • SentrySkill

    notion

    Search, fetch, create, update, and move Notion pages and data sources. Use when users ask to look up docs, specs, notes, meeting notes, project context, roadmaps, trackers, or internal references stored in Notion, or when they explicitly ask to create or edit Notion content.

    Also in 3 projects that use this

The file

Files
SKILL.md

图片生成

通过团队 AI 网关生成图片。按张计入团队积分,所以不要为一次请求反复重试。

怎么用

node scripts/generate.mjs --prompt "一片红色枫叶,扁平矢量风格,白色背景"

可选参数:

参数默认说明
--n1张数。每张都单独计费,用户没明确要多张就别传
--size1024x1024还支持 1024x1536(竖)、1536x1024(横)
--quality由网关决定low / medium / high。high 是标准价的 3 倍,用户没要求就别传
--out-dir当前目录一般不要传,见下面第 1 条

脚本只往 stdout 打印文件名、尺寸和大小。

四条硬约束

1. 图片必须留在会话目录里,引用必须用相对路径。

桌面端渲染 ![](...) 时会把路径按会话目录解析,解析结果只要落在会话目录之外就直接渲染成空 —— 没有报错、没有占位图、控制台也没有任何东西。所以:

![一片红色枫叶](maple-leaf-20260909-231500.png)   ← 对
![一片红色枫叶](/tmp/x.png)                        ← 用户看到的是一段没有图的文字
![一片红色枫叶](file:///Users/…/x.png)             ← 同上

直接用脚本打印出来的文件名,不要加目录前缀、不要转成绝对路径。

2. 绝对不要读这个图片文件。

不要 cat、不要 base64、不要用读文件工具打开它。一张图是 1–3 MB 的 base64,把它读进上下文会直接撑爆会话的压缩机制,之后每一轮都在白烧。你需要知道的一切(文件名、尺寸、大小)脚本已经打印了。

3. 不要自己拼 HTTP 请求。

只调 scripts/generate.mjs。不要去读 TEAMCLU_TEAM_PROVIDER、更不要读 tc_gateway_token,也不要用 curl 直接打网关。

4. 失败就照实告诉用户,不要重试。

脚本已经把错误翻译成人话了(积分不足、额度超限、团队没开网关、尺寸不支持、内容被拦截)。把那句话转述给用户就行 —— 这些都是用户自己能解决的问题,重试只会再花一次钱。唯一值得重试一次的是超时。

提示词写法

英文和中文都可以。把风格、构图、背景写进去,模型会自己改写提示词(脚本会把改写后的版本打印出来):

  • 好:一片红色枫叶,扁平矢量风格,纯白背景,居中构图
  • 差:枫叶

生成一张大约需要 30 秒,属于正常,不要中途取消。

完整示例

$ node scripts/generate.mjs --prompt "一片红色枫叶,扁平矢量,白底"
maple-leaf-20260909-231500.png  (765 KB, 1024x1024)
  改写后的提示词: A single red maple leaf, flat vector illustration, white background

然后在回复里写:

![一片红色枫叶](maple-leaf-20260909-231500.png)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.