agentleFS
BillLuckyBillLucky/tuiqiao-skills/skills/inspiration/SKILL.md

inspiration

Skill1 starsChanged 8 months agoMITView on GitHub

通过 tuiqiao.art 的 API 直接调用「灵感生图」能力。 在已登录的浏览器中执行 JavaScript,无需提取 Cookie:

  • Sends data out

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. holtzy/dataviz-skills★ 20same name
    2. TakeOff-Team/claude-shortform-video-editor★ 11same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Files
SKILL.md

推敲AI (tuiqiao.art) 灵感生图 Skill

通过 tuiqiao.art 的 API 直接调用「灵感生图」能力。


核心 API

操作方法路径
创建任务POST/api/v1/images/generate/new
查询最近记录GET/api/v1/images/records/lately

records/lately 响应结构

{
  "code": 200,
  "data": {
    "records": [{
      "id": 28018,
      "prompt": "提示词",
      "ratio": "4:3",
      "width": 1024,
      "height": 768,
      "count": 2,
      "status": "COMPLETED",
      "type": "INSPIRATION",
      "modelOutwardName": "灵感生图",
      "generatedImages": [{
        "id": 29016,
        "imageUrl": "https://tuiqiao.art/picture/original/ai-design-prod/...",
        "width": 1024,
        "height": 768
      }]
    }]
  }
}

高效工作流(只需3步)

  1. 创建任务 → POST /api/v1/images/generate/new,拿到 taskId
  2. 轮询记录 → GET /api/v1/images/records/lately,检查 records[0].id === taskId && status === "COMPLETED"
  3. 下载图片 → 从 generatedImages[].imageUrl 直接拿 URL 下载

创建任务请求体

{
  "prompt": "日本冲绳 海岛风 coworking space",
  "ratio": "4:3",
  "width": 1152,
  "height": 864,
  "count": 1,
  "type": "INSPIRATION",
  "modelId": 8889,
  "promptImageUrl": null,
  "underImageUrl": null,
  "negativePrompt": null
}

比例映射

ratiowidthheight
1:110241024
16:91344756
4:31152864
3:21152768
2:37681152
3:48641152
9:165761024

认证方式

方式一:浏览器自动化(✅ 推荐)

在已登录的浏览器中执行 JavaScript,无需提取 Cookie:

// 创建任务
const resp = await fetch('/api/v1/images/generate/new', {
    method: 'POST',
    credentials: 'include',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify(payload)
});
const { data: { id: taskId } } = await resp.json();

// 轮询 records/lately 直到完成
for (let i = 0; i < 30; i++) {
    const rec = await fetch('/api/v1/images/records/lately', { credentials: 'include' });
    const json = await rec.json();
    const record = json.data.records.find(r => r.id === taskId);
    if (record?.status === 'COMPLETED') {
        console.log('图片URL:', record.generatedImages.map(img => img.imageUrl));
        break;
    }
    await new Promise(r => setTimeout(r, 2000));
}

方式二:Cookie 环境变量

export TUIQIAO_COOKIE="你的Cookie字符串"

注意事项

  • 不要用 SSE — SSE 流不可靠,且 COMPLETED 时 data 可能为 null
  • 用 records/lately — 数据完整,包含所有图片 URL,无需额外解析
  • 轮询间隔 2-3 秒 — 生成通常 20-60 秒完成
  • 超时 90 秒 — 超过则放弃

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.