Qiaomu Opencli Oneshot logo

Qiaomu Opencli Oneshot

Community
joeseesun
qiaomu-opencli-oneshot

Use when quickly generating a single OpenCLI command from a specific URL and goal description. 4-step process — open page, capture API, write TS adapter, test. For full site exploration, use opencli-explorer instead.

Overview

Publisherjoeseesun
Repositoryqiaomu-opencli-skills
Skill nameqiaomu-opencli-oneshot
Stars
992
Forks
76
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by joeseesun on GitHub. Read the source before you install it.

Installation

Install the Qiaomu Opencli Oneshot AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/joeseesun/qiaomu-opencli-skills/tree/main/qiaomu-opencli-oneshot
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/joeseesun/qiaomu-opencli-skills.git /tmp/qiaomu-opencli-skills
mkdir -p .claude/skills
cp -r /tmp/qiaomu-opencli-skills/qiaomu-opencli-oneshot .claude/skills/qiaomu-opencli-oneshot
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qiaomu Opencli Oneshot in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Qiaomu Opencli Oneshot on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Qiaomu Opencli Oneshot is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CLI-ONESHOT — 单点快速 CLI 生成

给一个 URL + 一句话描述,4 步生成一个 CLI 命令。 完整探索式开发请看 opencli-explorer skill。


输入

项目示例
URLhttps://x.com/jakevin7/lists
Goal获取我的 Twitter Lists

流程

Step 1: 打开页面 + 抓包

1. browser_navigate → 打开目标 URL
2. 等待 3-5 秒(让页面加载完、API 请求触发)
3. browser_network_requests → 筛选 JSON API

关键:只关注返回 application/json 的请求,忽略静态资源。 如果没有自动触发 API,手动点击目标按钮/标签再抓一次。

Step 2: 锁定一个接口

从抓包结果中找到那个目标 API。看这几个字段:

字段关注什么
URLAPI 路径 pattern(如 /i/api/graphql/xxx/ListsManagePinTimeline)
MethodGET / POST
Headers有 Cookie? Bearer? CSRF? 自定义签名?
Response数据在哪个路径(如 data.list.lists)

Step 3: 验证接口能复现

在 browser_evaluate 中用 fetch 复现请求:

javascript
// Tier 2 (Cookie): 大多数情况
fetch('/api/endpoint', { credentials: 'include' }).then(r => r.json())

// Tier 3 (Header): 如 Twitter 需要额外 header
const ct0 = document.cookie.match(/ct0=([^;]+)/)?.[1];
fetch('/api/endpoint', {
  headers: { 'Authorization': 'Bearer ...', 'X-Csrf-Token': ct0 },
  credentials: 'include'
}).then(r => r.json())

如果 fetch 能拿到数据 → 用 TS adapter(cli() pipeline 或 func())。 如果 fetch 拿不到(签名/风控)→ 用 intercept 策略(TS func() + installInterceptor)。

Step 4: 套模板,生成 adapter

根据 Step 3 判定的策略,选一个模板生成文件。


认证速查

fetch(url) 直接能拿到?              → Tier 1: public   (TS pipeline, browser: false)
fetch(url, {credentials:'include'})? → Tier 2: cookie   (TS pipeline 或 func())
加 Bearer/CSRF header 后拿到?        → Tier 3: header   (TS func())
都不行,但页面自己能请求成功?          → Tier 4: intercept (TS func(), installInterceptor)

模板

TS — Cookie/Public(最简,func() 模式)

typescript
// clis/<site>/<name>.ts
import { cli, Strategy } from '@jackwener/opencli/registry';

cli({
  site: 'mysite',
  name: 'mycommand',
  description: '一句话描述',
  domain: 'www.example.com',
  strategy: Strategy.COOKIE,   // 或 Strategy.PUBLIC (加 browser: false)
  browser: true,
  args: [
    { name: 'limit', type: 'int', default: 20 },
  ],
  columns: ['rank', 'title', 'value'],
  func: async (page, kwargs) => {
    await page.goto('https://www.example.com/target-page');
    const data = await page.evaluate(`(async () => {
      const res = await fetch('/api/target', { credentials: 'include' });
      const d = await res.json();
      return (d.data?.items || []).map(item => ({
        title: item.title,
        value: item.value,
      }));
    })()`);
    return (data as any[]).slice(0, kwargs.limit).map((item, i) => ({
      rank: i + 1,
      title: item.title || '',
      value: item.value || '',
    }));
  },
});

TS — Intercept(抓包模式)

typescript
// clis/<site>/<name>.ts
import { cli, Strategy } from '@jackwener/opencli/registry';

cli({
  site: 'mysite',
  name: 'mycommand',
  description: '一句话描述',
  domain: 'www.example.com',
  strategy: Strategy.INTERCEPT,
  browser: true,
  args: [
    { name: 'limit', type: 'int', default: 20 },
  ],
  columns: ['rank', 'title', 'value'],
  func: async (page, kwargs) => {
    // 1. 导航
    await page.goto('https://www.example.com/target-page');
    await page.wait(3);

    // 2. 注入拦截器(URL 子串匹配)
    await page.installInterceptor('target-api-keyword');

    // 3. 触发 API(滚动/点击)
    await page.autoScroll({ times: 2, delayMs: 2000 });

    // 4. 读取拦截的响应
    const requests = await page.getInterceptedRequests();
    if (!requests?.length) return [];

    let results: any[] = [];
    for (const req of requests) {
      const items = req.data?.data?.items || [];
      results.push(...items);
    }

    return results.slice(0, kwargs.limit).map((item, i) => ({
      rank: i + 1,
      title: item.title || '',
      value: item.value || '',
    }));
  },
});

TS — Header(如 Twitter GraphQL)

typescript
import { cli, Strategy } from '@jackwener/opencli/registry';

cli({
  site: 'twitter',
  name: 'mycommand',
  description: '一句话描述',
  domain: 'x.com',
  strategy: Strategy.HEADER,
  browser: true,
  args: [
    { name: 'limit', type: 'int', default: 20 },
  ],
  columns: ['rank', 'name', 'value'],
  func: async (page, kwargs) => {
    await page.goto('https://x.com');
    const data = await page.evaluate(`(async () => {
      const ct0 = document.cookie.match(/ct0=([^;]+)/)?.[1];
      if (!ct0) return { error: 'Not logged in' };
      const bearer = 'AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D...';
      const res = await fetch('/i/api/graphql/QUERY_ID/Endpoint', {
        headers: {
          'Authorization': 'Bearer ' + decodeURIComponent(bearer),
          'X-Csrf-Token': ct0,
          'X-Twitter-Auth-Type': 'OAuth2Session',
        },
        credentials: 'include',
      });
      return res.json();
    })()`);
    // 解析 data...
    return [];
  },
});

测试(必做)

bash
npm run build                              # 语法检查
opencli list | grep mysite                 # 确认注册
opencli mysite mycommand --limit 3 -v      # 实际运行

就这样,没了

写完文件 → build → run → 提交。有问题再看 opencli-explorer skill。

Frequently asked questions

What does the Qiaomu Opencli Oneshot AI skill do?

Use when quickly generating a single OpenCLI command from a specific URL and goal description. 4-step process — open page, capture API, write TS adapter, test. For full site exploration, use opencli-explorer instead.

Why use Qiaomu Opencli Oneshot on TypingMind?

Because you install it once and use it with any model. Qiaomu Opencli Oneshot is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Qiaomu Opencli Oneshot in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/joeseesun/qiaomu-opencli-skills/tree/main/qiaomu-opencli-oneshot. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Qiaomu Opencli Oneshot?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Qiaomu Opencli Oneshot?

As many as you like. As long as a model supports skills, you can use Qiaomu Opencli Oneshot with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Qiaomu Opencli Oneshot AI skill free?

Yes. It is published on GitHub by joeseesun under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇