Skip to main content
skill CX Codex

qiaomu-opencli-oneshot — Claude Code skill: setup and guide

Generates a single OpenCLI TypeScript adapter from a target web page and a goal description in four steps.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add joeseesun/qiaomu-opencli-skills --skill qiaomu-opencli-oneshot -a claude-code
Open on GitHub

What qiaomu-opencli-oneshot does

The skill turns browser network traffic into a standalone OpenCLI command. The agent navigates to the target page, waits for network requests to settle, and isolates endpoints returning JSON. It inspects parameters, headers, and authentication tokens directly inside the browser environment.

It handles four access tiers: public endpoints, cookie-based sessions, explicit authorization headers, and request interception via installInterceptor. Once validated with fetch, the agent writes a TypeScript file using @jackwener/opencli/registry, defines CLI arguments, and runs npm run build to verify syntax.

Generating commands requires an OpenCLI environment with browser automation tools enabled. If a target site demands deep crawling across multiple paths, this workflow is intentionally scoped down to one endpoint.

What it helps with

  • capture network JSON responses from a target web page
  • generate an OpenCLI TypeScript adapter file
  • validate browser fetch requests across different authentication tiers
  • handle anti-scraping barriers using request interception

Example prompts for the agent

  • Create an OpenCLI command to export my reading list from this web page
  • Inspect network traffic on the target page and generate a TypeScript adapter
  • Build a one-shot OpenCLI command for fetching table data from the current view

How to install qiaomu-opencli-oneshot

1Skills CLI (Vercel)

npx skills add joeseesun/qiaomu-opencli-skills --skill qiaomu-opencli-oneshot -a claude-code

2Manually: put the files in place

~/.claude/skills/qiaomu-opencli-oneshot/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/qiaomu-opencli-oneshot/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about qiaomu-opencli-oneshot

How do I install qiaomu-opencli-oneshot in Claude Code?

Run npx skills add joeseesun/qiaomu-opencli-skills --skill qiaomu-opencli-oneshot -a claude-code.

What does qiaomu-opencli-oneshot do?

It automates creating OpenCLI commands by capturing network requests, verifying API calls, and generating TypeScript adapter files.

Which authentication strategies does the skill cover?

It classifies endpoints into public calls, cookie credentials, custom headers, and browser interception when requests cannot be reproduced directly.

Source text

SKILL.md · MIT
---
name: qiaomu-opencli-oneshot
description: 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.
author: joeseesun
upstream: jackwener/opencli
tags: [opencli, adapter, quick-start, ts, cli, one-shot, automation]
---

# 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](../opencli-explorer/SKILL.md)。

---

## 输入

| 项目 | 示例 |
|------|------|
| **URL** | `https://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 |
|------|----------|
| URL | API 路径 pattern(如 `/i/api/graphql/xxx/ListsManagePinTimeline`) |
| Method | GET / 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](../opencli-explorer/SKILL.md)。

© joeseesun · MIT · joeseesun/qiaomu-opencli-skills

Similar skills

All skills for Browser and scraping →

From the same set4

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor