skill-seekers

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Seekers

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills automatically.

自动将文档网站、GitHub仓库和PDF转换为Claude AI Skills

When to Activate

适用场景

Use this skill when:

User wants to create a Claude skill from documentation
User asks about scraping docs, GitHub repos, or PDFs for Claude
User needs to package documentation into a
```
.zip
```
for Claude
User wants to convert a website, repo, or PDF into knowledge for Claude

在以下场景使用本Skill：

当用户想要从文档创建Claude Skill时
当用户询问如何为Claude抓取文档、GitHub仓库或PDF时
当用户需要将文档打包为.zip文件供Claude使用时
当用户想要将网站、仓库或PDF转换为Claude的知识库时

Quick Reference

快速参考

Installation

安装

bash

pip install skill-seekers

bash

pip install skill-seekers

Core Commands

核心命令

bash

undefined

bash

undefined

Scrape documentation website

抓取文档网站

skill-seekers scrape --config configs/react.json skill-seekers scrape --url https://docs.example.com --name myskill

Scrape GitHub repository

抓取GitHub仓库

skill-seekers github --repo facebook/react

Extract from PDF

从PDF提取内容

skill-seekers pdf --pdf docs/manual.pdf --name myskill

Combine multiple sources (docs + GitHub + PDF)

合并多个来源（文档 + GitHub + PDF）

skill-seekers unified --config configs/react_unified.json

Enhance the skill with AI

使用AI优化Skill

skill-seekers enhance output/myskill/

Package into .zip for Claude

打包为Claude可用的.zip文件

skill-seekers package output/myskill/

undefined

skill-seekers package output/myskill/

undefined

Complete Workflow

完整工作流

bash

undefined

bash

undefined

1. Scrape documentation

1. 抓取文档

skill-seekers scrape --url https://react.dev --name react

2. Enhance with AI (optional but recommended)

2. 使用AI优化（可选但推荐）

skill-seekers enhance output/react/

3. Package into zip

3. 打包为ZIP文件

skill-seekers package output/react/

4. Upload output/react.zip to Claude at https://claude.ai/skills

4. 将output/react.zip上传至Claude：https://claude.ai/skills

undefined

undefined

Key Features

核心功能

Feature	Description
Doc Scraping	Scrape any documentation website
GitHub Scraping	Extract code, APIs, issues from repos
PDF Extraction	Extract text, tables, images from PDFs
Unified Scraping	Combine docs + code + PDF in one skill
Conflict Detection	Find discrepancies between docs and code
AI Enhancement	Improve SKILL.md quality automatically
Async Mode	2-3x faster with `--async` flag

功能	描述
文档抓取	抓取任意文档网站
GitHub抓取	从仓库中提取代码、API、问题内容
PDF提取	从PDF中提取文本、表格、图片
统一抓取	将文档、代码、PDF合并为一个Skill
冲突检测	发现文档与代码之间的不一致
AI优化	自动提升SKILL.md的质量
异步模式	使用 `--async` 标志可提升2-3倍速度

Output Structure

输出结构

output/
├── myskill_data/     # Raw scraped data (cached)
└── myskill/          # Built skill directory
    ├── SKILL.md      # Main skill file (required)
    └── references/   # Categorized documentation
        ├── index.md
        ├── api.md
        └── ...

output/
├── myskill_data/     # 原始抓取数据（已缓存）
└── myskill/          # 生成的Skill目录
    ├── SKILL.md      # 主Skill文件（必填）
    └── references/   # 分类后的文档
        ├── index.md
        ├── api.md
        └── ...

Available Presets

预设配置

bash

skill-seekers scrape --config configs/godot.json     # Godot Engine
skill-seekers scrape --config configs/react.json     # React
skill-seekers scrape --config configs/vue.json       # Vue.js
skill-seekers scrape --config configs/django.json    # Django
skill-seekers scrape --config configs/fastapi.json   # FastAPI

bash

skill-seekers scrape --config configs/godot.json     # Godot引擎
skill-seekers scrape --config configs/react.json     # React
skill-seekers scrape --config configs/vue.json       # Vue.js
skill-seekers scrape --config configs/django.json    # Django
skill-seekers scrape --config configs/fastapi.json   # FastAPI

Config File Structure

配置文件结构

json

{
  "name": "myframework",
  "description": "When to use this skill",
  "base_url": "https://docs.myframework.com/",
  "selectors": {
    "main_content": "article",
    "title": "h1",
    "code_blocks": "pre code"
  },
  "url_patterns": {
    "include": ["/docs", "/guide"],
    "exclude": ["/blog", "/about"]
  },
  "rate_limit": 0.5,
  "max_pages": 500
}

json

{
  "name": "myframework",
  "description": "When to use this skill",
  "base_url": "https://docs.myframework.com/",
  "selectors": {
    "main_content": "article",
    "title": "h1",
    "code_blocks": "pre code"
  },
  "url_patterns": {
    "include": ["/docs", "/guide"],
    "exclude": ["/blog", "/about"]
  },
  "rate_limit": 0.5,
  "max_pages": 500
}

skill-seekers

Original

Translation

Skill Seekers

Skill Seekers

When to Activate

适用场景

Quick Reference

快速参考

Installation

安装

Core Commands

核心命令

Scrape documentation website

抓取文档网站

Scrape GitHub repository

抓取GitHub仓库

Extract from PDF

从PDF提取内容

Combine multiple sources (docs + GitHub + PDF)

合并多个来源（文档 + GitHub + PDF）

Enhance the skill with AI

使用AI优化Skill

Package into .zip for Claude

打包为Claude可用的.zip文件

Complete Workflow

完整工作流

1. Scrape documentation

1. 抓取文档

2. Enhance with AI (optional but recommended)

2. 使用AI优化（可选但推荐）

3. Package into zip

3. 打包为ZIP文件

4. Upload output/react.zip to Claude at https://claude.ai/skills

4. 将output/react.zip上传至Claude：https://claude.ai/skills

Key Features

核心功能

Output Structure

输出结构

Available Presets

预设配置

Config File Structure

配置文件结构

Navigation

导航