diff --git a/README.md b/README.md index 056157c..32f4b05 100644 --- a/README.md +++ b/README.md @@ -1,322 +1,329 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/yusufkaraaslan/Skill_Seekers) · [上游 README](https://github.com/yusufkaraaslan/Skill_Seekers/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 +

Skill Seekers

# Skill Seekers -English | [简体中文](README.zh-CN.md) | [日本語](README.ja.md) | [한국어](README.ko.md) | [Español](README.es.md) | [Français](README.fr.md) | [Deutsch](README.de.md) | [Português](README.pt-BR.md) | [Türkçe](README.tr.md) | [العربية](README.ar.md) | [हिन्दी](README.hi.md) | [Русский](README.ru.md) +[English](README.md) | 简体中文 | [日本語](README.ja.md) | [한국어](README.ko.md) | [Español](README.es.md) | [Français](README.fr.md) | [Deutsch](README.de.md) | [Português](README.pt-BR.md) | [Türkçe](README.tr.md) | [العربية](README.ar.md) | [हिन्दी](README.hi.md) | [Русский](README.ru.md) -[![Version](https://img.shields.io/badge/version-3.7.0-blue.svg)](https://github.com/yusufkaraaslan/Skill_Seekers/releases) -[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) +> ⚠️ **机器翻译声明** +> +> 本文档由 AI 自动翻译生成。虽然我们努力确保翻译质量，但可能存在不准确或不自然的表述。 +> +> 欢迎通过 [GitHub Issue #260](https://github.com/yusufkaraaslan/Skill_Seekers/issues/260) 帮助改进翻译！您的反馈对我们非常宝贵。 + +[![版本](https://img.shields.io/badge/version-3.7.0-blue.svg)](https://github.com/yusufkaraaslan/Skill_Seekers/releases) +[![许可证: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/) -[![MCP Integration](https://img.shields.io/badge/MCP-40-Tools-blue.svg)](https://modelcontextprotocol.io) -[![Tested](https://img.shields.io/badge/Tests-3700%2B%20Passing-brightgreen.svg)](tests/) -[![Project Board](https://img.shields.io/badge/Project-Board-purple.svg)](https://github.com/users/yusufkaraaslan/projects/2) -[![PyPI version](https://badge.fury.io/py/skill-seekers.svg)](https://pypi.org/project/skill-seekers/) -[![PyPI - Downloads](https://img.shields.io/pypi/dm/skill-seekers.svg)](https://pypi.org/project/skill-seekers/) -[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/skill-seekers.svg)](https://pypi.org/project/skill-seekers/) -[![Website](https://img.shields.io/badge/Website-skillseekersweb.com-blue.svg)](https://skillseekersweb.com/) -[![Twitter Follow](https://img.shields.io/twitter/follow/_yUSyUS_?style=social)](https://x.com/_yUSyUS_) -[![GitHub Repo stars](https://img.shields.io/github/stars/yusufkaraaslan/Skill_Seekers?style=social)](https://github.com/yusufkaraaslan/Skill_Seekers) +[![MCP 集成](https://img.shields.io/badge/MCP-40-Tools-blue.svg)](https://modelcontextprotocol.io) +[![测试通过](https://img.shields.io/badge/Tests-3700%2B%20Passing-brightgreen.svg)](tests/) +[![项目看板](https://img.shields.io/badge/Project-Board-purple.svg)](https://github.com/users/yusufkaraaslan/projects/2) +[![PyPI 版本](https://badge.fury.io/py/skill-seekers.svg)](https://pypi.org/project/skill-seekers/) +[![PyPI - 下载量](https://img.shields.io/pypi/dm/skill-seekers.svg)](https://pypi.org/project/skill-seekers/) +[![PyPI - Python 版本](https://img.shields.io/pypi/pyversions/skill-seekers.svg)](https://pypi.org/project/skill-seekers/) [![PyPI Downloads](https://static.pepy.tech/personalized-badge/skill-seekers?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/skill-seekers) +Trendshift +[![官方网站](https://img.shields.io/badge/Website-skillseekersweb.com-blue.svg)](https://skillseekersweb.com/) +[![关注 Twitter](https://img.shields.io/twitter/follow/_yUSyUS_?style=social)](https://x.com/_yUSyUS_) +[![GitHub Stars](https://img.shields.io/github/stars/yusufkaraaslan/Skill_Seekers?style=social)](https://github.com/yusufkaraaslan/Skill_Seekers) -yusufkaraaslan%2FSkill_Seekers | Trendshift +**🧠 AI 系统的数据层。** Skill Seekers 将文档网站、GitHub 仓库、PDF、视频、笔记本、Wiki 等 18 种来源类型转换为结构化知识资产——可在几分钟（而非几小时）内为 AI 技能（Claude、Gemini、OpenAI）、RAG 流水线（LangChain、LlamaIndex、Pinecone）和 AI 编程助手（Cursor、Windsurf、Cline）提供支持。 -**🧠 The data layer for AI systems.** Skill Seekers turns documentation sites, GitHub repos, PDFs, videos, notebooks, wikis, and 10+ more source types into structured knowledge assets—ready to power AI Skills (Claude, Gemini, OpenAI), RAG pipelines (LangChain, LlamaIndex, Pinecone), and AI coding assistants (Cursor, Windsurf, Cline) in minutes, not hours. +> 🌐 **[访问 SkillSeekersWeb.com](https://skillseekersweb.com/)** - 浏览 24+ 个预设配置，分享您的配置，访问完整文档！ -> 🌐 **[Visit SkillSeekersWeb.com](https://skillseekersweb.com/)** - Browse 24+ preset configs, share your configs, and access complete documentation! +> 📋 **[查看开发路线图和任务](https://github.com/users/yusufkaraaslan/projects/2)** - 10 个类别的 134 个任务，选择任意一个参与贡献！ -> 📋 **[View Development Roadmap & Tasks](https://github.com/users/yusufkaraaslan/projects/2)** - 134 tasks across 10 categories, pick any to contribute! +## 🌐 生态系统 -## 🌐 Ecosystem +Skill Seekers 是一个多仓库项目。以下是各部分所在位置： -Skill Seekers is a multi-repo project. Here's where everything lives: +| 仓库 | 描述 | 链接 | +|------|------|------| +| **[Skill_Seekers](https://github.com/yusufkaraaslan/Skill_Seekers)** | 核心 CLI 和 MCP 服务器（本仓库） | [PyPI](https://pypi.org/project/skill-seekers/) | +| **[skillseekersweb](https://github.com/yusufkaraaslan/skillseekersweb)** | 网站和文档 | [在线](https://skillseekersweb.com/) | +| **[skill-seekers-configs](https://github.com/yusufkaraaslan/skill-seekers-configs)** | 社区配置仓库 | | +| **[skill-seekers-action](https://github.com/yusufkaraaslan/skill-seekers-action)** | GitHub Action CI/CD | | +| **[skill-seekers-plugin](https://github.com/yusufkaraaslan/skill-seekers-plugin)** | Claude Code 插件 | | +| **[homebrew-skill-seekers](https://github.com/yusufkaraaslan/homebrew-skill-seekers)** | macOS Homebrew tap | | -| Repository | Description | Links | -|-----------|-------------|-------| -| **[Skill_Seekers](https://github.com/yusufkaraaslan/Skill_Seekers)** | Core CLI & MCP server (this repo) | [PyPI](https://pypi.org/project/skill-seekers/) | -| **[skillseekersweb](https://github.com/yusufkaraaslan/skillseekersweb)** | Website & documentation | [Live](https://skillseekersweb.com/) | -| **[skill-seekers-configs](https://github.com/yusufkaraaslan/skill-seekers-configs)** | Community config repository | | -| **[skill-seekers-action](https://github.com/yusufkaraaslan/skill-seekers-action)** | GitHub Action for CI/CD | | -| **[skill-seekers-plugin](https://github.com/yusufkaraaslan/skill-seekers-plugin)** | Claude Code plugin | | -| **[homebrew-skill-seekers](https://github.com/yusufkaraaslan/homebrew-skill-seekers)** | Homebrew tap for macOS | | +> **想要贡献？** 网站和配置仓库是新贡献者的最佳起点！ -> **Want to contribute?** The website and configs repos are great starting points for new contributors! +## 🧠 AI 系统的数据层 -## 🧠 The Data Layer for AI Systems - -**Skill Seekers is the universal preprocessing layer** that sits between raw documentation and every AI system that consumes it. Whether you are building Claude skills, a LangChain RAG pipeline, or a Cursor `.cursorrules` file — the data preparation is identical. You do it once, and export to all targets. +**Skill Seekers 是通用预处理层**，位于原始文档和所有使用它的 AI 系统之间。无论您是在构建 Claude 技能、LangChain RAG 流水线，还是 Cursor `.cursorrules` 文件——数据准备工作完全相同。只需执行一次，即可导出到所有目标平台。 ```bash -# One command → structured knowledge asset +# 一条命令 → 结构化知识资产 skill-seekers create https://docs.react.dev/ -# or: skill-seekers create facebook/react -# or: skill-seekers create ./my-project +# 或: skill-seekers create facebook/react +# 或: skill-seekers create ./my-project -# Export to any AI system -skill-seekers package output/react --target claude # → Claude AI Skill (ZIP) +# 导出到任意 AI 系统 +skill-seekers package output/react --target claude # → Claude AI 技能 (ZIP) skill-seekers package output/react --target langchain # → LangChain Documents skill-seekers package output/react --target llama-index # → LlamaIndex TextNodes skill-seekers package output/react --target cursor # → .cursorrules -skill-seekers package output/react --target ibm-bob # → IBM Bob skill directory +skill-seekers package output/react --target ibm-bob # → IBM Bob 技能目录 ``` -### What gets built +### 可构建的输出 -| Output | Target | What it powers | -|--------|--------|---------------| -| **Claude Skill** (ZIP + YAML) | `--target claude` | Claude Code, Claude API | -| **Gemini Skill** (tar.gz) | `--target gemini` | Google Gemini | -| **OpenAI / Custom GPT** (ZIP) | `--target openai` | GPT-4o, custom assistants | -| **LangChain Documents** | `--target langchain` | QA chains, agents, retrievers | -| **LlamaIndex TextNodes** | `--target llama-index` | Query engines, chat engines | -| **Haystack Documents** | `--target haystack` | Enterprise RAG pipelines | -| **Pinecone-ready** (Markdown) | `--target markdown` | Vector upsert | -| **ChromaDB / FAISS / Qdrant** | `--target chroma/faiss/qdrant` | Local vector DBs | -| **IBM Bob Skill** (directory) | `--target ibm-bob` | IBM Bob project/global skills | -| **Cursor** `.cursorrules` | `--target markdown` → copy SKILL.md | Cursor IDE `.cursorrules` | -| **Windsurf / Cline / Continue** | `--target claude` → copy | VS Code, IntelliJ, Vim | +| 输出 | 目标 | 应用场景 | +|------|------|---------| +| **Claude 技能** (ZIP + YAML) | `--target claude` | Claude Code、Claude API | +| **Gemini 技能** (tar.gz) | `--target gemini` | Google Gemini | +| **OpenAI / Custom GPT** (ZIP) | `--target openai` | GPT-4o、自定义助手 | +| **LangChain Documents** | `--target langchain` | QA 链、智能体、检索器 | +| **LlamaIndex TextNodes** | `--target llama-index` | 查询引擎、对话引擎 | +| **Haystack Documents** | `--target haystack` | 企业级 RAG 流水线 | +| **Pinecone 就绪** (Markdown) | `--target markdown` | 向量上传 | +| **ChromaDB / FAISS / Qdrant** | `--target chroma/faiss/qdrant` | 本地向量数据库 | +| **IBM Bob 技能**（目录） | `--target ibm-bob` | IBM Bob 项目/全局技能 | +| **Cursor** `.cursorrules` | `--target markdown` → 复制 SKILL.md | Cursor IDE `.cursorrules` | +| **Windsurf / Cline / Continue** | `--target claude` → 复制 | VS Code、IntelliJ、Vim | -### Why it matters +### 为什么选择 Skill Seekers -- ⚡ **99% faster** — Days of manual data prep → 15–45 minutes -- 🎯 **AI Skill quality** — 500+ line SKILL.md files with examples, patterns, and guides -- 📊 **RAG-ready chunks** — Smart chunking preserves code blocks and maintains context -- 🎬 **Videos** — Extract code, transcripts, and structured knowledge from YouTube and local videos -- 🔄 **Multi-source** — Combine 18 source types (docs, GitHub, PDFs, videos, notebooks, wikis, and more) into one knowledge asset -- 🌐 **One prep, every target** — Export the same asset to 21 platforms without re-scraping -- ✅ **Battle-tested** — 3,700+ tests, 24+ framework presets, production-ready +- ⚡ **快 99%** — 数天的手动数据准备 → 15–45 分钟 +- 🎯 **AI 技能质量** — 500+ 行的 SKILL.md 文件，包含示例、模式和指南 +- 📊 **RAG 就绪的分块** — 智能分块保留代码块并维护上下文 +- 🎬 **视频** — 从 YouTube 和本地视频提取代码、字幕和结构化知识 +- 🔄 **多源支持** — 将 18 种来源类型（文档、GitHub、PDF、视频、笔记本、Wiki 等）合并为一个知识资产 +- 🌐 **一次准备，导出所有目标** — 无需重新抓取即可将同一资产导出到 21 个平台 +- ✅ **久经考验** — 3,700+ 测试，24+ 框架预设，生产就绪 -## 🚀 Quick Start (3 Commands) +## 🚀 快速开始（3 条命令） ```bash -# 1. Install +# 1. 安装 pip install skill-seekers -# 2. Create skill from any source +# 2. 从任意来源创建技能 skill-seekers create https://docs.django.com/ -# 3. Package for your AI platform +# 3. 为您的 AI 平台打包 skill-seekers package output/django --target claude ``` -**That's it!** You now have `output/django-claude.zip` ready to use. +**就是这么简单！** 您现在已拥有可直接使用的 `output/django-claude.zip`。 ```bash -# Use a different AI agent for enhancement (default: claude) +# 使用其他 AI 代理进行增强（默认：claude） skill-seekers create https://docs.django.com/ --agent kimi skill-seekers create https://docs.django.com/ --agent codex skill-seekers create https://docs.django.com/ --agent-cmd "my-custom-agent run" ``` -### 🛰️ AI-driven project scan (new) +### 🛰️ AI 驱动的项目扫描（新功能） -Point `scan` at any project and an AI agent reads its manifests, README, -Dockerfile/CI and sampled source imports — then emits one config per detected -framework plus a `-codebase.json` for your own code. Pins the -detected version so re-running reports bumps: +将 `scan` 指向任意项目，AI 代理会读取其清单文件、README、Dockerfile/CI 和采样的源码导入——然后为每个检测到的框架生成一个配置文件，并为您自己的代码生成 `-codebase.json`。它会固定检测到的版本，因此重新运行时会报告版本升级： ```bash skill-seekers scan ./my-react-app --out ./configs/scanned/ # → react.json, vite.json, tailwind.json, jest.json, my-react-app-codebase.json -# Then build any of them +# 然后构建其中任意一个 skill-seekers create ./configs/scanned/react.json ``` -If a detection has no existing preset, the AI generates a fresh config; on -exit you can optionally publish it back to the [community registry](https://github.com/yusufkaraaslan/skill-seekers-configs). +如果某个检测结果没有现成预设，AI 会生成全新配置；退出时您可以选择将其发布回 [社区注册表](https://github.com/yusufkaraaslan/skill-seekers-configs)。 -### Other Sources (18 Supported) +### 其他来源（支持 18 种） ```bash -# GitHub repository +# GitHub 仓库 skill-seekers create facebook/react -# Local project +# 本地项目 skill-seekers create ./my-project -# PDF document +# PDF 文档 skill-seekers create manual.pdf -# Word document +# Word 文档 skill-seekers create report.docx -# EPUB e-book +# EPUB 电子书 skill-seekers create book.epub -# Jupyter Notebook +# Jupyter 笔记本 skill-seekers create notebook.ipynb -# OpenAPI spec +# OpenAPI 规范 skill-seekers create openapi.yaml -# PowerPoint presentation +# PowerPoint 演示文稿 skill-seekers create presentation.pptx -# AsciiDoc document +# AsciiDoc 文档 skill-seekers create guide.adoc -# Local HTML file (auto-detected by extension) +# 本地 HTML 文件（根据扩展名自动检测） skill-seekers create page.html -# Whole directory of HTML files (auto-detected for HTML-dominant dirs) +# 整个 HTML 文件目录（自动检测以 HTML 为主的目录） skill-seekers create ./mirror_output/site/ -# Force HTML mode on a mixed/code-heavy directory +# 在代码混杂的目录上强制 HTML 模式 skill-seekers create ./repo/ --html-path ./repo/docs/build/html/ -# RSS/Atom feed +# RSS/Atom 订阅源 skill-seekers create feed.rss -# Man page +# Man 手册页 skill-seekers create curl.1 -# Video (YouTube, Vimeo, or local file — requires skill-seekers[video]) +# 视频（YouTube、Vimeo 或本地文件 — 需要 skill-seekers[video]） skill-seekers create --video-url https://www.youtube.com/watch?v=... --name mytutorial -# First time? Auto-install GPU-aware visual deps: +# 首次使用？自动安装 GPU 感知的视觉依赖： skill-seekers create --setup -# Confluence wiki +# Confluence 维基 skill-seekers create --space-key TEAM --name wiki -# Notion pages +# Notion 页面 skill-seekers create --database-id ... --name docs -# Slack/Discord chat export +# Slack/Discord 聊天记录 skill-seekers create --chat-export-path ./slack-export --name team-chat ``` -### Export Everywhere +### 导出到任何地方 ```bash -# Package for multiple platforms +# 为多个平台打包 for platform in claude gemini openai langchain; do skill-seekers package output/django --target $platform done ``` -## What is Skill Seekers? +## 什么是 Skill Seekers？ -Skill Seekers is the **data layer for AI systems**. It transforms 18 source types—documentation websites, GitHub repositories, PDFs, videos, Jupyter Notebooks, Word/EPUB/AsciiDoc documents, OpenAPI specs, PowerPoint presentations, RSS feeds, man pages, Confluence wikis, Notion pages, Slack/Discord exports, and more—into structured knowledge assets for every AI target: +Skill Seekers 是 **AI 系统的数据层**，将 18 种来源类型——文档网站、GitHub 仓库、PDF、视频、Jupyter 笔记本、Word/EPUB/AsciiDoc 文档、OpenAPI 规范、PowerPoint 演示文稿、RSS 订阅源、Man 手册页、Confluence 维基、Notion 页面、Slack/Discord 聊天记录等——转换为适用于所有 AI 目标的结构化知识资产： -| Use Case | What you get | Examples | -|----------|-------------|---------| -| **AI Skills** | Comprehensive SKILL.md + references | Claude Code, Gemini, GPT | -| **RAG Pipelines** | Chunked documents with rich metadata | LangChain, LlamaIndex, Haystack | -| **Vector Databases** | Pre-formatted data ready for upsert | Pinecone, Chroma, Weaviate, FAISS | -| **AI Coding Assistants** | Context files your IDE AI reads automatically | Cursor, Windsurf, Cline, Continue.dev | +| 使用场景 | 获得的内容 | 示例 | +|---------|-----------|------| +| **AI 技能** | 完整的 SKILL.md + 参考文件 | Claude Code、Gemini、GPT | +| **RAG 流水线** | 带丰富元数据的分块文档 | LangChain、LlamaIndex、Haystack | +| **向量数据库** | 预格式化的待上传数据 | Pinecone、Chroma、Weaviate、FAISS | +| **AI 编程助手** | IDE AI 自动读取的上下文文件 | Cursor、Windsurf、Cline、Continue.dev | -## 📚 Documentation +## 📚 文档 -| I want to... | Read this | +| 我想要... | 阅读此文档 | |--------------|-----------| -| **Get started quickly** | [Quick Start](docs/getting-started/02-quick-start.md) - 3 commands to first skill | -| **Understand concepts** | [Core Concepts](docs/user-guide/01-core-concepts.md) - How it works | -| **Scrape sources** | [Scraping Guide](docs/user-guide/02-scraping.md) - All source types | -| **Enhance skills** | [Enhancement Guide](docs/user-guide/03-enhancement.md) - AI enhancement | -| **Export skills** | [Packaging Guide](docs/user-guide/04-packaging.md) - Platform export | -| **Look up commands** | [CLI Reference](docs/reference/CLI_REFERENCE.md) - All 20 commands | -| **Configure** | [Config Format](docs/reference/CONFIG_FORMAT.md) - JSON specification | -| **Fix issues** | [Troubleshooting](docs/user-guide/06-troubleshooting.md) - Common problems | +| **快速上手** | [快速开始](docs/getting-started/02-quick-start.md) - 3 条命令构建首个技能 | +| **理解概念** | [核心概念](docs/user-guide/01-core-concepts.md) - 工作原理 | +| **抓取来源** | [抓取指南](docs/user-guide/02-scraping.md) - 所有来源类型 | +| **增强技能** | [增强指南](docs/user-guide/03-enhancement.md) - AI 增强 | +| **导出技能** | [打包指南](docs/user-guide/04-packaging.md) - 平台导出 | +| **查询命令** | [CLI 参考](docs/reference/CLI_REFERENCE.md) - 全部 20 条命令 | +| **进行配置** | [配置格式](docs/reference/CONFIG_FORMAT.md) - JSON 规范 | +| **解决问题** | [故障排除](docs/user-guide/06-troubleshooting.md) - 常见问题 | -**Complete documentation:** [docs/README.md](docs/README.md) +**完整文档：** [docs/README.md](docs/README.md) -Instead of spending days on manual preprocessing, Skill Seekers: +Skill Seekers 通过以下步骤代替数天的手动预处理工作： -1. **Ingests** — docs, GitHub repos, local codebases, PDFs, videos, notebooks, wikis, and 10+ more source types -2. **Analyzes** — deep AST parsing, pattern detection, API extraction -3. **Structures** — categorized reference files with metadata -4. **Enhances** — AI-powered SKILL.md generation (Claude, Gemini, or local) -5. **Exports** — 16 platform-specific formats from one asset +1. **采集** — 文档、GitHub 仓库、本地代码库、PDF、视频、笔记本、Wiki 等 10 种以上来源类型 +2. **分析** — 深度 AST 解析、模式检测、API 提取 +3. **结构化** — 带元数据的分类参考文件 +4. **增强** — AI 驱动的 SKILL.md 生成（Claude、Gemini 或本地） +5. **导出** — 从一个资产导出到 16 种平台专用格式 -## Why Use This? +## 为什么使用 Skill Seekers？ -### For AI Skill Builders (Claude, Gemini, OpenAI) +### 面向 AI 技能构建者（Claude、Gemini、OpenAI） -- 🎯 **Production-grade Skills** — 500+ line SKILL.md files with code examples, patterns, and guides -- 🔄 **Enhancement Workflows** — Apply `security-focus`, `architecture-comprehensive`, or custom YAML presets -- 🎮 **Any Domain** — Game engines (Godot, Unity), frameworks (React, Django), internal tools -- 🔧 **Teams** — Combine internal docs + code into a single source of truth -- 📚 **Quality** — AI-enhanced with examples, quick reference, and navigation guidance +- 🎯 **生产级技能** — 500+ 行的 SKILL.md 文件，包含代码示例、模式和指南 +- 🔄 **增强工作流** — 应用 `security-focus`、`architecture-comprehensive` 或自定义 YAML 预设 +- 🎮 **任意领域** — 游戏引擎（Godot、Unity）、框架（React、Django）、内部工具 +- 🔧 **团队协作** — 将内部文档 + 代码整合为单一事实来源 +- 📚 **高质量** — AI 增强，包含示例、快速参考和导航指南 -### For RAG Builders & AI Engineers +### 面向 RAG 构建者和 AI 工程师 -- 🤖 **RAG-ready data** — Pre-chunked LangChain `Documents`, LlamaIndex `TextNodes`, Haystack `Documents` -- 🚀 **99% faster** — Days of preprocessing → 15–45 minutes -- 📊 **Smart metadata** — Categories, sources, types → better retrieval accuracy -- 🔄 **Multi-source** — Combine docs + GitHub + PDFs + videos in one pipeline -- 🌐 **Platform-agnostic** — Export to any vector DB or framework without re-scraping +- 🤖 **RAG 就绪数据** — 预分块的 LangChain `Documents`、LlamaIndex `TextNodes`、Haystack `Documents` +- 🚀 **快 99%** — 数天的预处理 → 15–45 分钟 +- 📊 **智能元数据** — 类别、来源、类型 → 更高的检索精度 +- 🔄 **多源支持** — 在一个流水线中合并文档 + GitHub + PDF + 视频 +- 🌐 **平台无关** — 无需重新抓取即可导出到任意向量数据库或框架 -### For AI Coding Assistant Users +### 面向 AI 编程助手用户 -- 💻 **Cursor / Windsurf / Cline** — Generate `.cursorrules` / `.windsurfrules` / `.clinerules` automatically -- 🎯 **Persistent context** — AI "knows" your frameworks without repeated prompting -- 📚 **Always current** — Update context in minutes when docs change +- 💻 **Cursor / Windsurf / Cline** — 自动生成 `.cursorrules` / `.windsurfrules` / `.clinerules` +- 🎯 **持久上下文** — AI "了解"您的框架，无需重复提示 +- 📚 **始终最新** — 文档更新时可在几分钟内更新上下文 -## Key Features +## 核心功能 -### 🌐 Documentation Scraping -- ✅ **Smart SPA Discovery** - Three-layer discovery for JavaScript SPA sites (sitemap.xml → llms.txt → headless browser rendering) -- ✅ **llms.txt Support** - Automatically detects and uses LLM-ready documentation files (10x faster) -- ✅ **Universal Scraper** - Works with ANY documentation website -- ✅ **Smart Categorization** - Automatically organizes content by topic -- ✅ **Code Language Detection** - Recognizes Python, JavaScript, C++, GDScript, etc. -- ✅ **24+ Ready-to-Use Presets** - Godot, React, Vue, Django, FastAPI, and more +### 🌐 文档抓取 +- ✅ **智能 SPA 发现** - 针对 JavaScript SPA 网站的三层发现机制（sitemap.xml → llms.txt → 无头浏览器渲染） +- ✅ **llms.txt 支持** - 自动检测并使用 LLM 就绪文档文件（快 10 倍） +- ✅ **通用抓取器** - 适用于任意文档网站 +- ✅ **智能分类** - 按主题自动组织内容 +- ✅ **代码语言检测** - 识别 Python、JavaScript、C++、GDScript 等 +- ✅ **24+ 即用预设** - Godot、React、Vue、Django、FastAPI 等 -### 📄 PDF Support -- ✅ **Basic PDF Extraction** - Extract text, code, and images from PDF files -- ✅ **OCR for Scanned PDFs** - Extract text from scanned documents -- ✅ **Password-Protected PDFs** - Handle encrypted PDFs -- ✅ **Table Extraction** - Extract complex tables from PDFs -- ✅ **Parallel Processing** - 3x faster for large PDFs -- ✅ **Intelligent Caching** - 50% faster on re-runs +### 📄 PDF 支持 +- ✅ **基础 PDF 提取** - 从 PDF 提取文本、代码和图片 +- ✅ **扫描件 OCR** - 从扫描文档提取文本 +- ✅ **密码保护 PDF** - 处理加密 PDF +- ✅ **表格提取** - 提取复杂表格 +- ✅ **并行处理** - 大型 PDF 快 3 倍 +- ✅ **智能缓存** - 重复运行快 50% -### 🎬 Video Extraction -- ✅ **YouTube & Local Videos** - Extract transcripts, on-screen code, and structured knowledge from videos -- ✅ **Visual Frame Analysis** - OCR extraction from code editors, terminals, slides, and diagrams -- ✅ **GPU Auto-Detection** - Automatically installs correct PyTorch build (CUDA/ROCm/MPS/CPU) -- ✅ **AI Enhancement** - Two-pass: clean OCR artifacts + generate polished SKILL.md -- ✅ **Time Clipping** - Extract specific sections with `--start-time` and `--end-time` -- ✅ **Playlist Support** - Batch process all videos in a YouTube playlist -- ✅ **Vision API Fallback** - Use Claude Vision for low-confidence OCR frames +### 🎬 视频提取 +- ✅ **YouTube 和本地视频** - 从视频提取字幕、屏幕代码和结构化知识 +- ✅ **视觉帧分析** - OCR 提取代码编辑器、终端、幻灯片和图表内容 +- ✅ **GPU 自动检测** - 自动安装正确的 PyTorch 版本（CUDA/ROCm/MPS/CPU） +- ✅ **AI 增强** - 两阶段增强：清理 OCR + 生成精美 SKILL.md +- ✅ **时间裁剪** - 提取视频的特定片段（`--start-time`、`--end-time`） +- ✅ **播放列表支持** - 批量处理 YouTube 播放列表中的所有视频 +- ✅ **Vision API 回退** - 对低置信度 OCR 帧使用 Claude Vision -### 🐙 GitHub Repository Analysis -- ✅ **Deep Code Analysis** - AST parsing for Python, JavaScript, TypeScript, Java, C++, Go -- ✅ **API Extraction** - Functions, classes, methods with parameters and types -- ✅ **Repository Metadata** - README, file tree, language breakdown, stars/forks -- ✅ **GitHub Issues & PRs** - Fetch open/closed issues with labels and milestones -- ✅ **CHANGELOG & Releases** - Automatically extract version history -- ✅ **Conflict Detection** - Compare documented APIs vs actual code implementation -- ✅ **MCP Integration** - Natural language: "Scrape GitHub repo facebook/react" +### 🐙 GitHub 仓库分析 +- ✅ **深度代码分析** - 支持 Python、JavaScript、TypeScript、Java、C++、Go 的 AST 解析 +- ✅ **API 提取** - 函数、类、方法及参数和类型 +- ✅ **仓库元数据** - README、文件树、语言统计、星标/分支数 +- ✅ **GitHub Issues 和 PR** - 获取带标签和里程碑的开放/已关闭 issues +- ✅ **CHANGELOG 和发布** - 自动提取版本历史 +- ✅ **冲突检测** - 对比文档化 API 与实际代码实现 +- ✅ **MCP 集成** - 自然语言："抓取 GitHub 仓库 facebook/react" -### 🔄 Unified Multi-Source Scraping -- ✅ **Combine Multiple Sources** - Mix documentation + GitHub + PDF in one skill -- ✅ **Conflict Detection** - Automatically finds discrepancies between docs and code -- ✅ **Intelligent Merging** - Rule-based or AI-powered conflict resolution -- ✅ **Transparent Reporting** - Side-by-side comparison with ⚠️ warnings -- ✅ **Documentation Gap Analysis** - Identifies outdated docs and undocumented features -- ✅ **Single Source of Truth** - One skill showing both intent (docs) and reality (code) -- ✅ **Backward Compatible** - Legacy single-source configs still work +### 🔄 统一多源抓取 +- ✅ **合并多个来源** - 在一个技能中混合文档 + GitHub + PDF +- ✅ **冲突检测** - 自动发现文档与代码之间的差异 +- ✅ **智能合并** - 基于规则或 AI 驱动的冲突解决 +- ✅ **透明报告** - 带 ⚠️ 警告的并排对比 +- ✅ **文档差距分析** - 识别过时文档和未文档化功能 +- ✅ **单一事实来源** - 一个技能同时展示意图（文档）和现实（代码） +- ✅ **向后兼容** - 遗留单源配置继续有效 -### 🤖 Multi-LLM Platform Support -- ✅ **12 LLM Platforms** - Claude AI, Google Gemini, OpenAI ChatGPT, MiniMax AI, Generic Markdown, OpenCode, Kimi (Moonshot AI), DeepSeek AI, Qwen (Alibaba), OpenRouter, Together AI, Fireworks AI -- ✅ **Universal Scraping** - Same documentation works for all platforms -- ✅ **Platform-Specific Packaging** - Optimized formats for each LLM -- ✅ **One-Command Export** - `--target` flag selects platform -- ✅ **Optional Dependencies** - Install only what you need -- ✅ **100% Backward Compatible** - Existing Claude workflows unchanged +### 🤖 多 LLM 平台支持 +- ✅ **12 个 LLM 平台** - Claude AI、Google Gemini、OpenAI ChatGPT、MiniMax AI、通用 Markdown、OpenCode、Kimi（月之暗面）、DeepSeek AI、Qwen（阿里巴巴）、OpenRouter、Together AI、Fireworks AI +- ✅ **通用抓取** - 相同文档适用于所有平台 +- ✅ **平台专用打包** - 针对每个 LLM 的优化格式 +- ✅ **一键导出** - `--target` 标志选择平台 +- ✅ **可选依赖** - 仅安装所需内容 +- ✅ **100% 向后兼容** - 现有 Claude 工作流无需更改 -| Platform | Format | Upload | Enhancement | API Key | Custom Endpoint | -|----------|--------|--------|-------------|---------|-----------------| -| **Claude AI** | ZIP + YAML | ✅ Auto | ✅ Yes | ANTHROPIC_API_KEY | ANTHROPIC_BASE_URL | -| **Google Gemini** | tar.gz | ✅ Auto | ✅ Yes | GOOGLE_API_KEY | - | -| **OpenAI ChatGPT** | ZIP + Vector Store | ✅ Auto | ✅ Yes | OPENAI_API_KEY | - | -| **MiniMax AI** | ZIP + Knowledge Files | ✅ Auto | ✅ Yes | MINIMAX_API_KEY | - | -| **Generic Markdown** | ZIP | ❌ Manual | ❌ No | - | - | +| 平台 | 格式 | 上传 | 增强 | API Key | 自定义端点 | +|------|------|------|------|---------|-----------| +| **Claude AI** | ZIP + YAML | ✅ 自动 | ✅ 是 | ANTHROPIC_API_KEY | ANTHROPIC_BASE_URL | +| **Google Gemini** | tar.gz | ✅ 自动 | ✅ 是 | GOOGLE_API_KEY | - | +| **OpenAI ChatGPT** | ZIP + Vector Store | ✅ 自动 | ✅ 是 | OPENAI_API_KEY | - | +| **MiniMax AI** | ZIP + Knowledge Files | ✅ 自动 | ✅ 是 | MINIMAX_API_KEY | - | +| **通用 Markdown** | ZIP | ❌ 手动 | ❌ 否 | - | - | ```bash -# Claude (default - no changes needed!) +# Claude（默认 - 无需更改！） skill-seekers package output/react/ skill-seekers upload react.zip @@ -335,40 +342,40 @@ pip install skill-seekers[minimax] skill-seekers package output/react/ --target minimax skill-seekers upload react-minimax.zip --target minimax -# Generic Markdown (universal export) +# 通用 Markdown（通用导出） skill-seekers package output/react/ --target markdown -# Use the markdown files directly in any LLM +# Markdown 文件可直接用于任意 LLM ```
-🔧 Use your own AI provider (OpenAI-compatible endpoints + subscriptions, no Anthropic credits needed) +🔧 使用您自己的 AI 提供商（OpenAI 兼容端点 + 订阅计划，无需 Anthropic 额度） -The optional AI **enhancement** step (used by `create`, `scan`, and `enhance`) does **not** require an Anthropic key. You have three ways to power it: +可选的 AI **增强**步骤（由 `create`、`scan` 和 `enhance` 使用）**不需要** Anthropic 密钥。您有三种方式为其供能： -**1. Use a subscription you already pay for — no API credits at all (LOCAL agent mode)** +**1. 使用您已付费的订阅 — 完全无需 API 额度（LOCAL 代理模式）** -Skill Seekers can shell out to a coding-agent CLI you're already logged into, so enhancement runs on your existing plan instead of metered API tokens: +Skill Seekers 可以调用您已登录的编程代理 CLI，因此增强会使用您现有的订阅计划而非按量计费的 API token： ```bash -skill-seekers create --agent codex # OpenAI Codex CLI → your ChatGPT Plus -skill-seekers create --agent claude # Claude Code → your Claude Pro/Max +skill-seekers create --agent codex # OpenAI Codex CLI → 您的 ChatGPT Plus +skill-seekers create --agent claude # Claude Code → 您的 Claude Pro/Max ``` -Supported agents: `claude`, `codex`, `copilot`, `opencode`, `kimi`, and `custom` -(pair `--agent custom` with `--agent-cmd " ..."` to drive any other tool). +支持的代理：`claude`、`codex`、`copilot`、`opencode`、`kimi` 和 `custom` +（将 `--agent custom` 与 `--agent-cmd " ..."` 组合可驱动任意其他工具）。 -**2. Any OpenAI-compatible provider (OpenRouter, Groq, Cerebras, Mistral, NVIDIA NIM, …)** +**2. 任意 OpenAI 兼容提供商（OpenRouter、Groq、Cerebras、Mistral、NVIDIA NIM 等）** -All of these expose an OpenAI-compatible `/v1` endpoint. Point Skill Seekers at one with three env vars — it detects `OPENAI_API_KEY`, and the OpenAI SDK honors `OPENAI_BASE_URL` automatically: +这些提供商都暴露 OpenAI 兼容的 `/v1` 端点。只需三个环境变量即可让 Skill Seekers 指向其中之一——它会检测 `OPENAI_API_KEY`，而 OpenAI SDK 会自动识别 `OPENAI_BASE_URL`： ```bash export OPENAI_API_KEY="" -export OPENAI_BASE_URL="https://openrouter.ai/api/v1" # provider endpoint (see table) -export OPENAI_MODEL="" # required — default gpt-4o won't exist elsewhere +export OPENAI_BASE_URL="https://openrouter.ai/api/v1" # 提供商端点（见下表） +export OPENAI_MODEL="" # 必填 — 默认的 gpt-4o 在其他提供商处不存在 skill-seekers create ``` -| Provider | `OPENAI_BASE_URL` | +| 提供商 | `OPENAI_BASE_URL` | |--------------|--------------------------------------------| | OpenRouter | `https://openrouter.ai/api/v1` | | Groq | `https://api.groq.com/openai/v1` | @@ -376,542 +383,542 @@ skill-seekers create | Mistral | `https://api.mistral.ai/v1` | | NVIDIA NIM | `https://integrate.api.nvidia.com/v1` | -> Provider detection picks the **first** API-key env var it finds (`ANTHROPIC_API_KEY` → `GOOGLE_API_KEY` → `OPENAI_API_KEY` → `MOONSHOT_API_KEY`). Set `SKILL_SEEKER_PROVIDER` to force a specific provider, or make sure the higher-priority keys are unset. +> 提供商检测会选取**第一个**找到的 API 密钥环境变量（`ANTHROPIC_API_KEY` → `GOOGLE_API_KEY` → `OPENAI_API_KEY` → `MOONSHOT_API_KEY`）。设置 `SKILL_SEEKER_PROVIDER` 可强制指定提供商，或确保优先级更高的密钥未被设置。 -**3. Claude-compatible endpoints (e.g. GLM, proxies)** +**3. Claude 兼容端点（如 GLM、代理服务）** ```bash export ANTHROPIC_API_KEY="your-key" export ANTHROPIC_BASE_URL="https://your-claude-compatible-endpoint/v1" ``` -Google Gemini (`GOOGLE_API_KEY`) and Kimi/Moonshot (`MOONSHOT_API_KEY`) are also supported natively. See **[Environment Variables Reference](docs/reference/ENVIRONMENT_VARIABLES.md#llm-provider-selection)** for the full list, including per-provider model overrides. +Google Gemini（`GOOGLE_API_KEY`）和 Kimi/月之暗面（`MOONSHOT_API_KEY`）也获得原生支持。完整列表（包括每个提供商的模型覆盖设置）请参阅 **[环境变量参考](docs/reference/ENVIRONMENT_VARIABLES.md#llm-provider-selection)**。
-**Installation:** +**安装：** ```bash -# Install with Gemini support +# 安装 Gemini 支持 pip install skill-seekers[gemini] -# Install with OpenAI support +# 安装 OpenAI 支持 pip install skill-seekers[openai] -# Install with MiniMax support +# 安装 MiniMax 支持 pip install skill-seekers[minimax] -# Install with all LLM platforms +# 安装所有 LLM 平台 pip install skill-seekers[all-llms] ``` -### 🔗 RAG Framework Integrations +### 🔗 RAG 框架集成 -- ✅ **LangChain Documents** - Direct export to `Document` format with `page_content` + metadata - - Perfect for: QA chains, retrievers, vector stores, agents - - Example: [LangChain RAG Pipeline](examples/langchain-rag-pipeline/) - - Guide: [LangChain Integration](docs/integrations/LANGCHAIN.md) +- ✅ **LangChain Documents** - 直接导出为 `Document` 格式，包含 `page_content` + 元数据 + - 适用于：QA 链、检索器、向量存储、智能体 + - 示例：[LangChain RAG 流水线](examples/langchain-rag-pipeline/) + - 指南：[LangChain 集成](docs/integrations/LANGCHAIN.md) -- ✅ **LlamaIndex TextNodes** - Export to `TextNode` format with unique IDs + embeddings - - Perfect for: Query engines, chat engines, storage context - - Example: [LlamaIndex Query Engine](examples/llama-index-query-engine/) - - Guide: [LlamaIndex Integration](docs/integrations/LLAMA_INDEX.md) +- ✅ **LlamaIndex TextNodes** - 导出为带唯一 ID + 嵌入的 `TextNode` 格式 + - 适用于：查询引擎、对话引擎、存储上下文 + - 示例：[LlamaIndex 查询引擎](examples/llama-index-query-engine/) + - 指南：[LlamaIndex 集成](docs/integrations/LLAMA_INDEX.md) -- ✅ **Pinecone-Ready Format** - Optimized for vector database upsert - - Perfect for: Production vector search, semantic search, hybrid search - - Example: [Pinecone Upsert](examples/pinecone-upsert/) - - Guide: [Pinecone Integration](docs/integrations/PINECONE.md) +- ✅ **Pinecone 就绪格式** - 针对向量数据库上传进行优化 + - 适用于：生产级向量搜索、语义搜索、混合搜索 + - 示例：[Pinecone 上传](examples/pinecone-upsert/) + - 指南：[Pinecone 集成](docs/integrations/PINECONE.md) -**Quick Export:** +**快速导出：** ```bash -# LangChain Documents (JSON) +# LangChain Documents（JSON） skill-seekers package output/django --target langchain # → output/django-langchain.json -# LlamaIndex TextNodes (JSON) +# LlamaIndex TextNodes（JSON） skill-seekers package output/django --target llama-index # → output/django-llama-index.json -# Markdown (Universal) +# Markdown（通用） skill-seekers package output/django --target markdown # → output/django-markdown/SKILL.md + references/ ``` -**Complete RAG Pipeline Guide:** [RAG Pipelines Documentation](docs/integrations/RAG_PIPELINES.md) +**完整 RAG 流水线指南：** [RAG 流水线文档](docs/integrations/RAG_PIPELINES.md) --- -### 🧠 AI Coding Assistant Integrations +### 🧠 AI 编程助手集成 -Transform any framework documentation into expert coding context for 4+ AI assistants: +将任意框架文档转换为 4+ 种 AI 助手的专家编程上下文： -- ✅ **Cursor IDE** - Generate `.cursorrules` for AI-powered code suggestions - - Perfect for: Framework-specific code generation, consistent patterns - - Works with: Cursor IDE (VS Code fork) - - Guide: [Cursor Integration](docs/integrations/CURSOR.md) - - Example: [Cursor React Skill](examples/cursor-react-skill/) +- ✅ **Cursor IDE** - 为 AI 驱动的代码建议生成 `.cursorrules` + - 适用于：框架专用代码生成、一致的编码模式 + - 兼容工具：Cursor IDE（VS Code 分支） + - 指南：[Cursor 集成](docs/integrations/CURSOR.md) + - 示例：[Cursor React 技能](examples/cursor-react-skill/) -- ✅ **Windsurf** - Customize Windsurf's AI assistant context with `.windsurfrules` - - Perfect for: IDE-native AI assistance, flow-based coding - - Works with: Windsurf IDE by Codeium - - Guide: [Windsurf Integration](docs/integrations/WINDSURF.md) - - Example: [Windsurf FastAPI Context](examples/windsurf-fastapi-context/) +- ✅ **Windsurf** - 使用 `.windsurfrules` 自定义 Windsurf AI 助手上下文 + - 适用于：IDE 原生 AI 辅助、流式编程 + - 兼容工具：Codeium 出品的 Windsurf IDE + - 指南：[Windsurf 集成](docs/integrations/WINDSURF.md) + - 示例：[Windsurf FastAPI 上下文](examples/windsurf-fastapi-context/) -- ✅ **Cline (VS Code)** - System prompts + MCP for VS Code agent - - Perfect for: Agentic code generation in VS Code - - Works with: Cline extension for VS Code - - Guide: [Cline Integration](docs/integrations/CLINE.md) - - Example: [Cline Django Assistant](examples/cline-django-assistant/) +- ✅ **Cline（VS Code）** - VS Code 智能体的系统提示 + MCP + - 适用于：VS Code 中的智能代码生成 + - 兼容工具：VS Code 的 Cline 扩展 + - 指南：[Cline 集成](docs/integrations/CLINE.md) + - 示例：[Cline Django 助手](examples/cline-django-assistant/) -- ✅ **Continue.dev** - Context servers for IDE-agnostic AI - - Perfect for: Multi-IDE environments (VS Code, JetBrains, Vim), custom LLM providers - - Works with: Any IDE with Continue.dev plugin - - Guide: [Continue Integration](docs/integrations/CONTINUE_DEV.md) - - Example: [Continue Universal Context](examples/continue-dev-universal/) +- ✅ **Continue.dev** - 与 IDE 无关的 AI 上下文服务器 + - 适用于：多 IDE 环境（VS Code、JetBrains、Vim），自定义 LLM 提供商 + - 兼容工具：任何带有 Continue.dev 插件的 IDE + - 指南：[Continue 集成](docs/integrations/CONTINUE_DEV.md) + - 示例：[Continue 通用上下文](examples/continue-dev-universal/) -**Quick Export for AI Coding Tools:** +**快速导出（适用于 AI 编程工具）：** ```bash -# For any AI coding assistant (Cursor, Windsurf, Cline, Continue.dev) +# 适用于任意 AI 编程助手（Cursor、Windsurf、Cline、Continue.dev） skill-seekers create --config configs/django.json -skill-seekers package output/django --target claude # or --target markdown +skill-seekers package output/django --target claude # 或 --target markdown -# Copy to your project (example for Cursor) +# 复制到项目（以 Cursor 为例） cp output/django-claude/SKILL.md my-project/.cursorrules -# Or for Windsurf +# 或用于 Windsurf cp output/django-claude/SKILL.md my-project/.windsurf/rules/django.md -# Or for Cline +# 或用于 Cline cp output/django-claude/SKILL.md my-project/.clinerules -# Or for Continue.dev (HTTP server) +# 或用于 Continue.dev（HTTP 服务器） python examples/continue-dev-universal/context_server.py -# Configure in ~/.continue/config.json +# 在 ~/.continue/config.json 中配置 ``` -**Integration Hub:** [All AI System Integrations](docs/integrations/INTEGRATIONS.md) +**集成中心：** [所有 AI 系统集成](docs/integrations/INTEGRATIONS.md) --- -### 🌊 Three-Stream GitHub Architecture -- ✅ **Triple-Stream Analysis** - Split GitHub repos into Code, Docs, and Insights streams -- ✅ **Unified Codebase Analyzer** - Works with GitHub URLs AND local paths -- ✅ **C3.x as Analysis Depth** - Choose 'basic' (1-2 min) or 'c3x' (20-60 min) analysis -- ✅ **Enhanced Router Generation** - GitHub metadata, README quick start, common issues -- ✅ **Issue Integration** - Top problems and solutions from GitHub issues -- ✅ **Smart Routing Keywords** - GitHub labels weighted 2x for better topic detection +### 🌊 三流 GitHub 架构 +- ✅ **三流分析** - 将 GitHub 仓库拆分为代码流、文档流和洞察流 +- ✅ **统一代码库分析器** - 同时适用于 GitHub URL 和本地路径 +- ✅ **C3.x 分析深度** - 选择"basic"（1–2 分钟）或"c3x"（20–60 分钟）分析 +- ✅ **增强路由生成** - GitHub 元数据、README 快速入门、常见问题 +- ✅ **Issue 集成** - 来自 GitHub Issues 的常见问题和解决方案 +- ✅ **智能路由关键词** - GitHub 标签权重加倍，提升主题检测效果 -**Three Streams Explained:** -- **Stream 1: Code** - Deep C3.x analysis (patterns, examples, guides, configs, architecture) -- **Stream 2: Docs** - Repository documentation (README, CONTRIBUTING, docs/*.md) -- **Stream 3: Insights** - Community knowledge (issues, labels, stars, forks) +**三流说明：** +- **流 1：代码** - 深度 C3.x 分析（模式、示例、指南、配置、架构） +- **流 2：文档** - 仓库文档（README、CONTRIBUTING、docs/*.md） +- **流 3：洞察** - 社区知识（Issues、标签、Stars、Forks） ```python from skill_seekers.cli.unified_codebase_analyzer import UnifiedCodebaseAnalyzer -# Analyze GitHub repo with all three streams +# 使用三流分析 GitHub 仓库 analyzer = UnifiedCodebaseAnalyzer() result = analyzer.analyze( source="https://github.com/facebook/react", - depth="c3x", # or "basic" for fast analysis + depth="c3x", # 或 "basic" 快速分析 fetch_github_metadata=True ) -# Access code stream (C3.x analysis) -print(f"Design patterns: {len(result.code_analysis['c3_1_patterns'])}") -print(f"Test examples: {result.code_analysis['c3_2_examples_count']}") +# 访问代码流（C3.x 分析） +print(f"设计模式: {len(result.code_analysis['c3_1_patterns'])}") +print(f"测试示例: {result.code_analysis['c3_2_examples_count']}") -# Access docs stream (repository docs) +# 访问文档流（仓库文档） print(f"README: {result.github_docs['readme'][:100]}") -# Access insights stream (GitHub metadata) +# 访问洞察流（GitHub 元数据） print(f"Stars: {result.github_insights['metadata']['stars']}") -print(f"Common issues: {len(result.github_insights['common_problems'])}") +print(f"常见问题: {len(result.github_insights['common_problems'])}") ``` -**See complete documentation**: [Three-Stream Implementation Summary](docs/archive/historical/IMPLEMENTATION_SUMMARY_THREE_STREAM.md) +**完整文档**：[三流实现总结](docs/archive/historical/IMPLEMENTATION_SUMMARY_THREE_STREAM.md) -### 🔐 Smart Rate Limit Management & Configuration -- ✅ **Multi-Token Configuration System** - Manage multiple GitHub accounts (personal, work, OSS) - - Secure config storage at `~/.config/skill-seekers/config.json` (600 permissions) - - Per-profile rate limit strategies: `prompt`, `wait`, `switch`, `fail` - - Configurable timeout per profile (default: 30 min, prevents indefinite waits) - - Smart fallback chain: CLI arg → Env var → Config file → Prompt - - API key management for Claude, Gemini, OpenAI -- ✅ **Interactive Configuration Wizard** - Beautiful terminal UI for easy setup - - Browser integration for token creation (auto-opens GitHub, etc.) - - Token validation and connection testing - - Visual status display with color coding -- ✅ **Intelligent Rate Limit Handler** - No more indefinite waits! - - Upfront warning about rate limits (60/hour vs 5000/hour) - - Real-time detection from GitHub API responses - - Live countdown timers with progress - - Automatic profile switching when rate limited - - Four strategies: prompt (ask), wait (countdown), switch (try another), fail (abort) -- ✅ **Resume Capability** - Continue interrupted jobs - - Auto-save progress at configurable intervals (default: 60 sec) - - List all resumable jobs with progress details - - Auto-cleanup of old jobs (default: 7 days) -- ✅ **CI/CD Support** - Non-interactive mode for automation - - `--non-interactive` flag fails fast without prompts - - `--profile` flag to select specific GitHub account - - Clear error messages for pipeline logs +### 🔐 智能速率限制管理与配置 +- ✅ **多 Token 配置系统** - 管理多个 GitHub 账号（个人、工作、开源） + - 安全配置存储在 `~/.config/skill-seekers/config.json`（权限 600） + - 每个配置文件的速率限制策略：`prompt`、`wait`、`switch`、`fail` + - 每个配置文件可设置超时（默认：30 分钟，防止无限等待） + - 智能回退链：CLI 参数 → 环境变量 → 配置文件 → 提示 + - Claude、Gemini、OpenAI 的 API Key 管理 +- ✅ **交互式配置向导** - 美观的终端 UI，轻松设置 + - 浏览器集成辅助创建 token（自动打开 GitHub 等） + - Token 验证和连接测试 + - 带颜色编码的可视化状态显示 +- ✅ **智能速率限制处理器** - 不再无限等待！ + - 关于速率限制的预先警告（60 次/小时 vs 5000 次/小时） + - 从 GitHub API 响应中实时检测 + - 带进度的实时倒计时 + - 速率受限时自动切换配置文件 + - 四种策略：prompt（询问）、wait（倒计时）、switch（切换）、fail（中止） +- ✅ **断点续传** - 继续中断的任务 + - 按可配置间隔自动保存进度（默认：60 秒） + - 列出所有可恢复任务及其进度详情 + - 自动清理旧任务（默认：7 天） +- ✅ **CI/CD 支持** - 非交互式自动化模式 + - `--non-interactive` 标志快速失败、无提示 + - `--profile` 标志选择特定 GitHub 账号 + - 适用于流水线日志的清晰错误消息 -**Quick Setup:** +**快速设置：** ```bash -# One-time configuration (5 minutes) +# 一次性配置（5 分钟） skill-seekers config --github -# Use specific profile for private repos +# 为私有仓库使用特定配置文件 skill-seekers create mycompany/private-repo --profile work -# CI/CD mode (fail fast, no prompts) +# CI/CD 模式（快速失败，无提示） skill-seekers create owner/repo --non-interactive -# Resume interrupted job +# 恢复中断的任务 skill-seekers resume --list skill-seekers resume github_react_20260117_143022 ``` -**Rate Limit Strategies Explained:** -- **prompt** (default) - Ask what to do when rate limited (wait, switch, setup token, cancel) -- **wait** - Automatically wait with countdown timer (respects timeout) -- **switch** - Automatically try next available profile (for multi-account setups) -- **fail** - Fail immediately with clear error (perfect for CI/CD) +**速率限制策略说明：** +- **prompt**（默认）- 速率受限时询问操作（等待、切换、设置 token、取消） +- **wait** - 带倒计时自动等待（遵守超时设置） +- **switch** - 自动尝试下一个可用配置文件（适用于多账号场景） +- **fail** - 立即失败并给出清晰错误（适合 CI/CD） -### 🎯 Bootstrap Skill - Self-Hosting +### 🎯 Bootstrap 技能 - 自托管 -Generate skill-seekers as a skill to use within your AI agent (Claude Code, Kimi, Codex, etc.): +将 skill-seekers 自身生成为技能，在您的 AI 代理（Claude Code、Kimi、Codex 等）中使用： ```bash -# Generate the skill +# 生成技能 ./scripts/bootstrap_skill.sh -# Install to Claude Code +# 安装到 Claude Code cp -r output/skill-seekers ~/.claude/skills/ ``` -**What you get:** -- ✅ **Complete skill documentation** - All CLI commands and usage patterns -- ✅ **CLI command reference** - Every tool and its options documented -- ✅ **Quick start examples** - Common workflows and best practices -- ✅ **Auto-generated API docs** - Code analysis, patterns, and examples +**您将获得：** +- ✅ **完整的技能文档** - 所有 CLI 命令和使用模式 +- ✅ **CLI 命令参考** - 每个工具及其选项的文档 +- ✅ **快速入门示例** - 常见工作流和最佳实践 +- ✅ **自动生成的 API 文档** - 代码分析、模式和示例 -### 🔐 Private Config Repositories -- ✅ **Git-Based Config Sources** - Fetch configs from private/team git repositories -- ✅ **Multi-Source Management** - Register unlimited GitHub, GitLab, Bitbucket repos -- ✅ **Team Collaboration** - Share custom configs across 3-5 person teams -- ✅ **Enterprise Support** - Scale to 500+ developers with priority-based resolution -- ✅ **Secure Authentication** - Environment variable tokens (GITHUB_TOKEN, GITLAB_TOKEN) -- ✅ **Intelligent Caching** - Clone once, pull updates automatically -- ✅ **Offline Mode** - Work with cached configs when offline +### 🔐 私有配置仓库 +- ✅ **基于 Git 的配置源** - 从私有/团队 Git 仓库获取配置 +- ✅ **多源管理** - 注册无限数量的 GitHub、GitLab、Bitbucket 仓库 +- ✅ **团队协作** - 在 3–5 人团队间共享自定义配置 +- ✅ **企业支持** - 通过基于优先级的解析扩展到 500+ 开发者 +- ✅ **安全认证** - 环境变量 token（GITHUB_TOKEN、GITLAB_TOKEN） +- ✅ **智能缓存** - 克隆一次，自动拉取更新 +- ✅ **离线模式** - 离线时使用缓存的配置工作 -### 🤖 Codebase Analysis (C3.x) +### 🤖 代码库分析（C3.x） -**C3.4: Configuration Pattern Extraction with AI Enhancement** -- ✅ **9 Config Formats** - JSON, YAML, TOML, ENV, INI, Python, JavaScript, Dockerfile, Docker Compose -- ✅ **7 Pattern Types** - Database, API, logging, cache, email, auth, server configurations -- ✅ **AI Enhancement** - Optional dual-mode AI analysis (API + LOCAL) - - Explains what each config does - - Suggests best practices and improvements - - **Security analysis** - Finds hardcoded secrets, exposed credentials -- ✅ **Auto-Documentation** - Generates JSON + Markdown documentation of all configs -- ✅ **MCP Integration** - `extract_config_patterns` tool with enhancement support +**C3.4：配置模式提取（含 AI 增强）** +- ✅ **9 种配置格式** - JSON、YAML、TOML、ENV、INI、Python、JavaScript、Dockerfile、Docker Compose +- ✅ **7 种模式类型** - 数据库、API、日志、缓存、邮件、认证、服务器配置 +- ✅ **AI 增强** - 可选双模式 AI 分析（API + LOCAL） + - 解释每项配置的作用 + - 建议最佳实践和改进方案 + - **安全分析** - 发现硬编码的密钥和暴露的凭证 +- ✅ **自动文档生成** - 为所有配置生成 JSON + Markdown 文档 +- ✅ **MCP 集成** - 支持增强的 `extract_config_patterns` 工具 -**C3.3: AI-Enhanced How-To Guides** -- ✅ **Comprehensive AI Enhancement** - Transforms basic guides into professional tutorials -- ✅ **5 Automatic Improvements** - Step descriptions, troubleshooting, prerequisites, next steps, use cases -- ✅ **Dual-Mode Support** - API mode (Claude API) or LOCAL mode (Claude Code CLI) -- ✅ **No API Costs with LOCAL Mode** - FREE enhancement using your Claude Code Max plan -- ✅ **Quality Transformation** - 75-line templates → 500+ line comprehensive guides +**C3.3：AI 增强操作指南** +- ✅ **全面 AI 增强** - 将基础指南转换为专业教程 +- ✅ **5 项自动改进** - 步骤说明、故障排除、前提条件、后续步骤、使用场景 +- ✅ **双模式支持** - API 模式（Claude API）或 LOCAL 模式（Claude Code CLI） +- ✅ **LOCAL 模式零成本** - 使用您的 Claude Code Max 计划免费增强 +- ✅ **质量蜕变** - 75 行模板 → 500+ 行的完整指南 -**Usage:** +**使用方法：** ```bash -# Quick analysis (1-2 min, basic features only) +# 快速分析（1–2 分钟，仅基础功能） skill-seekers scan tests/ --quick -# Comprehensive analysis with AI (20-60 min, all features) +# 全面分析（含 AI，20–60 分钟） skill-seekers scan tests/ --comprehensive -# With AI enhancement +# 含 AI 增强 skill-seekers scan tests/ --enhance ``` -**Full Documentation:** [docs/features/HOW_TO_GUIDES.md](docs/features/HOW_TO_GUIDES.md#ai-enhancement-new) +**完整文档：** [docs/features/HOW_TO_GUIDES.md](docs/features/HOW_TO_GUIDES.md#ai-enhancement-new) -### 🔄 Enhancement Workflow Presets +### 🔄 增强工作流预设 -Reusable YAML-defined enhancement pipelines that control how AI transforms your raw documentation into a polished skill. +可重用的 YAML 定义增强流水线，控制 AI 如何将原始文档转换为精心打磨的技能。 -- ✅ **5 Bundled Presets** — `default`, `minimal`, `security-focus`, `architecture-comprehensive`, `api-documentation` -- ✅ **User-Defined Presets** — add custom workflows to `~/.config/skill-seekers/workflows/` -- ✅ **Multiple Workflows** — chain two or more workflows in one command -- ✅ **Fully Managed CLI** — list, inspect, copy, add, remove, and validate workflows +- ✅ **5 个内置预设** — `default`、`minimal`、`security-focus`、`architecture-comprehensive`、`api-documentation` +- ✅ **用户自定义预设** — 将自定义工作流添加到 `~/.config/skill-seekers/workflows/` +- ✅ **多工作流链式** — 在一条命令中链式使用两个或更多工作流 +- ✅ **完整 CLI 管理** — 列出、查看、复制、添加、删除和验证工作流 ```bash -# Apply a single workflow +# 应用单个工作流 skill-seekers create ./my-project --enhance-workflow security-focus -# Chain multiple workflows (applied in order) +# 链式多个工作流（按顺序应用） skill-seekers create ./my-project \ --enhance-workflow security-focus \ --enhance-workflow minimal -# Manage presets -skill-seekers workflows list # List all (bundled + user) -skill-seekers workflows show security-focus # Print YAML content -skill-seekers workflows copy security-focus # Copy to user dir for editing -skill-seekers workflows add ./my-workflow.yaml # Install a custom preset -skill-seekers workflows remove my-workflow # Remove a user preset -skill-seekers workflows validate security-focus # Validate preset structure +# 管理预设 +skill-seekers workflows list # 列出所有（内置 + 用户） +skill-seekers workflows show security-focus # 显示 YAML 内容 +skill-seekers workflows copy security-focus # 复制到用户目录以便编辑 +skill-seekers workflows add ./my-workflow.yaml # 安装自定义预设 +skill-seekers workflows remove my-workflow # 删除用户预设 +skill-seekers workflows validate security-focus # 验证预设结构 -# Copy multiple at once +# 同时复制多个 skill-seekers workflows copy security-focus minimal api-documentation -# Add multiple files at once +# 同时添加多个文件 skill-seekers workflows add ./wf-a.yaml ./wf-b.yaml -# Remove multiple at once +# 同时删除多个 skill-seekers workflows remove my-wf-a my-wf-b ``` -**YAML preset format:** +**YAML 预设格式：** ```yaml name: security-focus -description: "Security-focused review: vulnerabilities, auth, data handling" +description: "安全重点审查：漏洞、认证、数据处理" version: "1.0" stages: - name: vulnerabilities type: custom - prompt: "Review for OWASP top 10 and common security vulnerabilities..." + prompt: "审查 OWASP Top 10 和常见安全漏洞..." - name: auth-review type: custom - prompt: "Examine authentication and authorisation patterns..." + prompt: "检查认证和授权模式..." uses_history: true ``` -### ⚡ Performance & Scale -- ✅ **Async Mode** - 2-3x faster scraping with async/await (use `--async` flag) -- ✅ **Large Documentation Support** - Handle 10K-40K+ page docs with intelligent splitting -- ✅ **Router/Hub Skills** - Intelligent routing to specialized sub-skills -- ✅ **Parallel Scraping** - Process multiple skills simultaneously -- ✅ **Checkpoint/Resume** - Never lose progress on long scrapes -- ✅ **Caching System** - Scrape once, rebuild instantly +### ⚡ 性能与规模 +- ✅ **异步模式** - 使用 async/await 抓取速度快 2–3 倍（使用 `--async` 标志） +- ✅ **大型文档支持** - 通过智能拆分处理 10K–40K+ 页文档 +- ✅ **路由器/Hub 技能** - 智能路由到专用子技能 +- ✅ **并行抓取** - 同时处理多个技能 +- ✅ **检查点/续传** - 长时间抓取永不丢失进度 +- ✅ **缓存系统** - 抓取一次，即时重建 -### 🤖 Agent-Agnostic Skill Generation -- ✅ **Multi-Agent Support** - Generate skills for Claude, Kimi, Codex, Copilot, OpenCode, or any custom agent via `--agent` flag -- ✅ **Custom Agent Commands** - Use `--agent-cmd` to specify a custom agent CLI command for enhancement -- ✅ **Universal Flags** - `--agent` and `--agent-cmd` available on all commands (create, scrape, github, pdf, etc.) +### 🤖 与代理无关的技能生成 +- ✅ **多代理支持** - 通过 `--agent` 标志为 Claude、Kimi、Codex、Copilot、OpenCode 或任意自定义代理生成技能 +- ✅ **自定义代理命令** - 使用 `--agent-cmd` 指定用于增强的自定义代理 CLI 命令 +- ✅ **通用标志** - `--agent` 和 `--agent-cmd` 在所有命令（create、scrape、github、pdf 等）中均可用 -### 📦 Marketplace Pipeline -- ✅ **Publish to Marketplace** - Publish skills to Claude Code plugin marketplace repos -- ✅ **End-to-End Pipeline** - From documentation source to published marketplace entry +### 📦 市场流水线 +- ✅ **发布到市场** - 将技能发布到 Claude Code 插件市场仓库 +- ✅ **端到端流水线** - 从文档来源到已发布的市场条目 -### ✅ Quality Assurance -- ✅ **Fully Tested** - 3,700+ tests with comprehensive coverage +### ✅ 质量保证 +- ✅ **全面测试** - 3,700+ 测试，全面覆盖 --- -## 📦 Installation +## 📦 安装 ```bash -# Basic install (documentation scraping, GitHub analysis, PDF, packaging) +# 基础安装（文档抓取、GitHub 分析、PDF、打包） pip install skill-seekers -# With all LLM platform support +# 包含所有 LLM 平台支持 pip install skill-seekers[all-llms] -# With MCP server +# 包含 MCP 服务器 pip install skill-seekers[mcp] -# Everything +# 全部功能 pip install skill-seekers[all] ``` -**Need help choosing?** Run the setup wizard: +**需要帮助选择？** 运行设置向导： ```bash skill-seekers-setup ``` -### Installation Options +### 安装选项 -| Install | Features | -|---------|----------| -| `pip install skill-seekers` | Scraping, GitHub analysis, PDF, all platforms | -| `pip install skill-seekers[gemini]` | + Google Gemini support | -| `pip install skill-seekers[openai]` | + OpenAI ChatGPT support | -| `pip install skill-seekers[all-llms]` | + All LLM platforms | -| `pip install skill-seekers[mcp]` | + MCP server for Claude Code, Cursor, etc. | -| `pip install skill-seekers[video]` | + YouTube/Vimeo transcript & metadata extraction | -| `pip install skill-seekers[video-full]` | + Whisper transcription & visual frame extraction | -| `pip install skill-seekers[jupyter]` | + Jupyter Notebook support | -| `pip install skill-seekers[pptx]` | + PowerPoint support | -| `pip install skill-seekers[confluence]` | + Confluence wiki support | -| `pip install skill-seekers[notion]` | + Notion pages support | -| `pip install skill-seekers[rss]` | + RSS/Atom feed support | -| `pip install skill-seekers[chat]` | + Slack/Discord chat export support | -| `pip install skill-seekers[asciidoc]` | + AsciiDoc document support | -| `pip install skill-seekers[all]` | Everything enabled | +| 安装命令 | 功能 | +|---------|------| +| `pip install skill-seekers` | 抓取、GitHub 分析、PDF、所有平台 | +| `pip install skill-seekers[gemini]` | + Google Gemini 支持 | +| `pip install skill-seekers[openai]` | + OpenAI ChatGPT 支持 | +| `pip install skill-seekers[all-llms]` | + 所有 LLM 平台 | +| `pip install skill-seekers[mcp]` | + 适用于 Claude Code、Cursor 等的 MCP 服务器 | +| `pip install skill-seekers[video]` | + YouTube/Vimeo 字幕和元数据提取 | +| `pip install skill-seekers[video-full]` | + Whisper 转录和视觉帧提取 | +| `pip install skill-seekers[jupyter]` | + Jupyter 笔记本支持 | +| `pip install skill-seekers[pptx]` | + PowerPoint 支持 | +| `pip install skill-seekers[confluence]` | + Confluence 维基支持 | +| `pip install skill-seekers[notion]` | + Notion 页面支持 | +| `pip install skill-seekers[rss]` | + RSS/Atom 订阅源支持 | +| `pip install skill-seekers[chat]` | + Slack/Discord 聊天记录支持 | +| `pip install skill-seekers[asciidoc]` | + AsciiDoc 文档支持 | +| `pip install skill-seekers[all]` | 全部功能 | -> **Video visual deps (GPU-aware):** After installing `skill-seekers[video-full]`, run -> `skill-seekers create --setup` to auto-detect your GPU and install the correct PyTorch -> variant + easyocr. This is the recommended way to install visual extraction dependencies. +> **视频视觉依赖（GPU 感知）：** 安装 `skill-seekers[video-full]` 后，运行 +> `skill-seekers create --setup` 自动检测您的 GPU 并安装正确的 PyTorch +> 版本 + easyocr。这是安装视觉提取依赖的推荐方式。 --- -## 🚀 One-Command Install Workflow +## 🚀 一键安装工作流 -**The fastest way to go from config to uploaded skill - complete automation:** +**从配置到上传技能的最快方式——全自动化：** ```bash -# Install React skill from official configs (auto-uploads to Claude) +# 从官方配置安装 React 技能（自动上传到 Claude） skill-seekers install --config react -# Install from local config file +# 从本地配置文件安装 skill-seekers install --config configs/custom.json -# Install without uploading (package only) +# 安装但不上传（仅打包） skill-seekers install --config django --no-upload -# Preview workflow without executing +# 预览工作流而不执行 skill-seekers install --config react --dry-run ``` -**Time:** 20-45 minutes total | **Quality:** Production-ready (9/10) | **Cost:** Free +**耗时：** 总计 20–45 分钟 | **质量：** 生产就绪（9/10） | **成本：** 免费 -**Phases executed:** +**执行阶段：** ``` -📥 PHASE 1: Fetch Config (if config name provided) -📖 PHASE 2: Scrape Documentation -✨ PHASE 3: AI Enhancement (MANDATORY - no skip option) -📦 PHASE 4: Package Skill -☁️ PHASE 5: Upload to Claude (optional, requires API key) +📥 阶段 1：获取配置（如果提供配置名称） +📖 阶段 2：抓取文档 +✨ 阶段 3：AI 增强（必选 - 不可跳过） +📦 阶段 4：打包技能 +☁️ 阶段 5：上传到 Claude（可选，需要 API Key） ``` -**Requirements:** -- ANTHROPIC_API_KEY environment variable (for auto-upload) -- Claude Code Max plan (for local AI enhancement), or use `--agent` to select a different AI agent +**要求：** +- ANTHROPIC_API_KEY 环境变量（用于自动上传） +- Claude Code Max 计划（用于本地 AI 增强），或使用 `--agent` 选择其他 AI 代理 --- -## 📊 Feature Matrix +## 📊 功能矩阵 -Skill Seekers supports **12 LLM platforms**, **8 RAG/vector targets**, **18 source types**, and full feature parity across all targets. +Skill Seekers 支持 **12 个 LLM 平台**、**8 个 RAG/向量目标**、**18 种来源类型**，并在所有目标上实现完全的功能对等。 -**Platforms:** Claude AI, Google Gemini, OpenAI ChatGPT, MiniMax AI, Generic Markdown, OpenCode, Kimi (Moonshot AI), DeepSeek AI, Qwen (Alibaba), OpenRouter, Together AI, Fireworks AI -**Source Types:** Documentation websites, GitHub repos, PDFs, Word (.docx), EPUB, Video, Local codebases, Jupyter Notebooks, Local HTML, OpenAPI/Swagger, AsciiDoc, PowerPoint (.pptx), RSS/Atom feeds, Man pages, Confluence wikis, Notion pages, Slack/Discord chat exports +**平台：** Claude AI、Google Gemini、OpenAI ChatGPT、MiniMax AI、通用 Markdown、OpenCode、Kimi（月之暗面）、DeepSeek AI、Qwen（阿里巴巴）、OpenRouter、Together AI、Fireworks AI +**来源类型：** 文档网站、GitHub 仓库、PDF、Word (.docx)、EPUB、视频、本地代码库、Jupyter 笔记本、本地 HTML、OpenAPI/Swagger、AsciiDoc、PowerPoint (.pptx)、RSS/Atom 订阅源、Man 手册页、Confluence 维基、Notion 页面、Slack/Discord 聊天记录 -See [Complete Feature Matrix](docs/reference/FEATURE_MATRIX.md) for detailed platform and feature support. +完整信息请查看 [完整功能矩阵](docs/reference/FEATURE_MATRIX.md)。 -### Quick Platform Comparison +### 快速平台对比 -| Feature | Claude | Gemini | OpenAI | MiniMax | Markdown | -|---------|--------|--------|--------|--------|----------| -| Format | ZIP + YAML | tar.gz | ZIP + Vector | ZIP + Knowledge | ZIP | -| Upload | ✅ API | ✅ API | ✅ API | ✅ API | ❌ Manual | -| Enhancement | ✅ Sonnet 4 | ✅ 2.0 Flash | ✅ GPT-4o | ✅ M3 | ❌ None | -| All Skill Modes | ✅ | ✅ | ✅ | ✅ | ✅ | +| 功能 | Claude | Gemini | OpenAI | MiniMax | Markdown | +|------|--------|--------|--------|---------|----------| +| 格式 | ZIP + YAML | tar.gz | ZIP + Vector | ZIP + Knowledge | ZIP | +| 上传 | ✅ API | ✅ API | ✅ API | ✅ API | ❌ 手动 | +| 增强 | ✅ Sonnet 4 | ✅ 2.0 Flash | ✅ GPT-4o | ✅ M3 | ❌ 无 | +| 所有技能模式 | ✅ | ✅ | ✅ | ✅ | ✅ | --- -## Usage Examples +## 使用示例 -### Documentation Scraping +### 文档抓取 ```bash -# Scrape documentation website +# 抓取文档网站 skill-seekers create --config configs/react.json -# Quick scrape without config +# 快速抓取（无需配置） skill-seekers create https://react.dev --name react -# With async mode (3x faster) +# 异步模式（快 3 倍） skill-seekers create --config configs/godot.json --async --workers 8 -# Use a specific AI agent for enhancement +# 使用特定 AI 代理进行增强 skill-seekers create --config configs/react.json --agent kimi ``` -### PDF Extraction +### PDF 提取 ```bash -# Basic PDF extraction +# 基础 PDF 提取 skill-seekers create --pdf docs/manual.pdf --name myskill -# Advanced features +# 高级功能 skill-seekers create --pdf docs/manual.pdf --name myskill \ - --extract-tables \ # Extract tables - --parallel \ # Fast parallel processing - --workers 8 # Use 8 CPU cores + --extract-tables \ # 提取表格 + --parallel \ # 快速并行处理 + --workers 8 # 使用 8 个 CPU 核心 -# Scanned PDFs (requires: pip install pytesseract Pillow) +# 扫描 PDF（需要: pip install pytesseract Pillow） skill-seekers create --pdf docs/scanned.pdf --name myskill --ocr ``` -### Video Extraction +### 视频提取 ```bash -# Install video support -pip install skill-seekers[video] # Transcripts + metadata -pip install skill-seekers[video-full] # + Whisper + visual frame extraction +# 安装视频支持 +pip install skill-seekers[video] # 字幕 + 元数据 +pip install skill-seekers[video-full] # + Whisper 转录 + 视觉帧提取 -# Auto-detect GPU and install visual deps (PyTorch + easyocr) +# 自动检测 GPU 并安装视觉依赖（PyTorch + easyocr） skill-seekers create --setup -# Extract from YouTube video +# 从 YouTube 视频提取 skill-seekers create --video-url https://www.youtube.com/watch?v=dQw4w9WgXcQ --name mytutorial -# Extract from a YouTube playlist +# 从 YouTube 播放列表提取 skill-seekers create --video-playlist https://www.youtube.com/playlist?list=... --name myplaylist -# Extract from a local video file +# 从本地视频文件提取 skill-seekers create --video-file recording.mp4 --name myrecording -# Extract with visual frame analysis (requires video-full deps) +# 使用视觉帧分析提取（需要 video-full 依赖） skill-seekers create --video-url https://www.youtube.com/watch?v=... --name mytutorial --visual -# With AI enhancement (cleans OCR + generates polished SKILL.md) +# 使用 AI 增强（清理 OCR + 生成精美 SKILL.md） skill-seekers create --video-url https://www.youtube.com/watch?v=... --visual --enhance-level 2 -# Clip a specific section of a video (supports seconds, MM:SS, HH:MM:SS) +# 裁剪视频的特定片段（支持秒数、MM:SS、HH:MM:SS 格式） skill-seekers create --video-url https://www.youtube.com/watch?v=... --start-time 1:30 --end-time 5:00 -# Use Vision API for low-confidence OCR frames (requires ANTHROPIC_API_KEY) +# 使用 Vision API 处理低置信度 OCR 帧（需要 ANTHROPIC_API_KEY） skill-seekers create --video-url https://www.youtube.com/watch?v=... --visual --vision-ocr -# Re-build skill from previously extracted data (skip download) +# 从之前提取的数据重建技能（跳过下载） skill-seekers create --from-json output/mytutorial/video_data/extracted_data.json --name mytutorial ``` -> **Full guide:** See [docs/VIDEO_GUIDE.md](docs/VIDEO_GUIDE.md) for complete CLI reference, -> visual pipeline details, AI enhancement options, and troubleshooting. +> **完整指南：** 参见 [docs/VIDEO_GUIDE.md](docs/VIDEO_GUIDE.md) 了解完整 CLI 参考、 +> 视觉流水线详情、AI 增强选项和故障排除。 -### GitHub Repository Analysis +### GitHub 仓库分析 ```bash -# Basic repository scraping +# 基础仓库抓取 skill-seekers create facebook/react -# With authentication (higher rate limits) +# 配置认证（更高速率限制） export GITHUB_TOKEN=ghp_your_token_here skill-seekers create facebook/react -# Customize what to include +# 自定义包含内容 skill-seekers create django/django \ - --include-issues \ # Extract GitHub Issues - --max-issues 100 \ # Limit issue count - --include-changelog # Extract CHANGELOG.md + --include-issues \ # 提取 GitHub Issues + --max-issues 100 \ # 限制 issue 数量 + --include-changelog # 提取 CHANGELOG.md ``` -### Unified Multi-Source Scraping +### 统一多源抓取 -**Combine documentation + GitHub + PDF into one unified skill with conflict detection:** +**将文档 + GitHub + PDF 合并为一个带冲突检测的统一技能：** ```bash -# Use existing unified configs +# 使用现有统一配置 skill-seekers create --config configs/react_unified.json skill-seekers create --config configs/django_unified.json -# Or create unified config +# 或创建统一配置 cat > configs/myframework_unified.json << 'EOF' { "name": "myframework", @@ -934,229 +941,229 @@ EOF skill-seekers create --config configs/myframework_unified.json ``` -**Conflict Detection automatically finds:** -- 🔴 **Missing in code** (high): Documented but not implemented -- 🟡 **Missing in docs** (medium): Implemented but not documented -- ⚠️ **Signature mismatch**: Different parameters/types -- ℹ️ **Description mismatch**: Different explanations +**冲突检测自动发现：** +- 🔴 **代码中缺失**（高）：已文档化但未实现 +- 🟡 **文档中缺失**（中）：已实现但未文档化 +- ⚠️ **签名不匹配**：参数/类型不同 +- ℹ️ **描述不匹配**：解释不同 -**Full Guide:** See [docs/features/UNIFIED_SCRAPING.md](docs/features/UNIFIED_SCRAPING.md) for complete documentation. +**完整指南：** 参见 [docs/features/UNIFIED_SCRAPING.md](docs/features/UNIFIED_SCRAPING.md)。 -### Private Config Repositories +### 私有配置仓库 -**Share custom configs across teams using private git repositories:** +**使用私有 Git 仓库在团队间共享自定义配置：** ```bash -# Option 1: Using MCP tools (recommended) -# Register your team's private repo +# 选项 1：使用 MCP 工具（推荐） +# 注册团队私有仓库 add_config_source( name="team", git_url="https://github.com/mycompany/skill-configs.git", token_env="GITHUB_TOKEN" ) -# Fetch config from team repo +# 从团队仓库获取配置 fetch_config(source="team", config_name="internal-api") ``` -**Supported Platforms:** -- GitHub (`GITHUB_TOKEN`), GitLab (`GITLAB_TOKEN`), Gitea (`GITEA_TOKEN`), Bitbucket (`BITBUCKET_TOKEN`) +**支持的平台：** +- GitHub（`GITHUB_TOKEN`）、GitLab（`GITLAB_TOKEN`）、Gitea（`GITEA_TOKEN`）、Bitbucket（`BITBUCKET_TOKEN`） -**Full Guide:** See [docs/reference/GIT_CONFIG_SOURCES.md](docs/reference/GIT_CONFIG_SOURCES.md) for complete documentation. +**完整指南：** 参见 [docs/reference/GIT_CONFIG_SOURCES.md](docs/reference/GIT_CONFIG_SOURCES.md)。 -## How It Works +## 工作原理 ```mermaid graph LR - A[Documentation Website] --> B[Skill Seekers] - B --> C[Scraper] - B --> D[AI Enhancement] - B --> E[Packager] - C --> F[Organized References] + A[文档网站] --> B[Skill Seekers] + B --> C[抓取器] + B --> D[AI 增强] + B --> E[打包器] + C --> F[有序参考文件] D --> F F --> E - E --> G[AI Skill .zip] - G --> H[Upload to AI Platform] + E --> G[AI 技能 .zip] + G --> H[上传到 AI 平台] ``` -0. **Detect llms.txt** - Checks for llms-full.txt, llms.txt, llms-small.txt first (part of Smart SPA Discovery) -1. **Scrape**: Extracts all pages from documentation -2. **Categorize**: Organizes content into topics (API, guides, tutorials, etc.) -3. **Enhance**: AI analyzes docs and creates comprehensive SKILL.md with examples (supports multiple agents via `--agent`) -4. **Package**: Bundles everything into a platform-ready `.zip` file +0. **检测 llms.txt** - 优先检查 llms-full.txt、llms.txt、llms-small.txt（智能 SPA 发现的一部分） +1. **抓取**：提取文档中的所有页面 +2. **分类**：将内容组织为主题（API、指南、教程等） +3. **增强**：AI 分析文档并创建包含示例的完整 SKILL.md（通过 `--agent` 支持多种代理） +4. **打包**：将所有内容打包为平台就绪的 `.zip` 文件 -## Architecture +## 架构 -The system is organized into **8 core modules** and **5 utility modules** (~200 classes total): +系统由 **8 个核心模块**和 **5 个工具模块**组成（共约 200 个类）： -![Package Overview](docs/UML/exports/00_package_overview.png) +![包概览](docs/UML/exports/00_package_overview.png) -| Module | Purpose | Key Classes | -|--------|---------|-------------| -| **CLICore** | Git-style command dispatcher | `CLIDispatcher`, `SourceDetector`, `CreateCommand` | -| **Scrapers** | 18 source-type extractors | `DocToSkillConverter`, `DocumentSkillBuilder` (shared build layer), `UnifiedScraper` | -| **Adaptors** | 20+ output platform formats | `SkillAdaptor` (ABC), `ClaudeAdaptor`, `LangChainAdaptor` | -| **Analysis** | C3.x codebase analysis pipeline | `UnifiedCodebaseAnalyzer`, `PatternRecognizer`, 10 GoF detectors | -| **Enhancement** | AI-powered skill improvement via `AgentClient` | `AgentClient`, `AIEnhancer`, `UnifiedEnhancer`, `WorkflowEngine` | -| **Packaging** | Package, upload, install skills | `PackageSkill`, `InstallAgent` | -| **MCP** | FastMCP server (40 tools) | `SkillSeekerMCPServer`, 10 tool modules | -| **Sync** | Doc change detection | `ChangeDetector`, `SyncMonitor`, `Notifier` | +| 模块 | 用途 | 关键类 | +|------|------|--------| +| **CLICore** | Git 风格的命令分发器 | `CLIDispatcher`、`SourceDetector`、`CreateCommand` | +| **Scrapers** | 18 种来源类型提取器 | `DocToSkillConverter`、`DocumentSkillBuilder`（共享构建层）、`UnifiedScraper` | +| **Adaptors** | 20+ 输出平台格式 | `SkillAdaptor`（ABC）、`ClaudeAdaptor`、`LangChainAdaptor` | +| **Analysis** | C3.x 代码库分析流水线 | `UnifiedCodebaseAnalyzer`、`PatternRecognizer`、10 个 GoF 检测器 | +| **Enhancement** | 通过 `AgentClient` 实现 AI 驱动的技能改进 | `AgentClient`、`AIEnhancer`、`UnifiedEnhancer`、`WorkflowEngine` | +| **Packaging** | 打包、上传、安装技能 | `PackageSkill`、`InstallAgent` | +| **MCP** | FastMCP 服务器（40 个工具） | `SkillSeekerMCPServer`、10 个工具模块 | +| **Sync** | 文档变更检测 | `ChangeDetector`、`SyncMonitor`、`Notifier` | -Utility modules: **Parsers** (28 CLI parsers), **Storage** (S3/GCS/Azure), **Embedding** (multi-provider vectors), **Benchmark** (performance), **Utilities** (16 shared helpers). +工具模块：**Parsers**（28 个 CLI 解析器）、**Storage**（S3/GCS/Azure）、**Embedding**（多提供商向量）、**Benchmark**（性能）、**Utilities**（16 个共享辅助工具）。 -Full UML diagrams: **[docs/UML_ARCHITECTURE.md](docs/UML_ARCHITECTURE.md)** | StarUML project: `docs/UML/skill_seekers.mdj` | HTML API reference: `docs/UML/html/` +完整 UML 图：**[docs/UML_ARCHITECTURE.md](docs/UML_ARCHITECTURE.md)** | StarUML 项目：`docs/UML/skill_seekers.mdj` | HTML API 参考：`docs/UML/html/` -## 📋 Prerequisites +## 📋 前提条件 -**Before you start, make sure you have:** +**开始前，请确保您具备：** -1. **Python 3.10 or higher** - [Download](https://www.python.org/downloads/) | Check: `python3 --version` -2. **Git** - [Download](https://git-scm.com/) | Check: `git --version` -3. **15-30 minutes** for first-time setup +1. **Python 3.10 或更高版本** - [下载](https://www.python.org/downloads/) | 检查：`python3 --version` +2. **Git** - [下载](https://git-scm.com/) | 检查：`git --version` +3. **15–30 分钟**用于首次设置 -**First time user?** → **[Start Here: Bulletproof Quick Start Guide](BULLETPROOF_QUICKSTART.md)** 🎯 +**首次使用？** → **[从这里开始：防弹快速入门指南](BULLETPROOF_QUICKSTART.md)** 🎯 --- -## 📤 Uploading Skills to Claude +## 📤 上传技能到 Claude -Once your skill is packaged, you need to upload it to Claude: +技能打包完成后，需要将其上传到 Claude： -### Option 1: Automatic Upload (API-based) +### 选项 1：自动上传（基于 API） ```bash -# Set your API key (one-time) +# 设置 API Key（一次性） export ANTHROPIC_API_KEY=sk-ant-... -# Package and upload automatically +# 打包并自动上传 skill-seekers package output/react/ --upload -# OR upload existing .zip +# 或上传已有的 .zip skill-seekers upload output/react.zip ``` -### Option 2: Manual Upload (No API Key) +### 选项 2：手动上传（无需 API Key） ```bash -# Package skill +# 打包技能 skill-seekers package output/react/ -# → Creates output/react.zip +# → 创建 output/react.zip -# Then manually upload: -# - Go to https://claude.ai/skills -# - Click "Upload Skill" -# - Select output/react.zip +# 然后手动上传： +# - 访问 https://claude.ai/skills +# - 点击"上传技能" +# - 选择 output/react.zip ``` -### Option 3: MCP (Claude Code) +### 选项 3：MCP（Claude Code） ``` -In Claude Code, just ask: -"Package and upload the React skill" +在 Claude Code 中，直接询问： +"打包并上传 React 技能" ``` --- -## 🤖 Installing to AI Agents +## 🤖 安装到 AI 代理 -Skill Seekers can automatically install skills to 19 AI coding agents. +Skill Seekers 可自动将技能安装到 19 个 AI 编程代理。 ```bash -# Install to specific agent +# 安装到特定代理 skill-seekers install-agent output/react/ --agent cursor -# Install to IBM Bob (project-local .bob/skills/) +# 安装到 IBM Bob（项目本地 .bob/skills/） skill-seekers install-agent output/react/ --agent bob -# Install to all agents at once +# 一次性安装到所有代理 skill-seekers install-agent output/react/ --agent all -# Preview without installing +# 预览而不安装 skill-seekers install-agent output/react/ --agent cursor --dry-run ``` -### Supported Agents +### 支持的代理 -| Agent | Path | Type | -|-------|------|------| -| **Claude Code** | `~/.claude/skills/` | Global | -| **Cursor** | `.cursor/skills/` | Project | -| **VS Code / Copilot** | `.github/skills/` | Project | -| **Amp** | `~/.amp/skills/` | Global | -| **Goose** | `~/.config/goose/skills/` | Global | -| **OpenCode** | `~/.opencode/skills/` | Global | -| **Windsurf** | `~/.windsurf/skills/` | Global | -| **Roo Code** | `.roo/skills/` | Project | -| **Cline** | `.cline/skills/` | Project | -| **Aider** | `~/.aider/skills/` | Global | -| **Bolt** | `.bolt/skills/` | Project | -| **Kilo Code** | `.kilo/skills/` | Project | -| **Continue** | `~/.continue/skills/` | Global | -| **Kimi Code** | `~/.kimi/skills/` | Global | -| **IBM Bob** | `.bob/skills/` | Project | +| 代理 | 路径 | 类型 | +|------|------|------| +| **Claude Code** | `~/.claude/skills/` | 全局 | +| **Cursor** | `.cursor/skills/` | 项目 | +| **VS Code / Copilot** | `.github/skills/` | 项目 | +| **Amp** | `~/.amp/skills/` | 全局 | +| **Goose** | `~/.config/goose/skills/` | 全局 | +| **OpenCode** | `~/.opencode/skills/` | 全局 | +| **Windsurf** | `~/.windsurf/skills/` | 全局 | +| **Roo Code** | `.roo/skills/` | 项目 | +| **Cline** | `.cline/skills/` | 项目 | +| **Aider** | `~/.aider/skills/` | 全局 | +| **Bolt** | `.bolt/skills/` | 项目 | +| **Kilo Code** | `.kilo/skills/` | 项目 | +| **Continue** | `~/.continue/skills/` | 全局 | +| **Kimi Code** | `~/.kimi/skills/` | 全局 | +| **IBM Bob** | `.bob/skills/` | 项目 | --- -## 🔌 MCP Integration (40 Tools) +## 🔌 MCP 集成（40 个工具） -Skill Seekers ships an MCP server for use from Claude Code, Cursor, Windsurf, VS Code + Cline, or IntelliJ IDEA. +Skill Seekers 提供 MCP 服务器，可在 Claude Code、Cursor、Windsurf、VS Code + Cline 或 IntelliJ IDEA 中使用。 ```bash -# stdio mode (Claude Code, VS Code + Cline) +# stdio 模式（Claude Code、VS Code + Cline） python -m skill_seekers.mcp.server_fastmcp -# HTTP mode (Cursor, Windsurf, IntelliJ) +# HTTP 模式（Cursor、Windsurf、IntelliJ） python -m skill_seekers.mcp.server_fastmcp --transport http --port 8765 -# Auto-configure all agents at once +# 一次性自动配置所有代理 ./setup_mcp.sh ``` -**All 40 tools available:** -- **Core (9):** `list_configs`, `generate_config`, `validate_config`, `estimate_pages`, `scrape_docs`, `package_skill`, `upload_skill`, `enhance_skill`, `install_skill` -- **Extended (10):** `scrape_github`, `scrape_pdf`, `unified_scrape`, `merge_sources`, `detect_conflicts`, `add_config_source`, `fetch_config`, `list_config_sources`, `remove_config_source`, `split_config` -- **Vector DB (4):** `export_to_chroma`, `export_to_weaviate`, `export_to_faiss`, `export_to_qdrant` -- **Cloud (3):** `cloud_upload`, `cloud_download`, `cloud_list` +**全部 40 个可用工具：** +- **核心（9 个）：** `list_configs`、`generate_config`、`validate_config`、`estimate_pages`、`scrape_docs`、`package_skill`、`upload_skill`、`enhance_skill`、`install_skill` +- **扩展（10 个）：** `scrape_github`、`scrape_pdf`、`unified_scrape`、`merge_sources`、`detect_conflicts`、`add_config_source`、`fetch_config`、`list_config_sources`、`remove_config_source`、`split_config` +- **向量数据库（4 个）：** `export_to_chroma`、`export_to_weaviate`、`export_to_faiss`、`export_to_qdrant` +- **云存储（3 个）：** `cloud_upload`、`cloud_download`、`cloud_list` -**Full Guide:** [docs/guides/MCP_SETUP.md](docs/guides/MCP_SETUP.md) +**完整指南：** [docs/guides/MCP_SETUP.md](docs/guides/MCP_SETUP.md) --- -## ⚙️ Configuration +## ⚙️ 配置 -### Available Presets (24+) +### 可用预设（24+） ```bash -# List all presets -# skill-seekers list-configs # Not available in v3.7.0 +# 列出所有预设 +# skill-seekers list-configs # v3.7.0 中不可用 ``` -| Category | Presets | -|----------|---------| -| **Web Frameworks** | `react`, `vue`, `angular`, `svelte`, `nextjs` | -| **Python** | `django`, `flask`, `fastapi`, `sqlalchemy`, `pytest` | -| **Game Development** | `godot`, `pygame`, `unity` | -| **Tools & DevOps** | `docker`, `kubernetes`, `terraform`, `ansible` | -| **Unified (Docs + GitHub)** | `react-unified`, `vue-unified`, `nextjs-unified`, and more | +| 类别 | 预设 | +|------|------| +| **Web 框架** | `react`、`vue`、`angular`、`svelte`、`nextjs` | +| **Python** | `django`、`flask`、`fastapi`、`sqlalchemy`、`pytest` | +| **游戏开发** | `godot`、`pygame`、`unity` | +| **工具与 DevOps** | `docker`、`kubernetes`、`terraform`、`ansible` | +| **统一（文档 + GitHub）** | `react-unified`、`vue-unified`、`nextjs-unified` 等 | -### Creating Your Own Config +### 创建您自己的配置 ```bash -# Option 1: Interactive +# 选项 1：交互式 skill-seekers create --interactive -# Option 2: Copy and edit a preset +# 选项 2：复制并编辑预设 cp configs/react.json configs/myframework.json nano configs/myframework.json skill-seekers create --config configs/myframework.json ``` -### Config File Structure +### 配置文件结构 ```json { "name": "myframework", - "description": "When to use this skill", + "description": "何时使用此技能", "base_url": "https://docs.myframework.com/", "selectors": { "main_content": "article", @@ -1176,195 +1183,195 @@ skill-seekers create --config configs/myframework.json } ``` -### Where to Store Configs +### 配置存储位置 -The tool searches in this order: -1. Exact path as provided -2. `./configs/` (current directory) -3. `~/.config/skill-seekers/configs/` (user config directory) -4. SkillSeekersWeb.com API (preset configs) +工具按以下顺序搜索： +1. 提供的确切路径 +2. `./configs/`（当前目录） +3. `~/.config/skill-seekers/configs/`（用户配置目录） +4. SkillSeekersWeb.com API（预设配置） --- -## 📊 What Gets Created +## 📊 创建的内容 ``` output/ -├── godot_data/ # Scraped raw data -│ ├── pages/ # JSON files (one per page) -│ └── summary.json # Overview +├── godot_data/ # 抓取的原始数据 +│ ├── pages/ # JSON 文件（每页一个） +│ └── summary.json # 概览 │ -└── godot/ # The skill - ├── SKILL.md # Enhanced with real examples - ├── references/ # Categorized docs +└── godot/ # 技能文件 + ├── SKILL.md # 含真实示例的增强版 + ├── references/ # 分类文档 │ ├── index.md │ ├── getting_started.md │ ├── scripting.md │ └── ... - ├── scripts/ # Empty (add your own) - └── assets/ # Empty (add your own) + ├── scripts/ # 空（可添加自己的脚本） + └── assets/ # 空（可添加自己的资源） ``` --- -## 🐛 Troubleshooting +## 🐛 故障排除 -### No Content Extracted? -- Check your `main_content` selector -- Try: `article`, `main`, `div[role="main"]` +### 未提取到内容？ +- 检查您的 `main_content` 选择器 +- 尝试：`article`、`main`、`div[role="main"]` -### Data Exists But Won't Use It? +### 数据存在但不使用？ ```bash -# Force re-scrape +# 强制重新抓取 rm -rf output/myframework_data/ skill-seekers create --config configs/myframework.json ``` -### Categories Not Good? -Edit the config `categories` section with better keywords. +### 分类不理想？ +编辑配置中的 `categories` 部分，使用更好的关键词。 -### Want to Update Docs? +### 想要更新文档？ ```bash -# Delete old data and re-scrape +# 删除旧数据并重新抓取 rm -rf output/godot_data/ skill-seekers create --config configs/godot.json ``` -### Enhancement Not Working? +### 增强不工作？ ```bash -# Check if API key is set +# 检查 API Key 是否设置 echo $ANTHROPIC_API_KEY -# Try LOCAL mode instead (uses Claude Code Max, no API key needed) +# 尝试 LOCAL 模式（使用 Claude Code Max，无需 API Key） skill-seekers enhance output/react/ --mode LOCAL -# Monitor background enhancement status +# 监控后台增强状态 skill-seekers enhance-status output/react/ --watch ``` -### GitHub Rate Limit Issues? +### GitHub 速率限制问题？ ```bash -# Set a GitHub token (5000 req/hour vs 60/hour anonymous) +# 设置 GitHub Token（5000 次/小时 vs 匿名 60 次/小时） export GITHUB_TOKEN=ghp_your_token_here -# Or configure multiple profiles +# 或配置多个配置文件 skill-seekers config --github ``` --- -## 📈 Performance +## 📈 性能 -| Task | Time | Notes | -|------|------|-------| -| Scraping (sync) | 15-45 min | First time only, thread-based | -| Scraping (async) | 5-15 min | 2-3x faster with `--async` flag | -| Building | 1-3 min | Fast rebuild from cache | -| Re-building | <1 min | With `--skip-scrape` | -| Enhancement (LOCAL) | 30-60 sec | Uses Claude Code Max | -| Enhancement (API) | 20-40 sec | Requires API key | -| Video (transcript) | 1-3 min | YouTube/local, transcript only | -| Video (visual) | 5-15 min | + OCR frame extraction | -| Packaging | 5-10 sec | Final .zip creation | +| 任务 | 时间 | 备注 | +|------|------|------| +| 抓取（同步）| 15–45 分钟 | 仅首次，基于线程 | +| 抓取（异步）| 5–15 分钟 | `--async` 标志快 2–3 倍 | +| 构建 | 1–3 分钟 | 从缓存快速重建 | +| 重建 | <1 分钟 | 使用 `--skip-scrape` | +| 增强（LOCAL）| 30–60 秒 | 使用 Claude Code Max | +| 增强（API）| 20–40 秒 | 需要 API Key | +| 视频（字幕）| 1–3 分钟 | YouTube/本地，仅字幕 | +| 视频（视觉）| 5–15 分钟 | + OCR 帧提取 | +| 打包 | 5–10 秒 | 最终 .zip 创建 | --- -## 🆕 New in v3.6.0 +## 🆕 v3.6.0 新增功能 -### Workflow Presets -Control analysis depth with `--preset`: +### 工作流预设 +使用 `--preset` 控制分析深度： ```bash -skill-seekers create https://docs.react.dev/ --preset quick # Fast, surface-level -skill-seekers create https://docs.react.dev/ --preset standard # Balanced (default) -skill-seekers create https://docs.react.dev/ --preset comprehensive # Deep, exhaustive +skill-seekers create https://docs.react.dev/ --preset quick # 快速，浅层分析 +skill-seekers create https://docs.react.dev/ --preset standard # 平衡（默认） +skill-seekers create https://docs.react.dev/ --preset comprehensive # 深度，详尽分析 ``` -### Lifecycle Flags +### 生命周期标志 ```bash -skill-seekers create https://docs.react.dev/ --dry-run # Preview without scraping -skill-seekers create https://docs.react.dev/ --fresh # Ignore cache, full re-scrape -skill-seekers create https://docs.react.dev/ --resume # Resume interrupted job -skill-seekers create https://docs.react.dev/ --skip-scrape # Re-package existing output +skill-seekers create https://docs.react.dev/ --dry-run # 不抓取预览 +skill-seekers create https://docs.react.dev/ --fresh # 忽略缓存，完整重新抓取 +skill-seekers create https://docs.react.dev/ --resume # 恢复中断的任务 +skill-seekers create https://docs.react.dev/ --skip-scrape # 重新打包现有输出 ``` -### Health Check & Utilities +### 健康检查与工具 ```bash -skill-seekers doctor # Diagnose installation & environment -skill-seekers sync-config # Detect config drift -skill-seekers stream # Streaming ingestion for large docs -skill-seekers update output/react/ # Incremental update -skill-seekers multilang # Multi-language skill generation -skill-seekers quality output/react/ # Quality report (add --threshold 7 to gate: non-zero exit below 7/10) +skill-seekers doctor # 诊断安装与环境 +skill-seekers sync-config # 配置漂移检测 +skill-seekers stream # 大型文档流式摄取 +skill-seekers update output/react/ # 增量更新 +skill-seekers multilang # 多语言技能生成 +skill-seekers quality output/react/ # 质量报告（添加 --threshold 7 设置门槛：低于 7/10 时非零退出） ``` -### RAG Chunking Options (package) +### RAG 分块选项（打包） ```bash skill-seekers package output/react/ --chunk-for-rag --chunk-tokens 512 --chunk-overlap-tokens 50 ``` -### Marketplace Publishing +### 市场发布 ```bash skill-seekers package output/react/ --marketplace --marketplace-category frontend ``` -### Additional Optional Dependencies -| Extra | Install | Purpose | -|-------|---------|---------| -| `browser` | `pip install "skill-seekers[browser]"` | Headless Playwright for SPA sites | -| `embedding` | `pip install "skill-seekers[embedding]"` | Embedding server support | -| `s3` / `gcs` / `azure` | `pip install "skill-seekers[s3]"` etc. | Cloud storage upload | -| `rag-upload` | `pip install "skill-seekers[rag-upload]"` | Combined vector DB upload deps | +### 其他可选依赖 +| Extra | 安装 | 用途 | +|-------|------|------| +| `browser` | `pip install "skill-seekers[browser]"` | 适用于 SPA 网站的无头 Playwright | +| `embedding` | `pip install "skill-seekers[embedding]"` | 嵌入服务器支持 | +| `s3` / `gcs` / `azure` | `pip install "skill-seekers[s3]"` 等 | 云存储上传 | +| `rag-upload` | `pip install "skill-seekers[rag-upload]"` | 组合向量数据库上传依赖 | --- -## 📚 Documentation +## 📚 文档 -### Getting Started -- **[BULLETPROOF_QUICKSTART.md](BULLETPROOF_QUICKSTART.md)** - 🎯 **START HERE** if you're new! -- **[QUICKSTART.md](docs/archive/legacy/QUICKSTART.md)** - Quick start for experienced users -- **[TROUBLESHOOTING.md](TROUBLESHOOTING.md)** - Common issues and solutions -- **[docs/archive/legacy/QUICK_REFERENCE.md](docs/archive/legacy/QUICK_REFERENCE.md)** - One-page cheat sheet +### 入门指南 +- **[BULLETPROOF_QUICKSTART.md](BULLETPROOF_QUICKSTART.md)** - 🎯 **新用户从这里开始！** +- **[QUICKSTART.md](docs/archive/legacy/QUICKSTART.md)** - 有经验用户的快速入门 +- **[TROUBLESHOOTING.md](TROUBLESHOOTING.md)** - 常见问题和解决方案 +- **[docs/archive/legacy/QUICK_REFERENCE.md](docs/archive/legacy/QUICK_REFERENCE.md)** - 单页速查表 -### Architecture -- **[docs/UML_ARCHITECTURE.md](docs/UML_ARCHITECTURE.md)** - UML architecture overview with 14 diagrams -- **[docs/UML/exports/](docs/UML/exports/)** - PNG diagram exports (package overview + 13 class diagrams) -- **[docs/UML/html/](docs/UML/html/index.html/index.html)** - Full HTML API reference (all classes, operations, attributes) -- **[docs/UML/skill_seekers.mdj](docs/UML/skill_seekers.mdj)** - StarUML project file (open with [StarUML](https://staruml.io/)) +### 架构 +- **[docs/UML_ARCHITECTURE.md](docs/UML_ARCHITECTURE.md)** - 包含 14 张图的 UML 架构概览 +- **[docs/UML/exports/](docs/UML/exports/)** - PNG 图导出（包概览 + 13 张类图） +- **[docs/UML/html/](docs/UML/html/index.html/index.html)** - 完整 HTML API 参考（所有类、操作、属性） +- **[docs/UML/skill_seekers.mdj](docs/UML/skill_seekers.mdj)** - StarUML 项目文件（使用 [StarUML](https://staruml.io/) 打开） -### Guides -- **[docs/reference/LARGE_DOCUMENTATION.md](docs/reference/LARGE_DOCUMENTATION.md)** - Handle 10K-40K+ page docs -- **[docs/features/ENHANCEMENT_MODES.md](docs/features/ENHANCEMENT_MODES.md)** - AI enhancement modes guide -- **[docs/guides/MCP_SETUP.md](docs/guides/MCP_SETUP.md)** - MCP integration setup -- **[docs/features/UNIFIED_SCRAPING.md](docs/features/UNIFIED_SCRAPING.md)** - Multi-source scraping -- **[docs/VIDEO_GUIDE.md](docs/VIDEO_GUIDE.md)** - Video extraction guide +### 指南 +- **[docs/reference/LARGE_DOCUMENTATION.md](docs/reference/LARGE_DOCUMENTATION.md)** - 处理 10K–40K+ 页文档 +- **[docs/features/ENHANCEMENT_MODES.md](docs/features/ENHANCEMENT_MODES.md)** - AI 增强模式指南 +- **[docs/guides/MCP_SETUP.md](docs/guides/MCP_SETUP.md)** - MCP 集成设置 +- **[docs/features/UNIFIED_SCRAPING.md](docs/features/UNIFIED_SCRAPING.md)** - 多源抓取 +- **[docs/VIDEO_GUIDE.md](docs/VIDEO_GUIDE.md)** - 视频提取完整指南 -### Integration Guides +### 集成指南 - **[docs/integrations/LANGCHAIN.md](docs/integrations/LANGCHAIN.md)** - LangChain RAG - **[docs/integrations/CURSOR.md](docs/integrations/CURSOR.md)** - Cursor IDE - **[docs/integrations/WINDSURF.md](docs/integrations/WINDSURF.md)** - Windsurf IDE -- **[docs/integrations/CLINE.md](docs/integrations/CLINE.md)** - Cline (VS Code) -- **[docs/integrations/RAG_PIPELINES.md](docs/integrations/RAG_PIPELINES.md)** - All RAG pipelines +- **[docs/integrations/CLINE.md](docs/integrations/CLINE.md)** - Cline（VS Code） +- **[docs/integrations/RAG_PIPELINES.md](docs/integrations/RAG_PIPELINES.md)** - 所有 RAG 流水线 --- -## 📝 License +## 📝 许可证 -MIT License - see [LICENSE](LICENSE) file for details +MIT 许可证 - 详见 [LICENSE](LICENSE) 文件 --- -Happy skill building! 🚀 +祝您构建技能愉快！ 🚀 --- -## 🔒 Security +## 🔒 安全 -[![MseeP.ai Security Assessment Badge](https://mseep.net/pr/yusufkaraaslan-skill-seekers-badge.png)](https://mseep.ai/app/yusufkaraaslan-skill-seekers) +[![MseeP.ai 安全评估徽章](https://mseep.net/pr/yusufkaraaslan-skill-seekers-badge.png)](https://mseep.ai/app/yusufkaraaslan-skill-seekers) --- -## 💛 Sponsors +## 💛 赞助商

@@ -1372,4 +1379,4 @@ Happy skill building! 🚀

-[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=skill_seekers) — a full-modal, OpenAI-compatible AI inference platform. Skill Seekers supports it as a packaging/enhancement target via `--target atlas` with `ATLAS_API_KEY`. +[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=skill_seekers) — 全模态、OpenAI 兼容的 AI 推理平台。Skill Seekers 通过 `--target atlas`（配置 `ATLAS_API_KEY`）支持将其作为打包/增强目标。