Claude Skill
rodydavis/agent-skills-generator
开源TypeScript工具,能够从网站文档自动生成Claude Skill代理技能。通过基于网络的知识增强AI代理,并自动化技能创建工作流程。
概览
仓库信息
安装这个 Skill
git clone https://github.com/rodydavis/agent-skills-generator.gitRegistry 信息
项目简介
一个基于TypeScript的工具,能够从网站文档自动生成Claude Skill代理技能,使AI代理能够访问和利用基于网络的信息。
Generate agent skills from website documentation
要点
- 从网站文档生成Claude Skill代理技能
- 基于TypeScript实现,确保可靠性和类型安全
- 自动化AI代理技能创建
- 通过基于网络的知识增强代理能力
- 开源项目,持续活跃开发
使用场景
- 构建能够访问网络文档的AI代理
- 自动化Claude Skill创建工作流程
- 从网站增强代理知识库
- 快速原型化基于文档的技能
- 将网络内容集成到AI代理生态系统中
README 摘要
# Agent Skills Generator Convert documentation websites into Markdown skills optimized for AI agents and LLMs. This repository contains two projects: 1. **VS Code Extension**: A GUI-based tool to manage and generate skills directly within VS Code. 2. **Go CLI**: A robust command-line tool for high-performance crawling and generation. --- ## 1. VS Code Extension Code located in [`vscode-extension/`](./vscode-extension). A Visual Studio Code extension that provides a dedicated "Agent Skills" side panel to manage your crawling rules and generate skills. ### Features * **Visual Rule Management**: Add, edit, and delete URL patterns via a clean UI. * **One-Click Generation**: Fetch skills directly from VS Code. * **State Persistence**: Rules and settings are saved between sessions. * **Import/Export**: Share configurations via JSON files. * **Configurable**: Set output directory, file naming, and structure preferences. ### Installation 1. Clone this repository. 2. Open the `vscode-extension` folder in VS Code. 3. Run `npm install` to install dependencies. 4. Press `F5` to start the extension in a debug window. ### Usage 1. Open the **Agent Skills** view in the Activity Bar. 2. Add URL patterns (e.g., `https://docs.flutter.dev/`). 3. Configure **Include/Ignore** and **Subpaths**. 4. Click **Fetch Skills**. --- ## 2. Go CLI Code located in [`go-cli/`](./go-cli). A high-performance CLI tool written in Go for recursive crawling and Markdown conversion. ### Features * **Recursive Crawling**: Configurable depth and filtering. * **HTML to Markdown**: Clean conversion optimized for token efficiency. * **Metadata Extraction**: Frontmatter with original URL, title, and dates. * **Flat Storage**: Option to save as flat structures for RAG compatability.