npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

autoskill

v0.1.0

Published

将工程经验、Git 仓库、文档等知识快速转化为 Claude Skills

Readme

AutoSkill v1.0.0

Transform knowledge into AI Skills across all platforms

npm version License: MIT


English | 简体中文


Overview

AutoSkill is an intelligent tool that automatically extracts, parses, and generates AI Skills/Prompts from multiple knowledge sources. It supports Git repositories, technical documentation, conversation history, web content, and outputs to various AI platform formats.

Core Features

| Feature | Description | |---------|-------------| | Multi-Source Collection | Git, Docs, Chat, Web - four types of knowledge sources | | Intelligent Parsing | Automatic extraction of patterns, best practices, common issues | | Multi-Format Output | Claude Skills, OpenAI GPTs, LangChain, Character.AI, Universal Prompt | | Quality Validation | 7-dimension validation system to ensure quality | | LLM Optimization | Iterative critique-improvement cycle optimization | | Batch Processing | Concurrent processing of multiple knowledge sources | | Quality Gate | Policy-based quality standards | | Code Patterns | Design patterns, architectural patterns, language idioms |


Quick Start

Installation

# Global installation (recommended)
npm install -g autoskill

# Verify installation
autoskill --version

5-Minute Getting Started

# 1. Initialize configuration
autoskill init --global

# 2. Generate Skill from Git repository
autoskill git https://github.com/user/repo --name my-expert

# 3. Validate quality
autoskill validate ./skills/my-expert --verbose

More Usage

# Generate from documentation
autoskill doc README.md --name "project-guide"

# Generate from conversation history
autoskill chat conversations.jsonl --name "team-patterns"

# Generate from web
autoskill web https://docs.example.com --name "api-docs"

# Generate multiple formats
autoskill git ./repo --name "expert" --format openai-gpts
autoskill git ./repo --name "expert" --all-formats

# List supported formats
autoskill formats --verbose

# Optimize existing Skill
autoskill optimize ./skills/my-expert --improve prompts,examples

# Batch processing
autoskill batch ./projects --parallel 5

Documentation

| Document | Description | |----------|-------------| | User Guide | Complete usage instructions | | Architecture | System architecture design | | API Reference | Complete API documentation |


Workflow

┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│  Knowledge  │ -> │  Collector  │ -> │   Parser    │
│  Git/Doc/Web│    │             │    │             │
└─────────────┘    └─────────────┘    └─────────────┘
                                            │
┌─────────────┐    ┌─────────────┐    ┌────┴────────┐
│   Final     │ <- │  Validator  │ <- │  Generator  │
│   Output    │    │             │    │             │
└─────────────┘    └─────────────┘    └─────────────┘
                           │
                    ┌──────┴──────┐
                    │  Optimizer  │
                    └─────────────┘

Supported Formats

| Format | Description | Platforms | |--------|-------------|-----------| | claude-skills | Claude Code native Skills | Claude Code, Claude Desktop | | openai-gpts | OpenAI ChatGPT Custom GPTs | ChatGPT, OpenAI GPTs | | langchain | LangChain Prompt Template | LangChain apps | | character-ai | Character.AI character card | Character.AI | | universal-prompt | Universal prompt template | Claude, ChatGPT, Gemini, etc. |


License

MIT


概述

AutoSkill 是一个智能工具,能够从多种知识源自动提取、解析并生成符合规范的 AI Skills/Prompts。支持 Git 仓库、技术文档、对话历史、网页内容等多种知识源,并可输出到多种 AI 平台格式。

核心特性

| 特性 | 描述 | |------|------| | 多源采集 | Git、文档、对话、网页四类知识源 | | 智能解析 | 自动提取模式、最佳实践、常见问题 | | 多格式输出 | Claude Skills、OpenAI GPTs、LangChain、Character.AI、通用 Prompt | | 质量验证 | 七维度验证体系,确保质量 | | LLM 优化 | 迭代式批评-改进循环优化 | | 批量处理 | 并发处理多个知识源 | | 质量门禁 | 策略化质量标准 | | 代码模式 | 设计模式、架构模式、语言习惯用法 |


快速开始

安装

# 全局安装(推荐)
npm install -g autoskill

# 验证安装
autoskill --version

5 分钟上手

# 1. 初始化配置
autoskill init --global

# 2. 从 Git 仓库生成 Skill
autoskill git https://github.com/user/repo --name my-expert

# 3. 验证质量
autoskill validate ./skills/my-expert --verbose

更多用法

# 从文档生成
autoskill doc README.md --name "project-guide"

# 从对话历史生成
autoskill chat conversations.jsonl --name "team-patterns"

# 从网页生成
autoskill web https://docs.example.com --name "api-docs"

# 生成多种格式
autoskill git ./repo --name "expert" --format openai-gpts
autoskill git ./repo --name "expert" --all-formats

# 列出支持的格式
autoskill formats --verbose

# 优化现有 Skill
autoskill optimize ./skills/my-expert --improve prompts,examples

# 批量处理
autoskill batch ./projects --parallel 5

文档

| 文档 | 描述 | |------|------| | 用户指南 | 完整的使用说明 | | 技术架构 | 系统架构设计 | | API 参考 | 完整的 API 文档 |


工作流

┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│  知识源      │ -> │  采集器      │ -> │  解析器      │
│ Git/Doc/Web │    │ Collector   │    │ Parser      │
└─────────────┘    └─────────────┘    └─────────────┘
                                            │
┌─────────────┐    ┌─────────────┐    ┌────┴────────┐
│  最终输出    │ <- │  验证器      │ <- │  生成器      │
│ AI Skills   │    │ Validator   │    │ Generator   │
└─────────────┘    └─────────────┘    └─────────────┘
                           │
                    ┌──────┴──────┐
                    │  优化器      │
                    │ Optimizer   │
                    └─────────────┘

支持的格式

| 格式 | 说明 | 适用平台 | |------|------|----------| | claude-skills | Claude Code 原生 Skills 格式 | Claude Code, Claude Desktop | | openai-gpts | OpenAI ChatGPT Custom GPTs 格式 | ChatGPT, OpenAI GPTs | | langchain | LangChain Prompt Template 格式 | LangChain 应用 | | character-ai | Character.AI 角色卡格式 | Character.AI | | universal-prompt | 通用 Prompt 模板格式 | Claude, ChatGPT, Gemini 等 |


许可证

MIT