io.github.shadowrootdev/awesome-agent-skills
AI 与智能体by shadowrootdev
提供包含 100+ AI agent skills 的 MCP 服务器,整合 Anthropic、Vercel、Trail of Bits、Hugging Face 等资源。
什么是 io.github.shadowrootdev/awesome-agent-skills?
提供包含 100+ AI agent skills 的 MCP 服务器,整合 Anthropic、Vercel、Trail of Bits、Hugging Face 等资源。
README
Awesome Agent Skills MCP Server
A Model Context Protocol (MCP) server that provides access to 100+ curated AI agent skills from the VoltAgent Awesome Agent Skills collection.
Transform your AI assistants into specialized experts with skills from Anthropic, Vercel, Trail of Bits, Hugging Face, Stripe, Expo, and many more leading organizations.
🚀 Quick Start
npx awesome-agent-skills-mcp
That's it! Add to your MCP client config and start using 100+ AI skills.
Table of Contents
- Features
- Quick Start
- Installation
- Configuration
- Available Skills
- MCP Tools
- Usage Examples
- Development
- API Reference
- Troubleshooting
- Credits
- License
Features
- 100+ Curated Skills - Access skills from top organizations including Anthropic, Vercel, Trail of Bits, Hugging Face, and more
- Auto-Sync - Automatically fetches and updates skills from the VoltAgent repository
- MCP 2024-11-05 Compliant - Full compatibility with the latest Model Context Protocol specification
- Multi-Client Support - Works with Claude, GitHub Copilot, OpenCode, and any MCP-compatible client
- Smart Caching - Efficient JSON-based caching for fast startup times
- Type-Safe - Built with TypeScript and Zod for runtime validation
- Zero Configuration - Works out of the box with sensible defaults
Quick Start
Using npx (Recommended)
npx awesome-agent-skills-mcp
Global Installation
npm install -g awesome-agent-skills-mcp
awesome-agent-skills-mcp
Installation
Prerequisites
- Node.js >= 20.0.0
- npm or yarn
From npm
npm install awesome-agent-skills-mcp
From Source
git clone https://github.com/shadowrootdev/awesome-agent-skills-mcp.git
cd awesome-agent-skills-mcp
npm install
npm run build
Configuration
VS Code / GitHub Copilot
Create or update .vscode/mcp.json in your project:
{
"servers": {
"awesome-agent-skills": {
"command": "npx",
"args": ["awesome-agent-skills-mcp"]
}
}
}
Or with a local installation:
{
"servers": {
"awesome-agent-skills": {
"command": "node",
"args": ["/path/to/awesome-agent-skills-mcp/dist/index.js"]
}
}
}
Important: After adding the configuration, fully quit VS Code (Cmd+Q / Alt+F4) and reopen it for changes to take effect.
Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"awesome-agent-skills": {
"command": "npx",
"args": ["awesome-agent-skills-mcp"]
}
}
}
OpenCode
Add to ~/.config/opencode/opencode.json:
{
"mcp": {
"awesome-agent-skills": {
"type": "local",
"command": ["npx", "awesome-agent-skills-mcp"],
"enabled": true
}
}
}
Environment Variables
| Variable | Default | Description |
|---|---|---|
SKILLS_REPO_URL | https://github.com/VoltAgent/awesome-agent-skills.git | Skills repository URL |
SKILLS_CACHE_DIR | .cache | Cache directory path |
SKILLS_SYNC_INTERVAL | 60 | Auto-sync interval in minutes (0 to disable) |
LOG_LEVEL | info | Logging level (debug, info, warn, error) |
Available Skills
The server provides access to 100+ skills from leading organizations:
Anthropic
Document processing, presentation creation, spreadsheet manipulation, PDF handling, algorithmic art, MCP building, and more.
| Skill | Description |
|---|---|
docx | Create, edit, and analyze Word documents |
pptx | PowerPoint presentation creation and editing |
xlsx | Spreadsheet manipulation with formulas |
pdf | PDF processing and form filling |
mcp-builder | Guide for creating MCP servers |
webapp-testing | Playwright-based web app testing |
Vercel
React and Next.js best practices, deployment, and performance optimization.
| Skill | Description |
|---|---|
react-best-practices | React performance optimization guidelines |
next-best-practices | Next.js conventions and patterns |
web-design-guidelines | UI/UX compliance review |
vercel-deploy | Deploy apps to Vercel |
Trail of Bits
Security analysis, smart contract auditing, and code review tools.
| Skill | Description |
|---|---|
building-secure-contracts | Smart contract security toolkit |
semgrep-rule-creator | Create custom Semgrep rules |
property-based-testing | Property-based testing guidance |
static-analysis | Static analysis tooling |
Hugging Face
ML model training, dataset management, and Hub operations.
| Skill | Description |
|---|---|
hugging-face-cli | HF Hub CLI operations |
hugging-face-datasets | Dataset creation and management |
hugging-face-model-trainer | Model fine-tuning with TRL |
hugging-face-evaluation | Model evaluation workflows |
Sentry
Code review, commit conventions, and PR automation.
| Skill | Description |
|---|---|
code-review | Sentry engineering code review practices |
commit | Conventional commit messages |
create-pr | PR creation following Sentry conventions |
find-bugs | Bug and vulnerability detection |
And Many More...
- Stripe - Payment integration best practices
- Expo - React Native app development
- n8n - Workflow automation patterns
- Sanity - CMS best practices
- Neon - Serverless Postgres
- Remotion - Programmatic video creation
MCP Tools
The server exposes four MCP tools:
list_skills
List all available skills with optional filtering.
// List all skills
{ }
// Filter by source
{ "source": "repository" }
// Filter by tag
{ "tag": "security" }
get_skill
Get detailed information about a specific skill.
{ "skill_id": "react-best-practices" }
invoke_skill
Invoke a skill with optional parameters.
{
"skill_id": "docx",
"parameters": {
"document_type": "report"
}
}
refresh_skills
Manually trigger a skills refresh from the repository.
{ }
Usage Examples
In GitHub Copilot Chat
@workspace Use the react-best-practices skill to review my React components
@workspace List all available security-related skills
@workspace Get the stripe-best-practices skill and apply it to my checkout code
In Claude
What skills are available for Next.js development?
Use the code-review skill to analyze my pull request
Development
Setup
git clone https://github.com/shadowrootdev/awesome-agent-skills-mcp.git
cd awesome-agent-skills-mcp
npm install
Build
npm run build
Run Tests
# Run all tests
npm test
# Run tests in watch mode
npm run test:watch
# Run integration tests only
npm run test:integration
Lint & Format
npm run lint
npm run format
Project Structure
awesome-agent-skills-mcp/
├── src/
│ ├── index.ts # Entry point
│ ├── server.ts # MCP server implementation
│ ├── config.ts # Configuration management
│ ├── models/
│ │ ├── skill.ts # Skill type definitions
│ │ ├── parameter.ts # Parameter schemas
│ │ ├── registry.ts # SkillRegistry class
│ │ └── repository.ts # Repository source model
│ ├── services/
│ │ ├── git-sync.ts # Git repository sync
│ │ ├── skill-parser.ts # Skill parsing from README
│ │ └── skill-executor.ts # Skill invocation
│ ├── cache/
│ │ └── cache-manager.ts # JSON-based caching
│ └── utils/
│ └── logger.ts # Structured logging
├── tests/
│ ├── unit/ # Unit tests
│ └── integration/ # Integration tests
├── dist/ # Compiled output
└── .cache/ # Runtime cache (gitignored)
API Reference
Skill Object
interface Skill {
id: string; // Unique identifier
name: string; // Display name
description: string; // Short description
source: 'repository' | 'local';
sourcePath: string; // GitHub URL or local path
content: string; // Full skill content (markdown)
parameters: ParameterSchema[];
metadata: {
author?: string;
version?: string;
tags?: string[];
requirements?: string[];
sourceOrg?: string; // GitHub organization
sourceRepo?: string; // GitHub repository
};
lastUpdated: Date;
}
Parameter Schema
interface ParameterSchema {
name: string;
type: 'string' | 'number' | 'boolean' | 'object' | 'array';
description: string;
required: boolean;
default?: unknown;
enum?: unknown[];
}
Troubleshooting
Skills Not Loading
- Check cache: Delete
.cachedirectory and restart - Verify network: Ensure access to GitHub
- Check logs: Set
LOG_LEVEL=debugfor verbose output
GitHub Copilot Not Seeing Skills
- Full restart required: Quit VS Code completely (Cmd+Q) and reopen
- Check config path: Ensure
.vscode/mcp.jsonis in the workspace root - Verify server: Run
npx awesome-agent-skills-mcpmanually to test
Connection Errors
# Test the server manually
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}' | npx awesome-agent-skills-mcp
Credits
This project is built on top of the incredible work by the open-source community:
Data Source
VoltAgent Awesome Agent Skills - A curated collection of AI agent skills maintained by VoltAgent. This MCP server fetches and serves skills from this repository, making them accessible to MCP-compatible AI assistants.
Skill Contributors
Skills in this collection are contributed by leading organizations including:
- Anthropic - Document processing, art generation, MCP building
- Vercel - React, Next.js, deployment
- Trail of Bits - Security analysis, smart contracts
- Hugging Face - ML workflows, model training
- Sentry - Code review, commit conventions
- Expo - React Native development
- Stripe - Payment integrations
- And many more contributors!
Technologies
- Model Context Protocol - The protocol specification
- @modelcontextprotocol/sdk - Official TypeScript SDK
- Zod - TypeScript-first schema validation
- simple-git - Git operations
Contributing
Contributions are welcome! Please read our contributing guidelines before submitting PRs.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
See our issue templates for reporting bugs, requesting features, or asking questions.
Documentation & Demo
GitHub Pages
You can enable GitHub Pages to host interactive documentation or demos:
-
Create your documentation (recommended: use
/docsfolder):- Create a
docs/directory in your repository root - Add an
index.htmlfile or use a static site generator like VitePress or Docusaurus - This keeps documentation separate from source code
- Create a
-
Enable GitHub Pages:
- Go to your repository Settings → Pages
- Select Source: Deploy from a branch
- Choose Branch:
mainand folder/docs(recommended) or/if deploying entire repo - Save and wait for deployment
This is useful for:
- Interactive API documentation
- Live demos of MCP server capabilities
- Tutorial walkthroughs
- Skill catalog browser
Note: Using the
/docsfolder is recommended as it keeps documentation organized and separate from source code. Only use/(root) if you want to deploy the entire repository as a website.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Related Projects
- VoltAgent - AI agent framework
- Awesome Agent Skills - The source skill collection
- MCP Servers - Official MCP server implementations
<p align="center"> Made with ❤️ for the AI agent community <br> <a href="https://github.com/VoltAgent/awesome-agent-skills">⭐ Star the Awesome Agent Skills repository</a> </p>
常见问题
io.github.shadowrootdev/awesome-agent-skills 是什么?
提供包含 100+ AI agent skills 的 MCP 服务器,整合 Anthropic、Vercel、Trail of Bits、Hugging Face 等资源。
相关 Skills
Claude接口
by anthropics
面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。
✎ 想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心
提示工程专家
by alirezarezvani
覆盖Prompt优化、Few-shot设计、结构化输出、RAG评测与Agent工作流编排,适合分析token成本、评估LLM输出质量,并搭建可落地的AI智能体系统。
✎ 把提示优化、LLM评测到RAG与智能体设计串成一套方法,适合想系统提升AI开发效率的人。
智能体流程设计
by alirezarezvani
面向生产级多 Agent 编排,梳理顺序、并行、分层、事件驱动、共识五种工作流设计,覆盖 handoff、状态管理、容错重试、上下文预算与成本优化,适合搭建复杂 AI 协作系统。
✎ 帮你把多智能体流程设计、编排和自动化统一起来,复杂工作流也能更稳地落地,适合追求强控制力的团队。
相关 MCP Server
顺序思维
编辑精选by Anthropic
Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。
✎ 这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。
知识图谱记忆
编辑精选by Anthropic
Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。
✎ 帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。
PraisonAI
编辑精选by mervinpraison
PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。
✎ 如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。