# awesome-agent-skills

An MCP server providing over 100 curated agent skills from major engineering teams. It connects workflows for code review, document handling, and ML pipelines directly to your assistant.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 26
- Author: shadowrootdev
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/shadowrootdev/awesome-agent-skills-mcp
- Updated: 2026-04-13
- HTML: https://affpapa.org/en/nevibecode/mcp/awesome-agent-skills

## What it does

The server exposes skills from the VoltAgent catalog directly to MCP-compatible clients. It bundles ready-made instructions from multiple engineering teams. Anthropic supplies handlers for docx documents and spreadsheet formulas, Vercel provides optimization practices for Next.js and React, while Trail of Bits adds security audits and Semgrep rule generation. Hugging Face contributes routines for training runs and dataset management.

The package is built with TypeScript and Zod schema validation. It writes skills to a local JSON cache directory for instant startup. An automated sync process pulls repository updates every 60 minutes by default. You can disable background fetching by setting `SKILLS_SYNC_INTERVAL` to 0.

Running the server requires Node.js alongside npm or yarn. Without network reachability to GitHub, initial repository sync fails immediately because the server cannot clone remote skill definitions.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `SKILLS_REPO_URL`, `SKILLS_CACHE_DIR`, `SKILLS_SYNC_INTERVAL`, `LOG_LEVEL` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env SKILLS_REPO_URL=<SKILLS_REPO_URL> --env SKILLS_CACHE_DIR=<SKILLS_CACHE_DIR> --env SKILLS_SYNC_INTERVAL=<SKILLS_SYNC_INTERVAL> --env LOG_LEVEL=<LOG_LEVEL> --transport stdio awesome-agent-skills -- npx -y awesome-agent-skills-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add awesome-agent-skills --env SKILLS_REPO_URL=<SKILLS_REPO_URL> --env SKILLS_CACHE_DIR=<SKILLS_CACHE_DIR> --env SKILLS_SYNC_INTERVAL=<SKILLS_SYNC_INTERVAL> --env LOG_LEVEL=<LOG_LEVEL> -- npx -y awesome-agent-skills-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "awesome-agent-skills": {
            "command": "npx",
            "args": [
                "-y",
                "awesome-agent-skills-mcp"
            ],
            "env": {
                "SKILLS_REPO_URL": "<SKILLS_REPO_URL>",
                "SKILLS_CACHE_DIR": "<SKILLS_CACHE_DIR>",
                "SKILLS_SYNC_INTERVAL": "<SKILLS_SYNC_INTERVAL>",
                "LOG_LEVEL": "<LOG_LEVEL>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "awesome-agent-skills": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "awesome-agent-skills-mcp"
            ],
            "env": {
                "SKILLS_REPO_URL": "<SKILLS_REPO_URL>",
                "SKILLS_CACHE_DIR": "<SKILLS_CACHE_DIR>",
                "SKILLS_SYNC_INTERVAL": "<SKILLS_SYNC_INTERVAL>",
                "LOG_LEVEL": "<LOG_LEVEL>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e SKILLS_REPO_URL=<SKILLS_REPO_URL> -e SKILLS_CACHE_DIR=<SKILLS_CACHE_DIR> -e SKILLS_SYNC_INTERVAL=<SKILLS_SYNC_INTERVAL> -e LOG_LEVEL=<LOG_LEVEL> awesome-agent-skills npx -y awesome-agent-skills-mcp
```
Replace <…> with your own values

## When to use it
- generate docx, pptx, and xlsx files with formulas
- apply verified Next.js and React best practices
- audit smart contracts and generate Semgrep security rules
- manage datasets and model training workflows for Hugging Face

## Example prompts
- Generate a docx file named `report.docx` summarizing our performance benchmarks
- Review our components against Vercel best practices for React and Next.js
- Write a Semgrep rule to detect insecure calls in this smart contract

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md