awesome-agent-skills — Claude Code MCP server: setup and overview
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.
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-mcpWhat awesome-agent-skills 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.
What it helps with
- 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 for the agent
- Generate a docx file named
report.docxsummarizing 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
How to install awesome-agent-skills
Platform CLI
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-mcpReplace <…> with your own values
Platform CLI
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-mcpReplace <…> with your own values
Config file
{
"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
Config file
{
"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
Platform CLI
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-mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about awesome-agent-skills
How do I install awesome-agent-skills in Claude Code?
Run claude mcp add awesome-agent-skills -- npx -y awesome-agent-skills-mcp in your terminal. To adjust cache paths or sync intervals, supply additional --env flags before the transport arguments.
What does awesome-agent-skills do?
It provides your assistant with access to over 100 specialized agent skills. The catalog covers document creation, security auditing, web testing, and machine learning pipelines.
How do I turn off automatic skill syncing?
Set the SKILLS_SYNC_INTERVAL environment variable to 0. The server will stop pulling changes from GitHub and rely entirely on the local cache directory.
