Skip to content

skills

Skills library for AI coding agents

build.protocol_tooling.mcp#skills#ai#agent#cli#typescript#bun#claude#codex#gemini#mcp

Install skills in your MCP client

skills is a Model Context Protocol server. Add it to your MCP client config once, restart, and the server's tools become available to your AI assistant. The same JSON snippet below works across all four major clients — only the config file path differs.

  1. Locate your client's MCP config file.
    • Cursor: ~/.cursor/mcp.json
    • Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
    • Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json
    • VS Code: Settings → Extensions → MCP
    • Windsurf: Settings → MCP Servers
  2. Add skills to the mcpServers map — paste the snippet below into your config file. If you already have other MCP servers, merge the entry into the existing mcpServers object.
  3. Restart your client so it picks up the new server.
  4. Verify — ask the assistant to list available tools; skills's tools should appear.
{
  "mcpServers": {
    "skills": {
      "command": "npx",
      "args": [
        "-y",
        "@hasna/skills"
      ]
    }
  }
}

Install skills in Cursor

Open ~/.cursor/mcp.json in your editor, paste the snippet above into mcpServers, save, and restart Cursor. skills will show up in the assistant's tool list on next launch.

Install skills in Claude Desktop (macOS)

Open ~/Library/Application Support/Claude/claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (macOS). skills will show up in the assistant's tool list on next launch.

Install skills in Claude Desktop (Windows)

Open %APPDATA%\Claude\claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (Windows). skills will show up in the assistant's tool list on next launch.

Install skills in VS Code

Open Settings → Extensions → MCP in your editor, paste the snippet above into mcpServers, save, and restart VS Code. skills will show up in the assistant's tool list on next launch.

npm package: @hasna/skills

Transport

skills supports the following MCP transports. Most AI clients use stdio by default for locally-installed servers.

stdio

From the skills README

# @hasna/skills Skills library for AI coding agents — discover, pin, and run reusable capabilities through the Skills CLI and MCP server. Registers with Claude, Codex, Cursor, OpenCode, Gemini, Windsurf and Pi, and works with any MCP host. [![npm](https://img.shields.io/npm/v/@hasna/skills)](https://www.npmjs.com/package/@hasna/skills) [![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE) ## Install The CLI ```bash bun install -g @hasna/skills ``` Requires [Bun](https://bun.sh/) 1.0+. ## Quick Start ```bash # Browse skills interactively skills # Point the CLI at a Skills API server for server-owned (premium) skill runs skills setup --api-url https://skills.example.com skills auth login --api-key "$SKILLS_API_KEY" # With no API URL configured, skills simply r

Other Model Context Protocol servers in the same space as skills. Each one adds different capabilities to your AI assistant — pick based on the data sources or workflows you need.

Browse the full MCP server directory or use Stork's one-line install to let your agent pick the right server automatically.