Getting Started with AICoach

Everything you need to start using AICoach — from installing your first skill to querying the API.

What is AICoach?

AICoach is a platform that provides 169 production-ready AI skills and an MCP Registry with 9,000+ servers to supercharge your AI coding workflow.

Skills are structured workflows that turn your AI agent into a domain expert — they work with Claude Code, Cursor, and any agent that supports skills integration. MCP servers connect your agent to databases, APIs, and developer tools.

Install Your First Skill

The fastest way to get started is with the Skillfish CLI. Install a skill with a single command: 

skillfish add johnefemer/skillfish/skills/code-review-coach

This downloads the skill's SKILL.md and supporting files into your project. Your AI agent discovers and uses the skill automatically when you describe a matching task.

To install all skills at once: 

skillfish add johnefemer/skillfish --all

Browse the MCP Registry

Visit aicoach.pw/mcp to explore 9,000+ MCP servers across 21 categories including databases, APIs, DevOps, AI/ML, and more.

  • Search — Find servers by name, description, or capability
  • Filter — By transport type (stdio, SSE, HTTP), pricing, or category
  • Detail pages — Capabilities, install commands, environment variables, README, FAQ
  • Export — Download Claude Desktop config with one click

Generate an API Key

To use the AICoach API programmatically, you'll need an API key:

  1. Sign in with your GitHub account at aicoach.pw
  2. Go to Account → API Keys
  3. Click Create New Key
  4. Copy the key — it starts with mcp_ and is shown only once

Use the key in the Authorization header: 

Authorization: Bearer mcp_your_key_here

Use the API

The AICoach API is spec-compliant and supports cursor-based pagination. Here are some quick examples:

List MCP servers

curl "https://aicoach.pw/api/v1/mcp/servers?search=postgres&limit=5"

List skills

curl "https://aicoach.pw/api/v1/skills/list?q=review&limit=5"

Get a specific server

curl "https://aicoach.pw/api/v1/mcp/by-slug/modelcontextprotocol--filesystem"

Next Steps