📄️ MCP
MCP (Model Context Protocol) is the interface layer that lets an AI agent connect to tools and data sources in a structured way.
📄️ Skills
Skills are reusable instruction bundles that extend what an AI agent can do reliably.
📄️ Hooks
In Claude Code, hooks can be managed through the /hook command so you can automate checks and policy steps at key moments.
📄️ Plugins in Claude Code
Plugins extend agent capability for specific domains (for example: GitHub workflows, docs translation, design tooling, or product-specific operations).