Originally published at heyuan110.com
Claude Code has three distinct extension mechanisms: MCP (Model Context Protocol), Skills, and Hooks. They look related on the surface, but they operate at fundamentally different layers:
- Hooks (bottom layer): Lifecycle event automation — "what must always happen"
- MCP (middle layer): External tool connections via open protocol — "what can be done"
- Skills (top layer): Reusable workflows and domain knowledge — "how to do things well"
This guide covers:
- Three-layer architecture diagram
- Side-by-side comparison across 8 dimensions
- Same task implemented three different ways
- Decision framework: when to use which
- Common mistakes and how to avoid them
If you found this useful, check out my blog for more AI engineering guides.
Top comments (0)