Hooks and Skills are different abstractions for different jobs, not interchangeable. Plain-English decision guide with real examples from a production setup.
Originally published on rikuq.com. Republished here for Dev.to's readers.
Claude Code shipped Hooks and Skills near each other in 2026, and they get conflated. They solve different problems and the wrong choice burns context, breaks reliability, or both.
The 30-second answer: Hooks run on lifecycle events whether you want them to or not. Skills run when Claude decides they're relevant. That single distinction tells you which one to pick almost every time.
TL;DR
Hooks
Claude Code Skills are reusable, AI-callable workflows defined in SKILL.md files. Auto-discovered, invoked via Skill tool,…
The dotfiles piece from May 22 named hooks as one component of a personal AI stack and moved on. They...
Author(s): Narmadha Originally published on Towards AI. If you read Part 1, you know the why behind Claude Code Hooks: they turn…
#58 | The pattern behind Claude Code's extensibility - and a working implementation in 100 lines of Python.
Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...
Your git log and memory files are the most honest source for creating custom Claude Code skills. How to audit them, identify…
