This set of rules helps AI agents write code that is clean and easy to understand. The focus is on keeping things simple and direct. No one wants confusing code that is hard to fix.
Every function should do just one thing. Names should reveal what the code does without needing a comment. Code should be small and flat instead of long and deeply nested.
These standards stop over-engineering and useless comments. The goal is always working code that is easy to change later. Any developer who reads this code will thank you.
Global
mkdir -p ~/.claude/skills/clean-codeProject
mkdir -p .claude/skills/clean-codeSource Repository
Improve Codebase Architecturemattpocock/skills
Scan your codebase for architecture improvements with visual reports and pick one to refactor
Web Design Guidelinesvercel-labs/agent-skills
Review your UI code for compliance with web interface guidelines
Caveman Reviewjuliusbrussee/caveman
Ultra-compressed one-line code review comments that cut noise
Zoom Outmattpocock/skills
Get a big picture view of your code with a simple map of modules and callers
Codebase Designmattpocock/skills
Create deep modules with tiny interfaces and lots of hidden logic for testability
Requesting Code Reviewobra/superpowers
Catch code issues early with focused automated reviews before every merge
Request Refactor Planmattpocock/skills
Plan safe code refactors with tiny commits and clear GitHub issues
Receiving Code Reviewobra/superpowers
Think first, then code. Verify feedback before making changes. Stay objective