You can check the quality of any skill project with a two-part review. The first part uses deterministic code checks for structure, scripts, tests, and safety. The second part uses an LLM deep review to find issues and improvements.
This method gives you a reproducible score for each skill. You can set a score threshold to gate merges. If a skill scores low, you get concrete items to fix. The tool works across different projects using the --project-root option.
Global
mkdir -p ~/.claude/skills/dual-axis-skill-reviewerProject
mkdir -p .claude/skills/dual-axis-skill-reviewerSource 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