Evaluation Methodology
wshobson/agentsPlugin quality is measured with a clear and detailed system. Three different layers check how well a skill works. Static analysis looks at the structure and writing. An AI judge reviews the skill by running example tasks. A simulation tests the skill with many real prompts. Each layer gives a score for ten dimensions like triggering accuracy and output quality. These scores combine into one final score. Badges show if a skill is excellent or needs work. This helps you understand why a score is low and how to make your skill better.
Add Evaluation Methodology skill to your workflow
Global
mkdir -p ~/.claude/skills/evaluation-methodologyProject
mkdir -p .claude/skills/evaluation-methodologySource Repository
More Code Review & Quality Claude Code Skills
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