human-readable-refactor
Refactors AI-like code into clearer, repository-native code without changing behavior.
Refactors AI-like code into clearer, repository-native code without changing behavior.
human-readable-refactor performs focused, behavior-preserving cleanup over a file, directory, or diff. It removes comments that merely narrate code, improves vague private names, simplifies control flow, and deletes dead or duplicated logic while preserving public APIs and observable error behavior. It favors local conventions and narrow verification, and explicitly does not hide AI use, rewrite authorship, or introduce broad architecture changes.
Resource types
Use cases
Platforms
Capabilities
Review high-risk code through independent specialist agents and synthesis.
Audit a repository locally and turn cited findings into clear priorities.
Audience
Public GitHub facts last synced Jul 10, 2026.
Review code with adjustable roast levels and actionable fixes.
Score and audit Claude SKILL.md files