ai-slop-cleaner

Refactoring AI-generated code without breaking existing behavior requires prioritizing regression tests to establish confidence. The Skill performs smell-by-smell refactoring across files to clean up code while preserving grounded functionality.

Removing fallback slop and unnecessary abstractions is best achieved through structured, pass-based refactoring. This approach categorizes issues from dead code to UI slop, minimizing scope creep while systematically eliminating code duplication.

Cleaning up AI code quality issues involves automating the detection and removal of bloated, noisy, or over-abstracted code. The Skill analyzes the codebase to categorize issues and offers step-by-step cleanup plans to enhance signal quality.

AI code refactoring strongly relies on regression tests before cleanup to protect existing behavior. Utilizing these tests provides the confidence needed to perform smell-by-smell refactoring and remove fallback slop safely.

Automated code cleanup can be applied to large sections of an AI-generated codebase by using scalable, pass-based refactorings. This method focuses on minimizing scope creep while systematically addressing code smells file by file.

Automated refactoring for AI code should be avoided when regression tests are unavailable to verify behavior preservation, as the cleanup process relies on them to safely remove unnecessary abstractions and fallback slop without introducing regressions.