ai-slop-cleaner

AI code cleanup that preserves behavior requires a regression-tests-first workflow. This Skill automates smell-by-smell refactoring within a bounded scope, using staged passes and quality gates to ensure functionality remains intact.

Refactoring dead code and duplication in changed files is best handled by a structured cleanup workflow. This Skill executes targeted passes one smell at a time, providing an explicit plan and an evidence-dense report to verify correctness.

Regression tests verify AI code refactoring by validating behavior before and after changes. This Skill mandates a regression-tests-first approach, applying quality gates at each stage to prevent functionality regressions during cleanup.

AI slop cleanup operates on a bounded scope, targeting either a specific set of files or changed files. This minimizes risk by ensuring the cleanup workflow only refactors the explicitly defined target area.

Automated code quality refactoring for boundary violations is limited by scope and traceability. This Skill mitigates limitations by providing an explicit cleanup plan and an evidence-dense report to highlight remaining risks after the passes.

AI generated code needs a smell-by-smell cleanup workflow to systematically reduce slop while preserving behavior. Structured passes handle code smells like duplication and dead code incrementally, ensuring traceable and safe improvements.