What problem does it solve? Codebases accumulate dead code, speculative abstractions, and hand-rolled utilities that duplicate the standard library. This Skill scans the whole repository and produces a ranked list of what to delete, simplify, or replace, so you can cut bloat without a manual line-by-line review. ## Core Features & Use Cases - Whole-repo scan: Unlike a diff-based review, it audits the entire tree for over-engineering patterns. - Tagged findings: Each finding is labeled delete, stdlib, native, yagni, or shrink with a concrete replacement suggestion and file path. - Ranked one-shot report: Findings are ordered biggest cut first, ending with an estimate of net lines and dependencies removable. - Use Case: Before a major refactor, run the audit to find single-implementation interfaces, factories with one product, dead config flags, and wrappers that only delegate, then hand the list to your team as a cleanup backlog. ## Quick Start Ask the AI to audit this codebase for over-engineering and list what can be deleted or replaced with standard library equivalents.
