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 reading every file yourself. ## Core Features & Use Cases - Whole-repo over-engineering scan: Unlike a diff-based review, it audits the entire tree and ranks findings biggest cut first. - Tagged findings: Each finding is labeled delete, stdlib, native, yagni, or shrink, with a concrete replacement named. - Net impact summary: Ends with an estimate of removable lines and dependencies, e.g. net: -400 lines, -3 deps possible. - Use Case: Before a major refactor, ask for an audit to find single-implementation interfaces, dead config flags, and wrappers that only delegate, then plan the cleanup sprint. ## Quick Start Ask the AI to audit this codebase for over-engineering and list what can be deleted or replaced with stdlib equivalents.
