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 reports exactly what to delete, simplify, or replace, ranked by biggest cut first. ## Core Features & Use Cases - Whole-Repo Over-Engineering Scan: Hunts dead code, single-implementation interfaces, one-product factories, delegating wrappers, unused config flags, and hand-rolled stdlib equivalents. - Tagged Findings: Classifies each finding as delete, stdlib, native, yagni, or shrink, with a concrete replacement named for each. - Ranked One-Shot Report: Outputs one line per finding ordered by impact, ending with a net estimate of removable lines and dependencies. - Use Case: Before a refactor sprint, ask for an audit of your repo to find bloat such as a custom retry helper that the standard library already provides, then hand the ranked list to your team as a deletion 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.
