What problem does it solve? Cleaning up recent code changes by hand is slow and easy to get wrong: duplicated logic, redundant state, and inefficiencies slip through when one reviewer tries to check everything at once. This Skill runs three focused reviewers in parallel over your git diff, aggregates their findings, and applies only the fixes worth applying. ## Core Features & Use Cases - Parallel Three-Agent Review: Launches reuse, quality, and efficiency reviewers concurrently via batch delegation, so you pay the latency of one review instead of three. - Risk-Tiered Fix Application: Auto-applies SAFE fixes (unused imports, dead code), verifies CAREFUL refactors with tests, and flags RISKY changes (API renames, N+1 restructuring) for human approval. - Evidence-Based Findings: Each reviewer searches the codebase with git blame and grep before flagging anything, reporting file:line evidence with confidence levels. - Use Case: After finishing a feature branch, say "simplify my changes" to get duplicated helpers consolidated, redundant state removed, and N+1 patterns flagged — with tests re-run after every applied fix. ## Quick Start Ask the assistant to simplify your recent changes, optionally adding a focus like efficiency or a dry-run modifier to review findings without applying them.
