What problem does it solve? Cleaning up freshly written code is tedious and easy to skip, and a single broad review often misses duplication, quality issues, or inefficiencies hiding across files. This Skill runs three focused reviewers in parallel over your recent diff, aggregates their findings, and applies only the fixes that are safe to apply. ## Core Features & Use Cases - Parallel Three-Reviewer Analysis: Launches reuse, quality, and efficiency reviewers concurrently via delegate_task batch mode, each searching the full codebase for evidence with file:line citations. - Risk-Tiered Fix Application: Classifies findings as SAFE (auto-apply), CAREFUL (apply with test verification), or RISKY (flag for human review), so behavior-changing edits are never applied silently. - Flexible Scoping and Dry Run: Supports focusing on one category, scoping to staged changes, the last commit, a branch, or specific files, and running in report-only mode. - Use Case: After finishing a feature branch, say "simplify my changes" to get duplicated logic replaced with existing utilities, redundant state removed, and N+1 patterns flagged — with tests re-run after every applied fix. ## Quick Start Ask the agent to simplify my recent code changes and report what it fixed and what it deliberately skipped.
