What problem does it solve? Code issues caught late compound into larger problems, and self-review often misses defects in your own work. This Skill provides a structured workflow for dispatching an independent code reviewer subagent that evaluates completed work against its plan before issues cascade. ## Core Features & Use Cases - Subagent-Based Review: Dispatches a general-purpose subagent with a precisely crafted prompt template so the reviewer sees only the work product, not your session history. - Structured Review Template: The code-reviewer.md template enforces severity-calibrated feedback (Critical, Important, Minor) with file:line references and a clear merge verdict. - Git Range Review: Reviews a specific commit range using BASE_SHA and HEAD_SHA, with read-only rules that prevent the reviewer from mutating your working tree. - Use Case: After completing a task in subagent-driven development, capture the base and head commit SHAs, dispatch the reviewer with the template, fix Critical and Important issues, then proceed to the next task. ## Quick Start Ask the AI to request a code review of your latest commits using the code-reviewer template before merging to main.