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 with precisely crafted context, catching Critical and Important issues before they cascade into more work. ## Core Features & Use Cases - Subagent-Based Review: Dispatches a general-purpose subagent with a ready-made reviewer prompt template, keeping the reviewer focused on the work product rather than your session history. - Structured Feedback Format: Returns categorized findings (Critical, Important, Minor) with file:line references, plus strengths, recommendations, 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, you run the review workflow before starting the next task. The reviewer flags a missing progress indicator as Important, you fix it immediately, and proceed with confidence. ## Quick Start Ask the AI to request a code review of your recent commits using the code-reviewer template before merging to main.
