What problem does it solve? Code changes often get merged without independent verification, letting bugs, plan deviations, and quality issues cascade into later work. This Skill structures the process of requesting an unbiased code review from a fresh subagent that sees only the work product, not your session history. ## Core Features & Use Cases - Subagent-Based Review: Dispatches a general-purpose reviewer subagent with a precisely crafted prompt containing the description, requirements, and git SHA range. - Structured Review Template: The code-reviewer.md template enforces severity-calibrated feedback (Critical, Important, Minor) with file:line references and a clear merge verdict. - Workflow Integration: Defines mandatory review checkpoints after each task in subagent-driven development, after major features, and before merging to main. - Use Case: After completing a task that adds index verification functions, you capture the base and head SHAs, dispatch the reviewer with the plan reference, receive categorized issues, fix the Important ones, and proceed to the next task with confidence. ## Quick Start Ask the AI to request a code review of your latest commits using the code-reviewer template before merging to main.