What problem does it solve? Completed code changes often ship with undetected bugs, plan deviations, and quality gaps because self-review is unreliable and inline review burns the coordinator's context window. This Skill structures the review process by dispatching a dedicated reviewer subagent with precisely crafted context. ## Core Features & Use Cases - Subagent-Based Review: Dispatches a general-purpose reviewer subagent with a ready-made prompt template covering plan alignment, code quality, architecture, testing, and production readiness. - Severity-Calibrated Feedback: Returns findings categorized as Critical, Important, and Minor with file:line references, plus a clear merge verdict. - Read-Only Review Safety: Instructs the reviewer to never mutate the working tree, index, or HEAD, using git diff and git show for inspection. - Use Case: After finishing a feature task, capture the base and head commit SHAs, dispatch the reviewer with the template, fix Critical and Important issues, then proceed to the next task or merge. ## Quick Start Ask the AI to request a code review of the changes between the previous commit and HEAD using the code-reviewer template before merging.
