process-review-requesting-code-review

What problem does it solve? Code you wrote yourself is the hardest to review objectively, and skipping review lets bugs, security issues, and plan deviations cascade into later work. This Skill structures the process of requesting an independent code review so issues are caught before merging to main. ## Core Features & Use Cases - Subagent Review Dispatch: Fills a ready-made reviewer prompt template with a description, requirements, and git SHA range, then dispatches a fresh-context subagent that never saw your session. - Severity-Calibrated Feedback: The reviewer returns strengths, issues categorized as Critical, Important, or Minor with file:line references, recommendations, and a merge-readiness verdict. - Gate Integrity Guidance: Explains why an LLM reviewer finds issues but cannot authorize merges, and why verification gates must live outside the actor being checked. - Use Case: After completing a feature task, you capture the base and head SHAs, dispatch the reviewer subagent with the plan reference, fix the Important issues it reports, and only then proceed to the next task or merge. ## Quick Start Ask the AI to request a code review of the changes between the current HEAD and the previous commit using the code-reviewer template before merging.