What problem does it solve? Completed code changes often go unreviewed or get shallow self-review, letting bugs and architectural issues cascade into later work. This Skill structures the process of dispatching an independent code reviewer subagent with precisely crafted context before merging or proceeding. ## Core Features & Use Cases - Structured Review Dispatch: Provides a repeatable workflow for capturing git SHAs and dispatching a general-purpose reviewer subagent with a fill-in template. - Severity-Calibrated Feedback: The reviewer template enforces categorized output (Critical, Important, Minor) with file:line references and a clear merge verdict. - Read-Only Review Safety: Instructs the reviewer to never mutate the working tree, HEAD, or branch state during inspection. - Use Case: After finishing a feature task, you run git rev-parse to get the base and head SHAs, dispatch the reviewer with the template, receive categorized issues, fix the Important ones, and only then continue to the next task. ## Quick Start Ask the AI to request a code review of your latest commits using the requesting-code-review skill before merging to main.