What problem does it solve? Completed code often goes unreviewed or gets only a shallow self-review, letting bugs, plan deviations, and architectural issues cascade into later work. 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 subagent with a ready-made reviewer prompt template, keeping the diff evaluation out of your main context window. - Structured Feedback: Returns findings categorized as Strengths, Critical, Important, and Minor issues with file:line references and a clear merge verdict. - Use Case: After finishing a feature task, you capture the base and head git SHAs, fill in the code-reviewer.md template with a description and requirements, and receive a calibrated assessment before proceeding to the next task or merging to main. ## Quick Start Request a code review of my last commit against the task requirements before I continue to the next task.