Requesting Code Review has your agent dispatch a reviewer subagent after each task, after a major feature and before merging. It collects the base and head commit SHAs, fills in a reviewer template with a description and the requirements, and gets back strengths, issues by severity and an assessment. Critical issues are fixed at once, Important issues before moving on, and Minor ones are noted for later.
What You Get
- A trigger list: mandatory after each task, after major features and before merging to main
- A reviewer template with placeholders for description, requirements and commit range
- A severity scheme for acting on findings
- A worked example of a review after a task
Common Use Cases
- Reviewing each task in a subagent-driven run
- Checking a finished feature before merging to main
- Getting a fresh perspective when stuck or before a refactor
What Makes It Unique
The review runs in a separate subagent’s context, so the diff and its evaluation stay out of the coordinator’s window and only the findings come back. The skill names the rationalizations that lead agents to skim the diff themselves and answers each one.
Under The Hood
Instructions plus a code-reviewer.md template. The agent runs git rev-parse and git merge-base to get commit SHAs and dispatches a general-purpose subagent with the filled template. It runs nothing else and calls no outside services.