Code Review Process and Pull Request Quality Audit
Improve how the team reviews code.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Audit how my team reviews code. Team size and workflow: [TEAM_AND_WORKFLOW]. Data from the last 30 days: number of pull requests, median size, time to first review, time to merge, rework rounds, reverted changes, and defects found after merge: [REVIEW_DATA]. Examples of review comments, good and bad (anonymized): [REVIEW_COMMENT_EXAMPLES]. Score each from 1 to 5 with evidence: 1. Size: small changes that can be understood in one sitting. 2. Description quality: why, what, and how to test. 3. Speed: time to first response. 4. Depth: design and correctness, not only style. 5. Tone: respectful, specific, and question-based. 6. Automation: formatting, linting, tests, and security checks handled by tools. 7. Ownership and coverage: who reviews what; avoiding single reviewers. 8. Learning: knowledge shared, patterns documented. 9. Outcomes: defects escaping review. Return the scorecard, the three biggest problems, a pull request template, comment conventions (blocking versus non-blocking), working agreements with numbers to agree as a team, and a 4-week experiment. Do not use the data to rank individuals.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.