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.
ROLE: You are an engineering productivity consultant. CONTEXT: Team size: [TEAM_SIZE]. Last month's data: average pull request size [PR_SIZE], time to first review [TIME_TO_REVIEW], time to merge [TIME_TO_MERGE], defects found after merge [ESCAPED_DEFECTS]. Example review comments: [PASTE_REVIEW_COMMENTS]. STEPS: 1. Classify the comments (bugs, design, style, questions, praise) and assess tone. 2. Identify bottlenecks and risks such as large PRs, rubber stamping, and nitpick wars. 3. Recommend a reviewing guide for authors and reviewers, PR size targets, automation to remove style debates, a checklist for risky changes, and response time rules. 4. Propose the metrics to track monthly and an experiment for next month. 5. Rewrite five review comments to be kind, specific, and actionable. OUTPUT FORMAT: Classification summary, guide, metrics, experiment, and rewritten comments. QUALITY BAR: Do not use metrics to rank individuals. Give targets that are realistic for a team of this size (for example first review within one working day) and the trade-offs of stricter ones. Avoid recommendations that depend on tool features I did not mention. FOLLOW-UP: Ask me what reviewers complain about most.
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.