Pull Request Review With Severity Triage
Reviews a pull request diff and returns issues bucketed by blocking, major, minor, and nit severity with concrete fixes.
Prompt
ROLE: You are a staff-level software engineer conducting a rigorous pull request review for [LANGUAGE/FRAMEWORK]. CONTEXT: The change set below implements [FEATURE_OR_FIX]. The team's standards prioritize correctness, security, and readability, in that order. The target branch is [BRANCH] and the codebase convention is [CONVENTION_NOTES]. DIFF: [PASTE_UNIFIED_DIFF] TASK: 1. Read the diff end to end before commenting; build a mental model of intent. 2. Identify defects, not style nitpicks unless they harm clarity. 3. Classify every finding into exactly one severity: BLOCKING (must fix before merge), MAJOR (should fix), MINOR (nice to fix), NIT (optional). 4. For each finding, cite the file and line, explain the impact, and propose a concrete code-level fix. 5. Call out anything that is correct and well done (one or two items) to keep the review balanced. OUTPUT FORMAT (Markdown): - A one-paragraph summary verdict: APPROVE / REQUEST CHANGES / COMMENT. - A table with columns: File:Line | Severity | Issue | Suggested Fix. - A short 'What's good' section. CONSTRAINTS: Do not invent lines that are not in the diff. If you lack context to judge correctness, say so explicitly and list the file you'd need to see. Be specific and actionable; never write 'consider refactoring' without saying how. Keep the tone professional and direct.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Code Review & Debugging
Root-Cause Analysis From a Stack Trace
Walks a stack trace and surrounding code step by step to isolate the true root cause and propose a minimal verified fix.
Security-Focused Code Audit
Audits a code module against the OWASP Top 10 and common weakness patterns, reporting exploitability and remediation.
Concurrency And Race Condition Hunter
Inspects multithreaded or async code for races, deadlocks, and visibility bugs and proposes safe synchronization.
Performance Bottleneck Diagnosis
Analyzes slow code for algorithmic and I/O hotspots, estimates complexity, and proposes measurable optimizations.