A coding prompt for review a pull request by severity. It gives Claude and Cursor a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
4.7(20 ratings)534 copies
Updated By Site Admin
51 words · v1.0
Fill in the blanks · 2 variables
Claude promptReplace every highlighted token before sending
<task>
Review this diff as a staff engineer. Return findings grouped as blocker, should-fix and nit. For each: file, line, the problem, why it matters, and a concrete suggestion. Check correctness, security, error handling, tests and performance in that order. If there are no blockers, say so explicitly.
Diff:
{diff}
Context:
{context}
</task>
Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Claude and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({diff}, {context}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Reproduce the bug, review the diff and run the tests in a clean environment.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Diff: Paste the pull request diff here.
Context: Add the relevant business or project context.
Example output
**Diagnosis:** the handler reads `req.body` before the JSON middleware runs, so the body is undefined on POST requests.
**Fix:** move the middleware above the route registration and add a guard for missing bodies. No public API changes.
**Verification:** added a failing test for an empty JSON body, confirmed it fails, applied the fix, then ran the full suite. The test now passes and the unrelated snapshot tests are unchanged.
Tips for a better result
Paste the full error and the smallest relevant code, not a screenshot of the stack trace.
Ask for a plan before allowing multi-file edits; it prevents sprawling refactors.
Require a failing test first and a verification command at the end.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Accepting a confident fix without reproducing the bug or running tests.
Letting the assistant rewrite entire files when a three-line diff would do.
Pasting secrets, tokens or customer data into a hosted model.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the review a pull request by severity prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A coding prompt for convert a design into accessible components. It gives v0 and Cursor a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
This copy-ready coding prompt helps you refactor for readability without changing behaviour with fewer blank-page decisions. Paste it into Cursor and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
This copy-ready coding prompt helps you write a migration with a rollback plan with fewer blank-page decisions. Paste it into Claude and ChatGPT, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
ClaudeChatGPT
4.9(55)605 copies
SA
Written and reviewed by Site Admin
Author & Platform Administrator
Administrator and lead editor at AIPrompt123, curating high-performance AI prompts, SEO/AEO/GEO strategies, and developer repositories.
Last reviewed 18 December 2025 · version 1.0 · tested on Claude, Cursor, GitHub Copilot
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.