CodingText outputGuided
Code Review Prompt That Checks If It Actually Works
Reviews code for real bugs and broken cases first — kindness is optional. Why it matters: pretty code that fails still fails.
Scanned · no issuesReady to use
Prompt
Brutal-but-useful code review. Correctness first.
Context handling:
- First use relevant information already available from the conversation, attachments, or connected sources.
- Do not ask me to repeat details you already have.
- If a required detail is missing, ask one short follow-up.
- State important assumptions. Never invent facts, metrics, employers, prices, birth data, or credentials. Use [NEEDED] when something is missing.
Code / diff:
{{code}}
Intended behavior:
{{intent}}
Output:
1) Blockers (must-fix)
2) Likely bugs / edge cases
3) Tests you should add
4) Nits (only after blockers)
Do not rewrite everything — be precise.Create your final prompt
Add your context and generate
Fill in the required variables below. Optional variables can be left blank and will remain as placeholders.
Paste code or diff
What it should do
What to expect
Example output
A clear structured answer you can act on.
Example context
Example input
Paste your details into the variables.
Coding workflow prompts
More in this series
- Performance Profiling Plan — ChatGPT Prompt
- Python CLI Scaffold — ChatGPT Prompt
- Accessible React Component — ChatGPT Prompt
- Safe Refactor Plan — ChatGPT Prompt
- Regex with Tests — ChatGPT Prompt
- Pull Request Summary — ChatGPT Prompt
- Security-Focused Code Review — ChatGPT Prompt
- SQL Query Optimization — ChatGPT Prompt
- System Design Interview Practice — ChatGPT Prompt
- STRIDE Threat Model — ChatGPT Prompt
- TypeScript Types from JSON — ChatGPT Prompt
- Unit Test Suite from Spec — ChatGPT Prompt
Keep exploring
Discussion
Comments (0)
Sign in to leave a comment.
Loading comments…