Code Review Focused on One Dimension
Get a focused code review along a single axis — security, performance, readability, or correctness — with every finding tied to a line and a severity.
0 likes
0 dislikes
Sign in to rate this prompt
Prompt
Review the code below for **{{focus}}** issues only (for example: security, performance, readability, correctness, or maintainability). Ignore unrelated concerns so the review stays sharp.
Code:
{{code}}
Context (optional — language, framework, what it's supposed to do, constraints):
{{context}}
Return your findings as a table with these columns:
| Severity (blocker / high / medium / low) | Location (line or function) | Issue | Why it matters | Suggested fix |
Guidelines:
- Cite a specific line or function for every finding — no vague, whole-file remarks.
- Order findings by severity, most serious first.
- If a piece of code is genuinely good and worth keeping as-is, you can note that briefly at the end.
- If something looks wrong but you can't be sure without more context, say so instead of guessing.
Why this prompt works
-
How to Deploy an AI Agent
Every deployment problem follows from one property: you don't know how long a run takes, because you didn't write the path. Why the run m...
Read the guide → -
MCP Authorization and OAuth
Optional until you opt in, then very specific. Why the resource parameter is mandatory even when the server ignores it, why PKCE doesn't ...
Read the guide → -
MCP Transports: stdio vs Streamable HTTP
There are two transports now, not three, and the one that vanished is the one most tutorials still document. What each is exposed to, why...
Read the guide →