PromptKit
← All prompts
PromptBuild · CodingPro

Get a code review that catches what linters and tests miss

Style is checkable by machine. The expensive bugs live in the assumptions nobody wrote down.

Use it for
Anyone about to merge code who wants a real review, not a style pass.

A lot of "review my code" requests get answered with formatting suggestions and naming nitpicks — the exact things a linter already checks for free. The valuable review is the one that finds what automated tools structurally can't: unstated assumptions, missing edge cases, and error paths that silently swallow failures. That requires asking for it specifically, since a generic review request defaults to the easy, visible stuff.

When not to use this

For a trivial change, this is more ceremony than it needs — read it yourself. This is for code substantial enough that real defects could be hiding in the logic, not the formatting.

Pro

The full prompt text is part of PromptKit Pro.

Unlock with Pro

Did this work?

You get findings with a specific triggering input or state per issue — not stylistic nitpicks a linter would already catch.

Tested on claude-opus-5. Evidence status is draft; it moves to battle-tested only on recorded runs, never by hand.

Consense — Big decision? Compare and combine multiple LLM responses.