Skip to main content
Review

Get a code review that ranks issues by severity

Ask Gemini to review a diff for correctness, security, and clarity, rank findings by severity with a concrete failure scenario each, and skip style nits unless they hide a bug.

프롬프트

Review this change for correctness, security, and clarity. For each finding: give a severity (blocker / major / minor), the specific failure scenario, and the smallest fix. Skip pure style nits unless they hide a bug. If the change looks safe, say so plainly. Diff: [DIFF].

변수 바꾸기

[DIFF]

The diff or the changed files.

사용할 모델

  • Gemini 3.1 ProSeverity judgement and failure scenarios need careful reasoning.

예시 입력

  • [DIFF] = a pull request touching auth middleware.

예시 출력

저희는 실제 모델 실행의 예시 출력만 게시합니다. 이 템플릿은 아직 공식적으로 테스트되지 않아 출력이 표시되지 않습니다. 위의 입력값으로 직접 실행해 보세요.

이 구조가 작동하는 이유

  • Severity + failure scenario filters out noise and false alarms.
  • Permission to say "looks safe" reduces invented problems.

흔한 실패와 수정

Every line gets a comment.

수정: Cap it: "Report at most the 5 most important findings."

알려진 한계

  • A model review complements, not replaces, human review and tests.

Google과 제휴하거나 승인받지 않았습니다. Gemini, Nano Banana, Veo는 Google LLC의 상표입니다.