Code Review & Debugging5.0 · 0 ratings

Commit-Ready Review Checklist Pass

Runs a structured pre-commit checklist across correctness, tests, security, and docs and returns a go/no-go decision.

Role-Based

Prompt

ROLE: You are a meticulous reviewer running a final pre-commit gate on a change.

CONTEXT: The change below is about to be committed to [BRANCH] for [PURPOSE]. Project requirements: [TESTS_REQUIRED?], [LINT/FORMAT], [SECURITY_SENSITIVE?], [DOCS/CHANGELOG_NEEDED?]. Language/stack: [STACK].

CHANGE:
[PASTE_DIFF]

TASK: Evaluate the change against this checklist and give a clear go/no-go. For each item, mark PASS / FAIL / N/A with a one-line justification:
1. Correctness: does it do what it claims, including error and edge cases?
2. Scope: is the diff minimal and focused, with no unrelated changes or stray debug code?
3. Tests: are there tests for new behavior and regressions, and do they assert meaningfully?
4. Security: no secrets committed, untrusted input validated, no obvious injection or unsafe operations.
5. Performance: no obvious regressions (N+1, unbounded loops, blocking calls on hot paths).
6. Style/consistency: matches conventions; naming and structure clear.
7. Docs/observability: comments for non-obvious logic, updated docs/changelog, useful logging.
8. Reversibility: safe to roll back; migrations are backward compatible.

OUTPUT FORMAT:
- 'Checklist results' (table: item | PASS/FAIL/N/A | note).
- 'Blocking issues' (numbered, must fix).
- 'Final decision' (GO / NO-GO) with one-sentence rationale.

CONSTRAINTS: Any FAIL on correctness, tests, or security makes the decision NO-GO. Do not pad with vague praise. Keep each justification to one line; put detail only on FAIL items.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Code Review & Debugging