All prompts

Code review prompts

Senior-level reviews of diffs, security checks, AI-generated code audits, tests and PR descriptions.

Code review

Senior code review of a diff

Claude/GPT-class models; paste a git diff

Variables: diffwhat_the_change_does

Review this diff as a senior engineer who cares about correctness first, then clarity.

```diff
{{diff}}
```
Context: {{what_the_change_does}}

Output:
1. **Blocking issues** (bugs, security, data loss, race conditions) with line references and a suggested fix.
2. **Should fix** (error handling, edge cases, missing tests).
3. **Nits** (naming, style): max 5.
4. What's good about the change (1-2 lines).
If you're unsure whether something is a bug, say so and explain what would confirm it. Don't invent issues to fill sections.
Open & fill variables →
Code review

Security review

Not a substitute for a real audit

Variables: app_typecode

Do a focused security review of this code for a {{app_type}} app:

```
{{code}}
```

Check specifically for: injection (SQL, command, template), XSS, auth/authorisation gaps (IDOR), secrets in code, unsafe deserialisation, SSRF, path traversal, missing rate limits, insecure defaults, and dependency risks you can see.
For each finding: severity (high/med/low), exploit scenario in one sentence, and the fix. If nothing is found in a category, say "none found" rather than speculating.
Open & fill variables →
Code review

Review AI-generated code

Use on agent output before merging

Variables: code

This code was written by an AI assistant. Review it with that in mind:

```
{{code}}
```

Look for typical AI-code problems: invented APIs or library functions that don't exist, outdated syntax, silently swallowed errors, over-engineering, duplicated helpers that already exist in the codebase, tests that don't really test anything, hard-coded values, and comments that don't match the code.
List each problem with the fix. Then rate: merge / merge after fixes / rewrite.
Open & fill variables →
Code review

Write tests for existing code

Any model

Variables: languagetest_frameworkcode

Write tests for this {{language}} code using {{test_framework}}:

```
{{code}}
```

- Cover: happy path, edge cases (empty, null, boundaries, large inputs), and error paths.
- One behaviour per test, descriptive names ("returns X when Y").
- Mock only external I/O; don't mock the code under test.
- After the tests, list any behaviour that looks like a bug: write a failing test for it and flag it rather than "fixing" the expectation.
Open & fill variables →
Code review

Refactor for readability, same behaviour

Any model

Variables: code

Refactor this code for readability without changing behaviour:

```
{{code}}
```

Constraints: same public interface, same outputs, no new dependencies. Explain each change in one line. If a change could alter behaviour in an edge case, call it out explicitly. Suggest tests that would prove behaviour is unchanged.
Open & fill variables →
Code review

PR description writer

Any model, great on local 7B+

Variables: diff

Write a pull request description from this diff:

```diff
{{diff}}
```

Format: **Summary** (2-3 sentences, the why), **Changes** (bullets), **How to test** (numbered steps), **Risks / rollout notes**, **Screenshots** (placeholder if UI changed). Be factual; don't describe changes that aren't in the diff.
Open & fill variables →
Code review

Dependency upgrade risk check

Paste the changelog if you have it

Variables: packageold_versionnew_versionstack

I'm upgrading {{package}} from {{old_version}} to {{new_version}} in a {{stack}} project.

1. List the breaking changes between these versions you know of (say if unsure about any; your knowledge may be outdated, so tell me where to verify).
2. Show me how to search my codebase for affected usages (grep patterns).
3. Give an upgrade plan with a rollback step.
Open & fill variables →
Pro Prompt Pack · US$12

Get all 209 prompts + agent workflows

Every prompt as Markdown and JSON, 10 multi-step agent workflows, and 12 ready-made slash commands for Cursor and Claude Code. Instant zip download, one-time purchase.

Buy the Pro Pack for US$12 What's inside

New prompts every week

One short email with the best new prompts and agent workflows we've tested. Free; unsubscribe any time.