Back to guide/Developer Tools

PR Review Assistant

Claude Code can read the actual diff from git and cross-reference with the full codebase for context. Cursor can review individual files with @file references. The severity system keeps feedback actionable.

cursor-vs-claude-codepr_titlepr_descriptionfiles_changed
Edit View
Prompt
Review this pull request diff and provide feedback:

PR title: {{pr_title}}
PR description: {{pr_description}}
Files changed: {{files_changed}}

Review criteria:
1. **Correctness**: Any bugs, logic errors, or race conditions?
2. **Design**: Does this follow the project's existing patterns? Flag deviations
3. **Completeness**: Are there missing test cases, error handlers, or edge cases?
4. **Performance**: Any N+1 queries, unnecessary re-renders, or O(n^2) operations?
5. **Security**: Input validation, auth checks, SQL injection, XSS vectors?
6. **Naming**: Do new functions/variables follow the project's naming conventions?

For each issue, format as:
**[Severity]** File:line — Description
\`\`\`suggestion
// suggested fix
\`\`\`

Severity levels: BLOCKER (must fix) | WARNING (should fix) | NIT (style preference)

End with:
- Overall assessment: Approve / Request Changes / Needs Discussion
- One thing this PR does particularly well
- The single most important change to make before merging

Variables to customize

{{pr_title}}{{pr_description}}{{files_changed}}

Why this prompt works

Claude Code can read the actual diff from git and cross-reference with the full codebase for context. Cursor can review individual files with @file references. The severity system keeps feedback actionable.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Code Review Assistant

Get thorough code reviews with actionable feedback tailored to your language, framework, and standards.

Context-Aware Code Completion

Providing the surrounding code and project context lets the model match existing patterns exactly. The constraint against modifying existing code prevents unwanted side effects.

Inline Code Suggestion

Constraining suggestions to match existing style and scope produces insertions that feel native to the codebase. The 'no explanation' rule mimics real inline completion behavior.

Code Explanation

The audience level parameter adjusts complexity automatically. Requiring a usage example ensures the explanation is practical, not just theoretical.