Analyzes code changes and pull requests to identify security vulnerabilities, performance bottlenecks, and design flaws based on Sentry engineering standards. Provides actionable, empathetic feedback on code quality, test coverage, and long-term maintainability.
2 uses this weeksource getsentrylicence Apache-2.0
Quality gate: PASS · better answers · measured 2026-10-23 Blind-judged against the bare model on 2 requests: average lift +4.5 points (specificity, structure, method, fit). won 2/2, lift +4.5, tokens ×65.89
Security scan: clean · 2026-10-24 · 1 files · ran in sandbox no network calls, shell tricks, credential access or instruction tampering found in its files.
Try asking
Say it in your own words; the assistant finds this recipe by itself. Examples:
“Kan du gennemgå denne pull request og tjekke for sikkerhedsproblemer?”
“Se på min kode og find eventuelle N+1 query problemer i Django.”
“Jeg har brug for feedback på testdækningen for denne nye funktion.”
“Review this PR for potential security vulnerabilities and performance issues.”
“Can you check if my Django ORM queries in this diff are efficient?”
“I need feedback on the test coverage for this new feature branch.”
Try this skill from Claude, ChatGPT or a chat on your own page. Free plan, no credit card.Get started free
Do not use this skill for writing new code from scratch or generating entire modules, as it is focused on evaluating existing changes. It is not intended for automated linting or formatting fixes, which should be handled by static analysis tools. It is also not for debugging runtime errors in production environments, which requires a debugging or incident response skill.
Details
When it is the right choice
Use this skill when a user asks for a review of a specific pull request, diff, or code snippet. It is appropriate when the user wants to check for security issues, performance anti-patterns, or architectural consistency before merging code. It is also suitable when the user seeks constructive feedback on code quality and test coverage.
The full recipe the assistant reads
Sentry Code Review
Follow these guidelines when reviewing code for Sentry projects.
Side effects: Unintended behavioral changes affecting other components
Backwards compatibility: Breaking API changes without migration path
ORM queries: Complex Django ORM with unexpected query performance
Security vulnerabilities: Injection, XSS, access control gaps, secrets exposure
Design Assessment
Do component interactions make logical sense?
Does the change align with existing project architecture?
Are there conflicts with current requirements or goals?
Test Coverage
Every PR should have appropriate test coverage:
Functional tests for business logic
Integration tests for component interactions
End-to-end tests for critical user paths
Verify tests cover actual requirements and edge cases. Avoid excessive branching or looping in test code.
Long-Term Impact
Flag for senior engineer review when changes involve:
Database schema modifications
API contract changes
New framework or library adoption
Performance-critical code paths
Security-sensitive functionality
Feedback Guidelines
Tone
Be polite and empathetic
Provide actionable suggestions, not vague criticism
Phrase as questions when uncertain: "Have you considered...?"
Approval
Approve when only minor issues remain
Don't block PRs for stylistic preferences
Remember: the goal is risk reduction, not perfect code
Common Patterns to Flag
Python/Django
# Bad: N+1 query
for user in users:
print(user.profile.name) # Separate query per user
# Good: Prefetch related
users = User.objects.prefetch_related('profile')
TypeScript/React
// Bad: Missing dependency in useEffect
useEffect(() => {
fetchData(userId);
}, []); // userId not in deps
// Good: Include all dependencies
useEffect(() => {
fetchData(userId);
}, [userId]);
Security
# Bad: SQL injection risk
cursor.execute(f"SELECT * FROM users WHERE id = {user_id}")
# Good: Parameterized query
cursor.execute("SELECT * FROM users WHERE id = %s", [user_id])