Summary
This teaches Claude to review code the way Sentry's engineering team does it. It'll check for runtime errors, N+1 queries, security holes, and backwards compatibility issues. The skill includes actual code examples showing common Django and React pitfalls, plus guidelines on when to escalate to senior engineers (schema changes, API contracts, new dependencies). What's useful here is the tone guidance: it pushes for actionable feedback over nitpicking, and reminds you to approve PRs when only minor stuff remains. If you're doing code review and want a structured second opinion that knows the difference between blocking issues and style preferences, this is solid.
Install to Claude Code
npx -y skills add getsentry/sentry-skills --skill code-review --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
