Publisher: Sentry · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Turn a branch diff into prioritized feedback with a concrete failure mechanism. Useful for engineering teams that want reviewers to distinguish correctness concerns from optional style suggestions.
What input and output should you expect?
Input: Provide the base revision, complete diff, relevant callers and tests, plus the intended behavior. A patch alone may omit the code that proves a suspected regression.
Output: A review organized around actionable findings, their impact and suggested correction or test. Minor preferences should not masquerade as release-blocking bugs.
What does it need to run?
A readable Git checkout and an agent able to inspect neighboring files. Sentry conventions are the starting point; check them against your project standards.
Publisher documents Claude Code installation and skills.sh support for compatible agents including Cursor, Cline and GitHub Copilot. Host permissions and invocation behavior still require validation.
How should you approach installation?
- Read the pinned SKILL.md and repository LICENSE; compare project-specific conventions with your own instructions.
- Follow the publisher installation guidance for your host, retaining the full skill folder and references; begin in a disposable repository with minimal permissions.
- Run the suggested draft or read-only trial, review its acceptance checklist, and grant write or remote permissions only for the intended task.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Source and tests enter the host agent context and potentially its model provider. Start with read-only repository access; posting review comments or changing files is a separate action.
What does the skill cost?
No separate Skill purchase price is stated in the reviewed repository. The host agent subscription or model usage is separate; repository services and any authorized CI jobs may add costs. A local drafting trial does not require paid remote execution.
What are its limits and alternatives?
A checklist cannot establish runtime correctness or complete security coverage. React and Django examples are illustrative, and a project with different architecture needs different context.
Choose Sentry Find Bugs for a narrowly defect-focused pass, or a human architecture review for system-wide design decisions.
What could you ask in a small trial?
Try this with a small sample:
Review this disposable React change where an effect reads a new prop but its dependency list is unchanged. Inspect callers and tests, explain any reproducible stale-value behavior, and keep optional naming advice separate. Do not edit or post comments.
How would you verify the result?
- Every finding cites a relevant location and explains an observable consequence.
- The review checks whether an existing guard or caller invalidates the suspected bug.
- No changes, remote comments or test results are claimed without evidence.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
Apache-2.0 — repository LICENSE at the reviewed commit. License evidence
Version details and review scope
Source: getsentry/skills/skills/code-review
Reviewed commit: d12f250460ffd961f549dbebf7eeb0cf4afd4c2e
SKILL.md SHA-256: ec5fc8855cb4648b4f2c79b608f8c8824a2da6a683330524c4d6283e4a3954c4
Source-document review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.