Code Review

What it does

The instruction file organizes review around concrete failure modes such as exceptions, unnecessary database work, compatibility changes and security mistakes. It adds design and test-coverage questions, then describes feedback that focuses on actionable risks rather than stylistic preferences.

Best for

Reviewing changes in Python/Django or TypeScript/React codebases with conventions similar to the publisher’s projects.

Tradeoffs and requirements

Publisher-specific conventions should not be imposed on an unrelated repository without checking its rules. A checklist cannot establish correctness by itself, and example patterns can be safe or unsafe depending on surrounding code and framework behavior.

Unknown; inspect source requirements and supporting scripts.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code; this catalog never runs it.

npx skills add https://github.com/getsentry/skills/tree/d12f250460ffd961f549dbebf7eeb0cf4afd4c2e/skills/code-review --skill code-review

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Network Access — review the source context.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

86/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

100/100

100

Compatibility Evidence

80/100

80

Popularity

55/100

55

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Read the complete change and the affected callers, identify observable risks, then inspect existing tests and protections before writing a finding. Keep implementation suggestions scoped to the actual problem.

How to judge the result

Each substantive finding should identify a trigger, affected behavior and evidence. Verify suggested test cases against the requirement, and distinguish inspected code from areas that still need domain or production knowledge.