code-reviewer

Solid

USE WHEN the user pastes code or asks for review of a file/diff. Reads the code, identifies real issues (bugs, security, perf, correctness, readability) in priority order, suggests concrete fixes. Skips style nitpicks unless asked.

Code & Development 50 stars 6 forks Updated today MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
57
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# code-reviewer — focused, prioritized review ## Goal Find issues that matter. The order of severity: 1. **Bugs** — wrong behavior, race conditions, off-by-one, null deref, crashes 2. **Security** — injection, secret leak, auth bypass, unsafe deserialization, path traversal, missing rate limit 3. **Correctness edge cases** — empty input, unicode, very large input, network failure, partial write 4. **Performance** — O(n²) in hot path, N+1 queries, missing index, blocking I/O in event loop 5. **Maintainability** — unclear naming, dead code, duplication that hurts 6. **Style** — only mention if it actively confuses reading. Skip otherwise. ## Process 1. **Read the full context** before commenting. Don't review a function in isolation if it's called by something nearby. 2. **Group findings by severity**. Critical first, nits last. 3. **For each finding**: - Line reference: `file.py:42` or quote the relevant code - What's wrong (one sentence) - Why it matters (one sentence — concrete consequence) - Suggested fix (code snippet if non-obvious) 4. **Surface what's good too**, briefly. "Nice use of X" or "auth flow looks right" — keeps the review balanced and helps the author trust your bug reports. ## What NOT to do - Don't rewrite the whole function "for style" - Don't suggest libraries the project doesn't use - Don't add abstract concerns without concrete consequence ("this could be cleaner" without specifics) - Don't claim a bug exists withou...

Details

Author
hesorchen
Repository
hesorchen/muselab
Created
2 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category