code-review

- Full (default): Review for quality, security, conventions, simplicity, and best practices

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "code-review" with this command: npx skills add sirn/dotfiles/sirn-dotfiles-code-review

Run a code review.

Modes

  • Full (default): Review for quality, security, conventions, simplicity, and best practices

  • Fast: Review for quality and simplicity only

  • Performance: Focus on performance optimization

Process

Identify context:

  • If code changes are involved: run jj diff -s first to see changed files; then use jj diff -- path to restrict to specific files/directories

  • If the user specified specific files or paths, focus on those

Determine mode based on user request (default to Full)

Review the code:

Full Mode — analyze each aspect:

  • Quality: Check for bugs, logic errors, error handling issues, and edge cases

  • Security: Check for OWASP risks, injection vulnerabilities, auth issues, data exposure

  • Conventions: Check naming consistency, code organization, and style adherence

  • Simplicity: Check for over-engineering, unnecessary abstractions, and dead code

  • Best practices: Research patterns and idioms for the libraries/frameworks in use (use WebSearch/WebFetch as needed)

Fast Mode:

  • Quality: Check for bugs, logic errors, and error handling issues

  • Simplicity: Check for over-engineering and unnecessary complexity

Performance Mode:

  • Analyze for performance bottlenecks, algorithmic complexity, and memory usage

  • Suggest concrete optimizations with benchmarks where possible

Synthesize findings into a unified report

Output

  • Executive Summary

  • Critical Issues (Must fix)

  • Security Analysis (Full mode only)

  • Quality & Logic

  • Simplicity & Convention

  • Performance & Best Practices

  • Quick Wins

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

code-security-audit

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

code-review

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

code-review

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

code-review

No summary provided by upstream source.

Repository SourceNeeds Review