Code Review

This is a structured framework for doing code reviews that don't suck. It gives you checklists for correctness, maintainability, performance, and security, plus thresholds for when code is too complex (cyclomatic complexity over 20 means refactor required). The best part is the hard data on review effectiveness: PRs under 400 lines catch the most defects, while anything over 800 lines loses 90% effectiveness. It includes a comment severity system (blocking, major, minor, question) so you're not wasting time debating semicolons while missing actual bugs. Works with any language and integrates with github-agile for PR workflows. Honest take: the metrics and thresholds alone make this worth using as a reference, even if you don't follow it religiously.

skills.sh installs: 504
GitHub stars: 182
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwynia/agent-skills --skill code-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Code Review Diagnostic

Systematic code review catches 60-90% of defects before production, reduces maintenance costs by 40%, and serves as effective knowledge transfer. This skill provides structured review guidance for both human reviewers and AI agents.

When to Use This Skill

Use this skill when:

Reviewing code before merge
Assessing code quality
Preparing code for PR submission
Self-reviewing before requesting review

Do NOT use this skill when:

Writing new code (use implementation skills)
Designing architecture (use system-design)
Working on requirements (use requirements-analysis)

Core Principle

Review effectiveness degrades sharply with PR size. Under 400 lines: highest defect detection. 400-800 lines: 50% less effective. 800+ lines: 90% less effective.