Help us improve
Share bugs, ideas, or general feedback.
From devs
Comprehensive code review guidance for quality, performance, and architecture across all programming languages. Use when (1) User explicitly requests code review, (2) After writing significant code changes, (3) Before commits/PRs, (4) Reviewing existing codebases, (5) Analyzing code quality, (6) Detecting performance issues, (7) Identifying architectural problems, (8) Finding code smells. Provides automated analysis scripts and manual review checklists for thorough code evaluation.
npx claudepluginhub aaronbassett/agent-foundry --plugin devsHow this skill is triggered — by the user, by Claude, or both
Slash command
/devs:code-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Comprehensive code review for quality, performance, and architecture across all languages.
Performs comprehensive code reviews with automated fixes for Python, TypeScript, JavaScript, Go, Rust projects. Analyzes quality, security, performance, architecture, tests; applies safe fixes and generates reports.
Analyzes code structure, complexity, and quality using cyclomatic and cognitive complexity metrics, detects code smells like long methods and god objects, and suggests refactoring strategies.
Orchestrates multi-phase code reviews with specialized agents covering quality, architecture, security, performance, testing, and docs. Supports framework configs like React, Django.
Share bugs, ideas, or general feedback.
Comprehensive code review for quality, performance, and architecture across all languages.
Run complete analysis:
./scripts/review_code.sh /path/to/code
This runs:
Use comprehensive checklist:
Complexity analysis:
./scripts/analyze_complexity.py /path/to/code
Code smells:
./scripts/detect_code_smells.py /path/to/code
Trigger this skill when:
review_code.sh - Complete review orchestrator
analyze_complexity.py - Complexity metrics
detect_code_smells.py - Code smell detection
generate_review_report.py - Report generation
review-checklist.md - Complete review checklist
code-smells.md - Code smell catalog
# Run automated analysis
./scripts/review_code.sh /path/to/project
# Review output
cat .code-review-output/REVIEW.md
# Manual checklist review
# Consult references/review-checklist.md
# Address findings
# Refactor based on recommendations
# Analyze complexity
./scripts/analyze_complexity.py /path/to/code
# Identify complex functions
# Refactor functions with complexity >10
Cyclomatic Complexity:
Function Length:
Nesting Depth:
High - Address immediately:
Medium - Address soon:
Low - Address when convenient:
JavaScript/TypeScript:
Python:
Rust:
For languages not automatically detected:
Add to GitHub Actions:
- name: Code Review
run: |
./scripts/review_code.sh .
# Fail if high-severity issues found
#!/bin/bash
./scripts/review_code.sh . --quick
Most linters integrate with VS Code, IntelliJ, etc.
For specific issues:
After review:
# Code Review Report
## Executive Summary
- Total Functions Analyzed: 127
- Code Smells Detected: 23
- High Severity: 3
- Medium Severity: 15
- Low Severity: 5
## Complexity Analysis
- Average Complexity: 4.2
- Maximum Complexity: 18
- Functions Needing Attention: 8
## Recommendations
- Refactor 3 highly complex functions
- Address 3 high-severity code smells
- Extract duplicated code in 5 locations
Note: This skill provides guidance and automated checks. Final decisions on code quality depend on project context, team conventions, and business requirements.