Skip to content
Development
Skill

/pr-review

Systematic PR review for code quality assurance. Trigger with "review this PR", "check this pull request", "code review", "review please".

From plugin
claude-code-cookbook
1.1k39 skills9 agents39 commands8 MCP
Install
$ npx -y skills add wasabeef/claude-code-cookbook --skill pr-review --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/pr-review

Context preview

The summary Claude sees to decide when to auto-load this skill.

Systematic PR review for code quality assurance. Trigger with "review this PR", "check this pull request", "code review", "review please".

SKILL.md

pr-review.SKILL.md
description: 'Systematic PR review for code quality assurance. Trigger with "review this PR", "check this pull request", "code review", "review please".'
allowed-tools:
  - Bash(gh *)
  - Read
  - Grep
  - Glob

Systematic PR review for code quality assurance

Ensure code quality and architectural soundness through systematic Pull Request reviews.

Usage

# Comprehensive PR review
gh pr view 123 --comments
"Systematically review this PR and provide feedback from code quality, security, and architecture perspectives"

# Security-focused review
gh pr diff 123
"Focus on reviewing security risks and vulnerabilities"

# Architecture perspective review
gh pr checkout 123 && find . -name "*.js" | head -10
"Evaluate the architecture from the perspectives of layer separation, dependencies, and SOLID principles"

Basic Examples

# Quantitative code quality assessment
find . -name "*.js" -exec wc -l {} + | sort -rn | head -5
"Evaluate code complexity, function size, and duplication, and point out improvements"

# Security vulnerability check
grep -r "password\|secret\|token" . --include="*.js" | head -10
"Check for risks of sensitive information leakage, hardcoding, and authentication bypass"

# Architecture violation detection
grep -r "import.*from.*\.\./\.\." . --include="*.js"
"Evaluate layer violations, circular dependencies, and coupling issues"

Comment Classification System

🔴 critical.must: Critical issues
├─ Security vulnerabilities
├─ Data integrity problems
└─ System failure risks

🟡 high.imo: High-priority improvements
├─ Risk of malfunction
├─ Performance issues
└─ Significant decrease in maintainability

🟢 medium.imo: Medium-priority improvements
├─ Readability enhancement
├─ Code structure improvement
└─ Test quality improvement

🟢 low.nits: Minor points
├─ Style unification
├─ Typo fixes
└─ Comment additions

🔵 info.q: Questions/information
├─ Implementation intent confirmation
├─ Design decision background
└─ Best practices sharing

Review Perspectives

1. Code Correctness

  • **Logic errors**: Boundary values, null checks, exception handling
  • **Data integrity**: Type safety, validation
  • **Error handling**: Completeness, appropriate processing

2. Security

  • **Authentication/authorization**: Appropriate checks, permission management
  • **Input validation**: SQL injection, XSS countermeasures
  • **Sensitive information**: Logging restrictions, encryption

3. Performance

  • **Algorithms**: Time complexity, memory efficiency
  • **Database**: N+1 queries, index optimization
  • **Resources**: Memory leaks, cache utilization

4. Architecture

  • **Layer separation**: Dependency direction, appropriate separation
  • **Coupling**: Tight coupling, interface utilization
  • **SOLID principles**: Single responsibility, open-closed, dependency inversion

Review Flow

1. **Pre-check**: PR information, change diff, related issues 2. **Systematic checks**: Security → Correctness → Performance → Architecture 3. **Constructive feedback**: Specific improvement suggestions and code examples 4. **Follow-up**: Fix confirmation, CI status, final approval

Comment Templates

Security Issues Template

**Format:**

  • Priority: `critical.must.`
  • Issue: Clear description of the problem
  • Code example: Proposed fix
  • Rationale: Why this is necessary

**Example:**

critical.must. Password is stored in plaintext

Proposed fix:
const bcrypt = require('bcrypt');
const hashedPassword = await bcrypt.hash(password, 12);

Hashing is required to prevent security risks.

Performance Improvement Template

**Format:**

  • Priority: `high.imo.`
  • Issue: Explain performance impact
  • Code example: Proposed improvement
  • Effect: Describe expected improvement

**Example:**

high.imo. N+1 query problem occurs

Improvement: Eager Loading
const users = await User.findAll({ include: [Post] });

This can significantly reduce the number of queries.

Architecture Violation Template

**Format:**

  • Priority: `high.must.`
  • Issue: Point out architectural principle violation
  • Recommendation: Specific improvement method

**Example:**

high.must. Layer violation occurred

The domain layer directly depends on the infrastructure layer.
Please introduce an interface following the dependency inversion principle.

Notes

  • **Constructive tone**: Collaborative rather than aggressive communication
  • **Specific suggestions**: Provide solutions along with pointing out problems
  • **Prioritization**: Address in order of Critical → High → Medium → Low
  • **Continuous improvement**: Document review results in a knowledge base
Read more
Ships withclaude-code-cookbook

A collection of commands, roles, and automation scripts for Claude Code. Automate your workflow without unnecessary confirmations, allowing you to focus on what matters.

Get the whole plugin

Other skills on claude-code-cookbook.