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

Claude Code

$ npx -y skills add wasabeef/claude-code-cookbook --skill pr-review --agent claude-code

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
@wasabeef
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.

1.1k39 skills9 agents8 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
1.1k
Star history of wasabeef/claude-code-cookbook on GitHub, a chart by star-history.com

Other skills on claude-code-cookbook.

check-fact

check-fact

Verify information accuracy against codebase and documentation. Trigger with "is this correct?", "fact check", "verify this", "is…

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills12d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react3d252k
@facebook@facebookInstall Skill

Questions about pr-review.

Which coding agents can use pr-review?
pr-review installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.