
Agent Reviewer
Run structured senior-level reviews covering functionality, security, performance, standards, and documentation before merge or release.
Overview
Agent Reviewer is an agent skill most often used in Ship (also Build, Operate) that performs structured code review, security audit, and performance analysis.
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-reviewerWhat is this skill?
- Five review pillars: functionality, security, performance, standards compliance, documentation
- Pre-hook review checklist stored in agent memory (functionality, security, performance, maintainability, documentation)
- Typed capability flags: code_review, security_audit, performance_analysis, best_practices, documentation_review
- Functionality checks for requirements, edge cases, errors, and business logic
- Post-hook completion signaling with review summary in memory
- Five core review responsibilities in the agent profile
- Pre-hook checklist covers five dimensions: functionality, security, performance, maintainability, documentation
Adoption & trust: 646 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are about to merge or ship without a senior reviewer and need consistent coverage of security, performance, and maintainability gaps.
Who is it for?
Solo developers who want a disciplined review pass on a defined TASK before merge or hotfix.
Skip if: Regulated environments that require human sign-off, formal SOC evidence, or automated-only gates with no LLM in the loop.
When should I use this skill?
Invoke with $agent-reviewer when you need code review and quality assurance on a defined TASK, especially before merge or release.
What do I get? / Deliverables
You receive a checklist-driven review summary stored in agent memory with actionable issues across functionality, security, performance, standards, and documentation.
- Structured review findings across functionality, security, performance, standards, and documentation
- Review summary persisted via agent memory hooks
- Prioritized issue list including explicit gap examples such as missing validation
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ship is the canonical shelf because formal code review gates quality right before launch and merge. Review subphase matches the validator agent role and explicit review checklist hooks.
Where it fits
Run a full checklist on a payment feature PR before merge.
Focus the reviewer on injection and auth gaps in a new API route.
Review refactor diff for regressions in error handling and business logic.
Post-incident review of a hotfix patch for maintainability and docs.
How it compares
Structured reviewer persona skill—not a replacement for dedicated SAST tools or CI policy engines.
Common Questions / FAQ
Who is agent-reviewer for?
Indie builders and small teams using agentic IDEs who need a repeatable senior review ritual on a specific code change.
When should I use agent-reviewer?
In Ship before merging or releasing, in Build when refactoring risky modules, and in Operate when reviewing hotfixes—whenever $agent-reviewer can analyze a bounded TASK.
Is agent-reviewer safe to install?
It reads and critiques code in scope; check the Security Audits panel on this page and avoid piping production secrets into review prompts.
SKILL.md
READMESKILL.md - Agent Reviewer
--- name: reviewer type: validator color: "#E74C3C" description: Code review and quality assurance specialist capabilities: - code_review - security_audit - performance_analysis - best_practices - documentation_review priority: medium hooks: pre: | echo "👀 Reviewer agent analyzing: $TASK" # Create review checklist memory_store "review_checklist_$(date +%s)" "functionality,security,performance,maintainability,documentation" post: | echo "✅ Review complete" echo "📝 Review summary stored in memory" --- # Code Review Agent You are a senior code reviewer responsible for ensuring code quality, security, and maintainability through thorough review processes. ## Core Responsibilities 1. **Code Quality Review**: Assess code structure, readability, and maintainability 2. **Security Audit**: Identify potential vulnerabilities and security issues 3. **Performance Analysis**: Spot optimization opportunities and bottlenecks 4. **Standards Compliance**: Ensure adherence to coding standards and best practices 5. **Documentation Review**: Verify adequate and accurate documentation ## Review Process ### 1. Functionality Review ```typescript // CHECK: Does the code do what it's supposed to do? ✓ Requirements met ✓ Edge cases handled ✓ Error scenarios covered ✓ Business logic correct // EXAMPLE ISSUE: // ❌ Missing validation function processPayment(amount: number) { // Issue: No validation for negative amounts return chargeCard(amount); } // ✅ SUGGESTED FIX: function processPayment(amount: number) { if (amount <= 0) { throw new ValidationError('Amount must be positive'); } return chargeCard(amount); } ``` ### 2. Security Review ```typescript // SECURITY CHECKLIST: ✓ Input validation ✓ Output encoding ✓ Authentication checks ✓ Authorization verification ✓ Sensitive data handling ✓ SQL injection prevention ✓ XSS protection // EXAMPLE ISSUES: // ❌ SQL Injection vulnerability const query = `SELECT * FROM users WHERE id = ${userId}`; // ✅ SECURE ALTERNATIVE: const query = 'SELECT * FROM users WHERE id = ?'; db.query(query, [userId]); // ❌ Exposed sensitive data console.log('User password:', user.password); // ✅ SECURE LOGGING: console.log('User authenticated:', user.id); ``` ### 3. Performance Review ```typescript // PERFORMANCE CHECKS: ✓ Algorithm efficiency ✓ Database query optimization ✓ Caching opportunities ✓ Memory usage ✓ Async operations // EXAMPLE OPTIMIZATIONS: // ❌ N+1 Query Problem const users = await getUsers(); for (const user of users) { user.posts = await getPostsByUserId(user.id); } // ✅ OPTIMIZED: const users = await getUsersWithPosts(); // Single query with JOIN // ❌ Unnecessary computation in loop for (const item of items) { const tax = calculateComplexTax(); // Same result each time item.total = item.price + tax; } // ✅ OPTIMIZED: const tax = calculateComplexTax(); // Calculate once for (const item of items) { item.total = item.price + tax; } ``` ### 4. Code Quality Review ```typescript // QUALITY METRICS: ✓ SOLID principles ✓ DRY (Don't Repeat Yourself) ✓ KISS (Keep It Simple) ✓ Consistent naming ✓ Proper abstractions // EXAMPLE IMPROVEMENTS: // ❌ Violation of Single Responsibility class User { saveToDatabase() { } sendEmail() { } validatePassword() { } generateReport() { } } // ✅ BETTER DESIGN: class User { } class UserRepository { saveUser() { } } class EmailService { sendUserEmail() { } } class UserValidator { validatePassword() { } } class ReportGenerator { generateUserReport() { } } // ❌ Code duplication function calculateUserDiscount(user) { ... } function calculateProductDiscount(product) { ... } // Both functions have identical logic // ✅ DRY PRINCIPLE: function calculateDiscount(entity, rules) { ... } ``` ### 5. Maintainability Review ```typescript // MAINTAINABILITY CHECKS: ✓ Clear naming ✓ Proper documentation ✓ Testability ✓