Provides structured, multi-dimensional code reviews for security, performance, and correctness.

Install

mkdir -p .claude/skills/reviewing-code && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/187" && unzip -o skill.zip -d .claude/skills/reviewing-code && rm skill.zip

Installs to .claude/skills/reviewing-code

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
194 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Validates code against spec docs
  • Checks for security vulnerabilities
  • Benchmarks algorithmic efficiency
  • Performs sequential or parallel reviews
  • Verifies compliance with data plans

How it works

Cross-references code changes against project-specific technical design and acceptance criteria documents using multi-dimensional analysis.

Inputs & outputs

You give it
PR code diff and specs
You get back
Prioritized findings report

When to use reviewing-code

  • Reviewing pull requests
  • Assessing code quality
  • Verifying implementation against design specs
  • Checking for security vulnerabilities

About this skill

Reviewing Code

Evaluate code changes across security, correctness, spec alignment, performance, and maintainability. Apply sequential or parallel review based on scope.

Quick Start

Sequential (small PRs, <5 files):

  1. Gather context from feature specs and acceptance criteria
  2. Review sequentially through focus areas
  3. Report findings by priority
  4. Recommend approval/revision/rework

Parallel (large PRs, >5 files):

  1. Identify independent review aspects (security, API, UI, data)
  2. Spawn specialist agents for each dimension
  3. Consolidate findings
  4. Report aggregate assessment

Context Gathering

Read documentation:

  • docs/feature-spec/F-##-*.md — Technical design and requirements
  • docs/user-stories/US-###-*.md — Acceptance criteria
  • docs/api-contracts.yaml — Expected API signatures
  • docs/data-plan.md — Event tracking requirements (if applicable)
  • docs/design-spec.md — UI/UX requirements (if applicable)
  • docs/system-design.md — Architecture patterns (if available)
  • docs/plans/<slug>/plan.md — Original implementation plan (if available)

Determine scope:

  • Files changed and features affected (F-## IDs)
  • Stories implemented (US-### IDs)
  • API, database, or schema changes

Quality Dimensions

Security (/25)

  • Input validation and sanitization
  • Authentication/authorization checks
  • Sensitive data handling
  • Injection vulnerabilities (SQL, XSS, etc.)

Correctness (/25)

  • Logic matches acceptance criteria
  • Edge cases handled properly
  • Error handling complete
  • Null/undefined checks present

Spec Alignment (/20)

  • APIs match docs/api-contracts.yaml
  • Data events match docs/data-plan.md
  • UI matches docs/design-spec.md
  • Implementation follows feature spec

Performance (/15)

  • Algorithm efficiency
  • Database query optimization
  • Resource usage (memory, network)

Maintainability (/15)

  • Code clarity and readability
  • Consistent with codebase patterns
  • Appropriate abstraction levels
  • Comments where needed

Total: /100

Finding Priority

🔴 CRITICAL (Must fix before merge)

  • Security vulnerabilities
  • Broken functionality
  • Spec violations (API contract breaks)
  • Data corruption risks

Format:

Location: file.ts:123
Problem: [Description]
Impact: [Risk/consequence]
Fix: [Specific change needed]
Spec reference: [docs/api-contracts.yaml line X]

🟡 IMPORTANT (Should fix)

  • Logic bugs in edge cases
  • Missing error handling
  • Performance issues
  • Missing analytics events
  • Accessibility violations

🟢 NICE-TO-HAVE (Optional)

  • Code style improvements
  • Better abstractions
  • Enhanced documentation

✅ GOOD PRACTICES

Highlight what was done well for learning

Review Strategies

Single-Agent Review

Best for <5 files, single concern:

  1. Review sequentially through focus areas
  2. Concentrate on 1-2 most impacted areas
  3. Generate unified report

Parallel Multi-Agent Review

Best for >5 files, multiple concerns:

  1. Spawn specialized agents:

    • Security: senior-engineer for vulnerability assessment
    • Architecture: Explore for pattern compliance
    • API Contracts: programmer for endpoint validation
    • Frontend: programmer for UI/UX and accessibility
    • Documentation: documentor for comment quality and docs
  2. Each agent reviews specific quality dimension

  3. Consolidate findings into single report

Report Structure

# Code Review: [Feature/PR]

## Summary
**Quality Score:** [X/100]
**Issues:** Critical: [N], Important: [N], Nice-to-have: [N]
**Assessment:** [APPROVE / NEEDS REVISION / MAJOR REWORK]

## Spec Compliance
- [ ] APIs match `docs/api-contracts.yaml`
- [ ] Events match `docs/data-plan.md`
- [ ] UI matches `docs/design-spec.md`
- [ ] Logic satisfies story AC

## Findings

### Critical Issues
[Issues with fix recommendations]

### Important Issues
[Issues that should be addressed]

### Nice-to-Have Suggestions
[Optional improvements]

### Good Practices
[What worked well]

## Recommendations
[Next steps: approval, revision needed, etc.]

Fix Implementation

Offer options:

  1. Fix critical + important issues
  2. Fix only critical (minimum for safety)
  3. Provide detailed explanation for learning
  4. Review only (no changes)

Parallel fixes for large revisions:

  • Spawn agents for independent fix areas
  • Coordinate on shared dependencies
  • Document each fix with location, change, and verification method

Document format:

✅ FIXED: [Issue name]
File: [path:line]
Change: [what changed]
Verification: [how to test]

Documentation Updates

Check if specs need updates:

  • Feature spec "Decisions" or "Deviations" if implementation differs
  • Design spec if UI changed
  • API contracts if endpoints modified (requires approval)
  • Data plan if events changed

Always flag for user approval before modifying specs.

Key Points

  • Read all context documents before starting
  • Focus on most impacted areas first
  • Be thorough with security-sensitive code, API changes, and critical user flows
  • Use scoring framework for comprehensive reviews
  • Parallel review scales to large PRs
  • Flag spec deviations for user decision

When not to use it

  • Reviewing non-code documents
  • Very small, trivial changes

Prerequisites

Access to technical design docsRepository structure

Limitations

  • Review quality depends on documentation clarity
  • May require multiple passes for large codebases

How it compares

It validates against specific project documentation rather than performing generic static code analysis.

Compared to similar skills

reviewing-code side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
reviewing-code (this skill)218moNo flagsIntermediate
pr-review62moReviewIntermediate
code-review-checklist326dNo flagsBeginner
fix-review34moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by CaptainCrouton89

View all by CaptainCrouton89

railway-cli-management

CaptainCrouton89

Deploy, manage services, view logs, and configure Railway infrastructure. Use when deploying to Railway, managing environment variables, viewing deployment logs, scaling services, or managing volumes.

9139

writing-like-user

CaptainCrouton89

Emulate the user's personal writing voice and style patterns. Use when the user asks to write content in their voice, draft documents, compose messages, or requests "write this like me" or "in my style."

687

gathering-requirements

CaptainCrouton89

Systematically clarify user needs, preferences, and constraints before planning or implementation. Classifies work type, investigates existing systems, discovers edge cases and integration points, resolves assumptions, and creates detailed specifications. Use when building features, enhancements, or integrations where requirements need clarification.

31

auditing-security

CaptainCrouton89

Identify and remediate vulnerabilities through systematic code analysis. Use when performing security assessments, pre-deployment reviews, compliance validation (OWASP, PCI-DSS, GDPR), investigating known vulnerabilities, or post-incident analysis.

10

documenting-code

CaptainCrouton89

Maintain project documentation synchronized with code. Keep feature specs, API contracts, and README current with init-project standards. Use when updating docs after code changes, adding new features, or ensuring documentation completeness.

14

executing-work-in-parallel

CaptainCrouton89

Coordinate concurrent task execution through agent delegation. Plan independent work, manage dependencies, and execute multiple agents simultaneously. Use when handling multiple unrelated tasks, research investigations, or layer-based implementations that can run concurrently.

12

Search skills

Search the agent skills registry