CO

code-review-checklist

A standardized checklist for evaluating code quality, security vulnerabilities, and AI-specific implementation patterns.

Install

mkdir -p .claude/skills/code-review-checklist && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1080" && unzip -o skill.zip -d .claude/skills/code-review-checklist && rm skill.zip

Installs to .claude/skills/code-review-checklist

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.

Code review guidelines covering code quality, security, and best practices.
75 charsno explicit “when” trigger
Beginner

Key capabilities

  • Audit code for security vulnerabilities like injection and hardcoded secrets
  • Evaluate performance through query and loop analysis
  • Check adherence to SOLID principles and DRY patterns
  • Validate AI-generated code for prompt injection and hallucination risks
  • Standardize review feedback using specific color-coded indicators

How it works

The tool applies a predefined checklist covering correctness, security, performance, and documentation to evaluate code. It specifically provides patterns for auditing AI-generated logic and prompt engineering.

Inputs & outputs

You give it
Source code or pull request content
You get back
Structured checklist evaluation and categorized review comments

When to use code-review-checklist

  • Reviewing a new pull request for potential security flaws
  • Evaluating code quality according to SOLID principles
  • Checking AI-generated code for prompt injection risks
  • Verifying edge case coverage and error handling
  • Validating that documentation and tests meet project standards

About this skill

Code Review Checklist

Quick Review Checklist

Correctness

  • Code does what it's supposed to do
  • Edge cases handled
  • Error handling in place
  • No obvious bugs

Security

  • Input validated and sanitized
  • No SQL/NoSQL injection vulnerabilities
  • No XSS or CSRF vulnerabilities
  • No hardcoded secrets or sensitive credentials
  • AI-Specific: Protection against Prompt Injection (if applicable)
  • AI-Specific: Outputs are sanitized before being used in critical sinks

Performance

  • No N+1 queries
  • No unnecessary loops
  • Appropriate caching
  • Bundle size impact considered

Code Quality

  • Clear naming
  • DRY - no duplicate code
  • SOLID principles followed
  • Appropriate abstraction level

Testing

  • Unit tests for new code
  • Edge cases tested
  • Tests readable and maintainable

Documentation

  • Complex logic commented
  • Public APIs documented
  • README updated if needed

AI & LLM Review Patterns

Logic & Hallucinations

  • Chain of Thought: Does the logic follow a verifiable path?
  • Edge Cases: Did the AI account for empty states, timeouts, and partial failures?
  • External State: Is the code making safe assumptions about file systems or networks?

Prompt Engineering Review

// ❌ Vague prompt in code
const response = await ai.generate(userInput);

// ✅ Structured & Safe prompt
const response = await ai.generate({
  system: "You are a specialized parser...",
  input: sanitize(userInput),
  schema: ResponseSchema
});

Anti-Patterns to Flag

// ❌ Magic numbers
if (status === 3) { ... }

// ✅ Named constants
if (status === Status.ACTIVE) { ... }

// ❌ Deep nesting
if (a) { if (b) { if (c) { ... } } }

// ✅ Early returns
if (!a) return;
if (!b) return;
if (!c) return;
// do work

// ❌ Long functions (100+ lines)
// ✅ Small, focused functions

// ❌ any type
const data: any = ...

// ✅ Proper types
const data: UserData = ...

Review Comments Guide

// Blocking issues use 🔴
🔴 BLOCKING: SQL injection vulnerability here

// Important suggestions use 🟡
🟡 SUGGESTION: Consider using useMemo for performance

// Minor nits use 🟢
🟢 NIT: Prefer const over let for immutable variable

// Questions use ❓
❓ QUESTION: What happens if user is null here?

How it compares

This tool provides a standardized framework for categorizing review feedback with specific indicators for blocking issues, suggestions, and minor nits, unlike manual ad-hoc reviews.

Compared to similar skills

code-review-checklist side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
code-review-checklist (this skill)327dNo flagsBeginner
pr-review01moNo flagsAdvanced
full-audit03moNo flagsIntermediate
reviewing-code218moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry