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.zipInstalls 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.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
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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| code-review-checklist (this skill) | 3 | 27d | No flags | Beginner |
| pr-review | 0 | 1mo | No flags | Advanced |
| full-audit | 0 | 3mo | No flags | Intermediate |
| reviewing-code | 21 | 8mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by vudovn
View all by vudovn →You might also like
pr-review
microsoft
Multi-dimensional review of a PR or feature branch in the microsoft/winappcli repo. Activate when a contributor asks to "review my PR", "review my changes", "vet my branch before pushing", "do a full review", "PR review", "review this feature", or similar. Fans out parallel sub-agents covering secur
full-audit
oscardlfr
Run a unified audit across all quality dimensions — architecture, code quality, testing, security, docs, and release readiness. Consolidates findings from multiple agents and scripts into a single deduplicated report.
reviewing-code
CaptainCrouton89
Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
cookbook-audit
anthropics
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
fix-review
sickn33
Verify fix commits address audit findings without new bugs