code-review

Reviews source files for bugs, security vulnerabilities, performance issues, and code quality problems.

Updated Jun 4, 2026
One-click install
npx skills add https://github.com/nayounghye/my-claude-skills --skill code-review-nayounghye
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/nayounghye/my-claude-skills/tree/main/code-review
Command: npx skills add https://github.com/nayounghye/my-claude-skills --skill code-review-nayounghye

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually reviewing code across security, performance, QA, and style dimensions is time-consuming and easy to do inconsistently. This Skill applies a structured, severity-classified checklist to any file so nothing important gets missed. ## Core Features & Use Cases - Four-Dimension Review: Checks bugs/QA (type safety, error handling, edge cases), security (XSS, SQL injection, auth, secrets), optimization (re-renders, N+1 queries, bundle size, caching), and code quality (DRY, SOLID, naming, consistency). - Severity-Classified Reports: Outputs findings as Critical, Warning, or Suggestion with file/line references, current code, recommended fixes, and reasoning. - Category Filtering: Run a full review or focus on a single category such as performance via a --category argument. - Use Case: Before merging a pull request for a Next.js API route, run the review to catch missing session checks, unhandled promise rejections, and N+1 Airtable queries, then receive a prioritized fix list. ## Quick Start Ask the AI to run a code review on a specific file, for example: review app/api/events/[id]/register/route.ts for security and performance issues.

Frequently Asked Questions about code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a code review on a specific file?▼

Invoke the skill with the file path as an argument, such as /code-review app/api/events/[id]/register/route.ts. You can optionally narrow the scope with a category flag like --category=performance to focus the review.

What does an automated code review checklist cover?▼

It covers four areas: bugs and QA (type safety, error handling, edge cases), security (XSS, SQL injection, auth checks, exposed secrets), optimization (re-renders, N+1 queries, bundle size, caching), and code quality (DRY, SOLID, naming, consistency).

Can I review only security or performance issues instead of everything?▼

Yes, pass a category argument such as --category=performance or --category=security to limit the review to that dimension. Omitting the category runs the full checklist across all four areas.

Does this code review work with Next.js and TypeScript projects?▼

Yes, the checklist is tailored to Next.js App Router, React, and TypeScript codebases, including checks for server-side rendering strategy, NextAuth session validation, and API response formats. It can still review other files with its general checks.

How are code review findings prioritized?▼

Findings are classified into three severity levels: Critical for security vulnerabilities and runtime errors, Warning for performance and maintainability problems, and Suggestion for style and readability improvements. Each finding includes the location, current code, and a recommended fix.