code-review

Reviews pull requests for security, performance, code quality, and testing issues.

Updated Dec 23, 2025
One-click install
npx skills add https://github.com/macintorsten/aurapod --skill code-review-macintorsten
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/macintorsten/aurapod/tree/main/.github/skills/code-review
Command: npx skills add https://github.com/macintorsten/aurapod --skill code-review-macintorsten

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manual code reviews are time-consuming and inconsistent, often missing critical security vulnerabilities, performance bottlenecks, or testing gaps that slip into production. ## Core Features & Use Cases - Multi-Category Analysis: Systematically checks code for security flaws (SQL injection, XSS, hardcoded secrets), performance issues (N+1 queries, memory leaks), code quality problems (duplication, poor naming), and testing gaps. - Structured Review Output: Produces a standardized report with severity tiers (Critical, Suggestions, Nits) plus positive feedback, each issue including file location, explanation, and suggested fix. - Use Case: When a teammate opens a pull request adding a new API endpoint, run this review to catch an unparameterized SQL query and missing error handling before merge. ## Quick Start Review the changes in this pull request and flag any security, performance, or code quality issues with suggested fixes.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I review a pull request for security vulnerabilities?▼

Check the diff for SQL injection, XSS, command injection, hardcoded secrets, and improper authentication or authorization. Flag each issue with its file and line number, explain the risk, and suggest a fix such as parameterized queries.

What should a code review checklist include?▼

A solid checklist covers hardcoded secrets, input validation, complete error handling, defined types, tests for new code, performance issues, readability, and documented breaking changes. This skill provides exactly that checklist plus severity-tiered output.

How to detect N+1 query problems during code review?▼

Look for database calls inside loops, such as awaiting a query per user in a forEach. Recommend batching by collecting IDs first and running a single query for all records instead.

Can this review handle languages other than JavaScript?▼

The review categories and checklist are language-agnostic, covering security, performance, quality, and testing patterns. The included code examples use JavaScript and SQL, but the same principles apply to other stacks.

What are the limitations of automated code review?▼

Pattern-based review catches common issues like injection and swallowed errors but cannot judge business logic correctness or architectural fit. Human review is still needed for design decisions and domain-specific behavior.