code-review

Review code changes for bugs, security vulnerabilities, and performance regressions.

2|1|Updated May 17, 2026
One-click install
npx skills add https://github.com/rakibulism/agent-skills-os --skill code-review-rakibulism
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/rakibulism/agent-skills-os/tree/main/skills/engineering-code-review
Command: npx skills add https://github.com/rakibulism/agent-skills-os --skill code-review-rakibulism

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you evaluate code changes before they ship, focusing on bugs, security issues, performance regressions, and maintainability problems that are easy to miss during development.

Core Features & Use Cases

  • Security Review: Flags issues like injection risks, auth flaws, unsafe deserialization, secrets exposure, and other common vulnerabilities.
  • Performance and Correctness Review: Spots N+1 queries, inefficient loops, race conditions, edge-case failures, and error-handling gaps.
  • Actionable Feedback: Produces prioritized findings, concrete suggestions, and a clear verdict so teams can decide whether to approve or request changes.

Quick Start

Ask the assistant to review a PR, diff, or file path for security, performance, and correctness issues.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I check a pull request for security vulnerabilities and performance regressions?

To check a pull request for security vulnerabilities and performance regressions, submit the PR, diff, or file path to the assistant, which evaluates the changes and produces prioritized findings with actionable fix recommendations.

What kinds of bugs and security issues can a code review catch before shipping?

A code review can catch injection risks, auth flaws, unsafe deserialization, secrets exposure, N+1 queries, inefficient loops, race conditions, and edge-case failures before changes ship.

Does this work for reviewing frontend and infrastructure code, or just backend?

This works for reviewing frontend and infrastructure code, as well as backend changes, applying its correctness and security checks across all layers of the codebase.

How do I get actionable feedback on a diff to decide whether to approve or request changes?

To get actionable feedback on a diff, submit it to the assistant, which outputs structured findings with prioritized severity, file and line references, and a clear verdict to help teams decide whether to approve or request changes.

What is the best way to identify N+1 queries and error-handling gaps in file-level changes?

The best way to identify N+1 queries and error-handling gaps in file-level changes is to submit the files for a performance and correctness review, which spots inefficient loops and edge-case failures.

Why does my code review need prioritized severity and file references?

A code review needs prioritized severity and file references to produce structured findings, enabling teams to quickly locate issues and make informed decisions on whether to approve or request changes.