code-review-and-quality

Identify correctness, security, architecture, and test risks in code diffs.

6|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/moberghr/mtk-agent-toolkit --skill code-review-and-quality-moberghr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review-and-quality
Source: https://github.com/moberghr/mtk-agent-toolkit/tree/main/.claude/skills/code-review-and-quality
Command: npx skills add https://github.com/moberghr/mtk-agent-toolkit --skill code-review-and-quality-moberghr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams catch real risks in code changes by performing adversarial reviews focused on correctness, security, architecture, and test quality.

Core Features & Use Cases

  • Adversarial review focus: identify deep risks beyond style checks.
  • PR and merge-safety checks: guide post-implementation reviews to reduce regressions.
  • Reference-driven: aligns with CLAUDE.md standards and relevant security/testing guides.

Quick Start

Provide an adversarial review of the latest diff to identify critical risks and report findings.

Frequently Asked Questions about code-review-and-quality

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

FAQPage Schema
How do I perform an adversarial code review on a pull request to find security and correctness risks?

Adversarial code review identifies deep risks in pull requests by evaluating diffs against security, testing, and performance references. It guides reviewers through sensitivity areas to catch potential regressions and architecture issues beyond standard style checks.

What is a merge-safety audit and when do I need one for my code changes?

A merge-safety audit is a post-implementation review that checks code changes for correctness, security, architecture, and test quality. You need one to reduce regressions and ensure code aligns with project standards before merging.

How do I review a diff to ensure it meets my project's testing and architecture standards?

Review a diff by loading standards from CLAUDE.md and evaluating the changes against relevant security and testing guides. This reference-driven approach produces structured findings that highlight critical risks.

Can I use this code review approach across any tech stack or is it framework-specific?

You can use this adversarial review approach across any tech stack. It focuses on identifying deep risks in correctness, security, architecture, and test quality without relying on framework-specific rules.

What is the difference between an adversarial review and a standard code style check?

An adversarial review focuses on identifying deep risks in correctness, security, architecture, and test quality. Standard code style checks only format syntax, while adversarial reviews evaluate diffs against performance references to prevent regressions.