code-review-expert

Perform multi-agent code reviews across security, architecture, performance, reliability, and quality.

3|2|Updated Mar 6, 2026

Search Tags:#code quality #code review #security audit #ai agent #performance analysis #architecture review

Ready to run

npx skills add https://github.com/YuhangNie/sub2api --skill code-review-expert-yuhangnie

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: code-review-expert
Source: https://github.com/YuhangNie/sub2api/tree/main/skills/code-review-expert
Command: npx skills add https://github.com/YuhangNie/sub2api --skill code-review-expert-yuhangnie

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the comprehensive review of code for security vulnerabilities, architectural flaws, performance issues, reliability concerns, and general code quality, ensuring higher standards and reducing manual review time.

Core Features & Use Cases

Multi-dimensional Analysis: Conducts reviews across five key areas: Security, Architecture, Performance, Reliability, and Quality.
Parallel Agent Execution: Utilizes multiple specialized AI agents working concurrently in isolated environments for faster results.
Context7 Anti-Hallucination: Integrates with Context7 to verify API usage against official documentation, preventing AI hallucinations.
Use Case: A development team can use this Skill to automatically audit a new feature branch before merging, catching critical bugs and security risks early in the development cycle.

Quick Start

Use the code-review-expert skill to perform a full code review on the current git repository.

Frequently Asked Questions about code-review-expert

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

FAQPage Schema

How do I automate code review for security vulnerabilities and architecture flaws?▼

Automated code review for security and architecture flaws is done by dispatching parallel AI agents across five dimensions. This approach analyzes vulnerabilities and structural issues concurrently, reducing manual review time and catching bugs early.

How does AI code review prevent hallucinations when verifying API usage?▼

AI code review prevents hallucinations by integrating with Context7 to verify API usage against official documentation. This ensures the analysis accurately reflects current API behaviors rather than relying on potentially outdated model assumptions.

Can I run a multi-dimensional code review on large git repositories?▼

Multi-dimensional code review on large git repositories is supported using adaptive strategies. The process utilizes isolated git worktrees and parallel agent dispatch to handle the scale efficiently while ensuring temporary environments are cleaned up.

What is the best way to review code quality and reliability before merging a feature branch?▼

Reviewing code quality and reliability before a merge is best handled by conducting a comprehensive analysis across security, architecture, performance, and quality dimensions. This automated audit catches critical bugs and security risks early in the development cycle.

Does automated code review work without leaving temporary environments behind?▼

Automated code review ensures complete cleanup of all temporary environments after execution. It uses isolated git worktrees for parallel processing and systematically removes these temporary spaces once the multi-agent review is finished.