deep-review

Analyze code changes across correctness, tests, UX, performance, and safety.

Updated Feb 24, 2026

Search Tags:#testing #quality assurance #code review #code analysis #software development #ai agent

Ready to run

npx skills add https://github.com/neilmovva/mux --skill deep-review-neilmovva

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deep-review
Source: https://github.com/neilmovva/mux/tree/main/.mux/skills/deep-review
Command: npx skills add https://github.com/neilmovva/mux --skill deep-review-neilmovva

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates and enhances the code review process by leveraging multiple specialized AI sub-agents to provide comprehensive feedback on code changes.

Core Features & Use Cases

Parallelized Review: Utilizes multiple sub-agents to analyze code from different perspectives simultaneously.
Multi-faceted Analysis: Covers correctness, test coverage, consistency, UX, performance, safety, and documentation.
Actionable Findings: Generates specific, actionable feedback with severity levels and file paths.
Use Case: When submitting a complex feature change, this Skill can provide a thorough review covering all aspects, ensuring higher code quality and faster iteration cycles.

Quick Start

Use the deep-review skill to review the attached code changes.

Frequently Asked Questions about deep-review

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

FAQPage Schema

How do I automate code review for complex feature changes?▼

Automating code review involves deploying multiple AI sub-agents to simultaneously analyze correctness, tests, consistency, UX, performance, and safety, producing actionable feedback categorized by severity for complex feature changes.

What does multi-agent code analysis cover?▼

Multi-agent code analysis evaluates correctness, test coverage, consistency, UX, performance, safety, and documentation, synthesizing findings into a consolidated review with actionable issues, questions, and a validation plan.

How do I get actionable feedback with severity levels from a code review?▼

Actionable feedback with severity levels is generated by synthesizing findings from parallelized sub-agents analyzing code from different perspectives, categorizing issues by severity and including specific file paths.

Does AI code review work for safety and performance analysis?▼

AI code review works for safety and performance analysis by utilizing specialized sub-agents to evaluate these aspects simultaneously alongside correctness, tests, consistency, and UX.

Can I generate a validation plan during automated code analysis?▼

Generating a validation plan during automated code analysis is possible by synthesizing findings from multiple specialized sub-agents, outputting a consolidated review with issues, questions, and the validation plan.

What is the best way to review code changes for test coverage and consistency?▼

The best way to review code changes for test coverage and consistency is using parallelized AI sub-agents analyzing these facets simultaneously, synthesizing findings into a consolidated review with actionable feedback.