code-review

Review git changes for Python, PyTorch, and ML code quality issues.

71|Updated May 9, 2026
One-click install
npx skills add https://github.com/DeepExperience/HyperEyes --skill code-review-deepexperience
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/DeepExperience/HyperEyes/tree/main/RL/relax-hypereyes/Relax/skills/code-review
Command: npx skills add https://github.com/DeepExperience/HyperEyes --skill code-review-deepexperience

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps engineers identify correctness issues, maintainability problems, security risks, and machine learning training bugs in current code changes before they are merged.

Core Features & Use Cases

  • Structured Code Analysis: Reviews git changes for SOLID violations, architecture concerns, Python anti-patterns, and reliability issues.
  • ML and Distributed Training Checks: Evaluates PyTorch workflows, tensor operations, gradient handling, memory usage, and distributed system risks.
  • Security and Cleanup Guidance: Detects vulnerabilities, resource issues, dead code candidates, and provides prioritized remediation plans for Relax framework development.

Quick Start

Ask the code-review skill to review my current git changes and report critical issues, architecture concerns, and recommended 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 git changes for security and maintainability issues before merging?

Review git changes by analyzing code for SOLID violations, security vulnerabilities, and Python anti-patterns. This process evaluates correctness and maintainability problems, providing prioritized remediation plans without automatically modifying the code.

How does code review work for PyTorch distributed training and ML pipelines?

Code review for PyTorch distributed training evaluates tensor operations, gradient handling, memory usage, and distributed system risks. It identifies machine learning training bugs and reliability issues within ML pipeline repositories.

Can I use automated code review to detect dead code and architecture concerns in Python?

Automated code review detects dead code candidates and architecture concerns in Python workflows. It applies structured analysis to identify software quality issues and provides cleanup guidance for Relax framework development.

What is the best way to check SOLID principles and correctness in my current git changes?

Checking SOLID principles and correctness involves reviewing current git changes against software quality standards. This identifies violations, reliability issues, and maintainability problems before integration without modifying the code.

Does this code review process automatically fix the issues it finds?

This code review process does not automatically fix issues. It evaluates code changes to identify software quality, security, correctness, and maintainability problems, then outputs prioritized findings and recommended fixes.