Skills
.Work. You
Rest

ml-code-review

Community

Thorough ML code reviews for correctness.

Software Engineering#code-review#reproducibility#ml#transformers#diffusion-models#training-loop
Authorschmidtkk
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Reviews AI/ML experiment Python code for correctness, reproducibility, and best practices across PyTorch, TensorFlow, and JAX. It helps identify issues in training loops, data handling, and architectural choices that can affect results and reproducibility.

Core Features & Use Cases

  • Automated ML code reviews focusing on reproducibility, training loop correctness, data handling, and architectural best practices for ML models including diffusion models, Transformers, GANs, and VAEs.
  • Supports PyTorch, TensorFlow, and JAX codebases with domain-aware checks and actionable remediation steps.
  • Generates structured reports with severity levels, concrete fixes, and example invocations to speed up debugging and auditing.

Quick Start

Provide a comprehensive ML code review for a given training script to ensure correctness, reproducibility, and adherence to best practices.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ml-code-review
Download link: https://github.com/schmidtkk/skills/archive/main.zip#ml-code-review

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.