Can this skill help with GPU driver issues?

Yes, it specializes in diagnosing and configuring NVIDIA drivers, CUDA, and cuDNN for optimal machine learning performance on Linux.

Can I use this for cloud-based Linux instances?

Yes, it is ideal for setting up ML environments on AWS EC2, GCP, or Azure GPU instances running Linux distributions.

Does it include support for Jupyter?

Yes, it assists with the installation and configuration of Jupyter Notebooks and JupyterLab for interactive data exploration and visualization.

Does it support multiple Python versions?

Absolutely; it provides guidance on using Conda, virtualenv, and pyenv to manage isolated environments for different project requirements.

Data Science & AI Setup

Name: Data Science & AI Setup
Author: pluginagentmarketplace

bypluginagentmarketplace

•

数据科学与机器学习

Configures and optimizes Linux-based data science and machine learning environments with full hardware acceleration support.

关于

The Data Science & AI Setup skill empowers Claude to architect, install, and troubleshoot complex machine learning development environments on Linux systems. It provides deep expertise in managing NVIDIA GPU drivers, CUDA libraries, and deep learning frameworks like PyTorch and TensorFlow, while ensuring seamless integration with Python environment managers and Jupyter-based workflows. This skill is essential for developers and data scientists who need to move from a fresh Linux install to a production-ready AI workstation efficiently.

主要功能

Automated GPU acceleration setup with CUDA and cuDNN
Deep learning framework installation for TensorFlow and PyTorch
Python environment orchestration using Conda and pyenv
Jupyter Notebook and data science toolchain configuration
1 GitHub stars
Docker containerization with NVIDIA Container Toolkit support

使用场景

Containerizing ML workflows for reproducible deployments with GPU passthrough
Setting up a new Linux workstation for deep learning model training
Troubleshooting broken CUDA drivers or library version conflicts

关于

主要功能

Automated GPU acceleration setup with CUDA and cuDNN
Deep learning framework installation for TensorFlow and PyTorch
Python environment orchestration using Conda and pyenv
Jupyter Notebook and data science toolchain configuration
1 GitHub stars
Docker containerization with NVIDIA Container Toolkit support

使用场景

Containerizing ML workflows for reproducible deployments with GPU passthrough
Setting up a new Linux workstation for deep learning model training
Troubleshooting broken CUDA drivers or library version conflicts