data-ai
Linux data science and AI/ML environment setup - TensorFlow, PyTorch, CUDA, Jupyter
When & Why to Use This Skill
The Data AI Skill for Claude is a comprehensive automation tool designed to streamline the setup of Linux-based data science and AI/ML environments. It simplifies the complex process of configuring GPU acceleration (CUDA/cuDNN), managing isolated Python environments, and installing essential machine learning frameworks like PyTorch and TensorFlow, ensuring a stable and optimized workspace for developers.
Use Cases
- GPU Acceleration Setup: Quickly configure NVIDIA drivers, CUDA, and cuDNN to enable high-performance computing for deep learning tasks.
- Environment Management: Create and manage isolated development environments using Conda, virtualenv, or pyenv to avoid dependency conflicts between AI projects.
- ML Framework Installation: Automate the deployment of major libraries such as TensorFlow, PyTorch, and JAX alongside interactive tools like Jupyter Notebooks.
- Containerized Data Science: Set up Docker with GPU support to create portable and reproducible AI development environments across different Linux distributions.
| name | data-ai |
|---|---|
| description | "Linux data science and AI/ML environment setup - TensorFlow, PyTorch, CUDA, Jupyter" |
| sasmp_version | "1.3.0" |
| bonded_agent | linux-expert |
| bond_type | PRIMARY_BOND |
Data Ai Skill
Overview
Master Linux environment configuration for data science and machine learning workflows.
Capabilities
- GPU Setup: CUDA, cuDNN, NVIDIA drivers
- Python Environments: Conda, virtualenv, pyenv
- ML Frameworks: TensorFlow, PyTorch, JAX
- Data Tools: Jupyter, pandas, numpy
- Containerization: Docker with GPU support
Examples
# Check GPU availability
nvidia-smi
# Create ML environment
conda create -n ml python=3.11
conda activate ml
pip install torch torchvision