pytorch — Claude Code skill: what it does, how to install
Guides AI coding agents through building PyTorch architectures, fine-tuning Hugging Face transformers, running diffusion models, and optimizing GPU memory.
npx skills add Mindrally/skills --skill pytorch -a claude-codeWhat pytorch does
This skill establishes practical rules for deep learning engineering in PyTorch. The agent implements architectures by subclassing nn.Module, initializes weights inside __init__, and registers non-trainable tensors as buffers. Forward pass logic sits cleanly inside forward. For evaluation and inference, the agent wraps passes in torch.no_grad().
The instructions cover pre-trained transformers from Hugging Face alongside diffusion pipelines from the Diffusers library, including SDXL. To run generative pipelines, external packages like transformers and diffusers must be installed in the environment. Large batch training relies on torch.cuda.amp for mixed precision and gradient accumulation to prevent out-of-memory errors on GPUs. Multi-GPU setups use DistributedDataParallel or DataParallel.
Data pipelines use custom DataLoaders with streaming support for large datasets. Training loops include learning rate schedulers, early stopping, and gradient clipping to avoid numerical instabilities. For interactive testing, the agent scaffolds Gradio demos with built-in error handling. Code stays concise and direct.
What it helps with
- Build custom neural network architectures with
nn.Module - Fine-tune transformer models using LoRA or P-tuning
- Run diffusion pipelines with SDXL and noise schedulers
- Enable mixed precision training via
torch.cuda.ampto reduce GPU memory usage - Scaffold a Gradio demo interface for model inference
Example prompts for the agent
- Create a custom PyTorch
nn.Modulewith registered buffers and weight initialization - Set up LoRA fine-tuning for a Hugging Face transformer with
torch.cuda.amp - Build an SDXL diffusion pipeline with a Gradio inference interface
How to install pytorch
1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill pytorch -a claude-code2Manually: put the files in place
~/.claude/skills/pytorch/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pytorch/
1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill pytorch -a codex2Manually: put the files in place
.agents/skills/pytorch/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill pytorch -a cursor2Manually: put the files in place
.cursor/skills/pytorch/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Mindrally/skills pytorch2Manually: put the files in place
.github/skills/pytorch/SKILL.md1Skills CLI (Vercel)
npx skills add Mindrally/skills --skill pytorch -a gemini-cli2Platform CLI
gemini skills install https://github.com/Mindrally/skills --path pytorchManually: put the files in place
.devin/skills/pytorch/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Mindrally/skills --skill pytorch -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pytorch
How do I install the pytorch skill in Claude Code?
Run npx skills add Mindrally/skills --skill pytorch -a claude-code in your terminal.
What does the pytorch skill do?
It guides your AI assistant to generate modular PyTorch code, configure mixed precision training, and apply proper weight initialization. It also structures transformer fine-tuning and diffusion pipelines.
How does the skill handle multi-GPU training?
It instructs the agent to configure DistributedDataParallel or DataParallel along with gradient accumulation and profiling tools to locate performance bottlenecks.
Source text
SKILL.md · Apache-2.0
--- name: pytorch description: PyTorch deep learning development with transformers, diffusion models, and GPU optimization. metadata: maintainer: Mindrally source: https://github.com/Mindrally/skills --- # PyTorch Development You are an expert in deep learning with PyTorch, transformers, and diffusion models. ## Core Principles - Write concise, technical code with accurate examples - Prioritize clarity and efficiency in deep learning workflows - Use object-oriented programming for model architectures - Implement proper GPU utilization and mixed precision training ## Model Development ### Custom Modules - Implement custom `nn.Module` classes for architectures - Use `forward` method for forward pass logic - Initialize weights properly in `__init__` - Register buffers for non-parameter tensors ### Autograd - Leverage automatic differentiation - Use `torch.no_grad()` for inference - Implement custom autograd functions when needed - Handle gradient accumulation properly ## Transformers Integration - Use Hugging Face Transformers for pre-trained models - Implement attention mechanisms correctly - Apply efficient fine-tuning (LoRA, P-tuning) - Handle tokenization and sequences properly ## Diffusion Models - Use Diffusers library for diffusion model work - Implement forward/reverse diffusion processes - Utilize appropriate noise schedulers - Understand pipeline variants (SDXL, etc.) ## Training Best Practices ### Data Loading - Implement efficient DataLoaders - Use proper train/validation/test splits - Apply data augmentation appropriately - Handle large datasets with streaming ### Optimization - Apply learning rate scheduling - Implement early stopping - Use gradient clipping for stability - Handle NaN/Inf values properly ## Performance Optimization - Use DataParallel/DistributedDataParallel for multi-GPU - Implement gradient accumulation for large batches - Apply mixed precision with `torch.cuda.amp` - Profile code to identify bottlenecks ## Gradio Integration - Create interactive demos for inference - Build user-friendly interfaces - Handle errors gracefully in demos
© Mindrally · Apache-2.0 · Mindrally/skills
