Building deep learning models with PyTorch can be tricky. This guide shares simple patterns to make your work robust and efficient. You will learn how to write code that works on any device and how to get reproducible results every time.
These tips help you organize model code cleanly. They also show you how to manage tensor shapes and train your models step by step. Whether you are new to PyTorch or have some experience, these practices will save you time and avoid common mistakes.
Global
mkdir -p ~/.claude/skills/pytorch-patternsProject
mkdir -p .claude/skills/pytorch-patternsSource Repository
Env And Assets Bootstraplllllllama/ai-paper-reproduction-skill
Prepare conda-first environment and asset paths for deep learning reproduction
Env And Assets Bootstraplllllllama/rigorpilot-skills
Safe and careful setup of conda environments and asset paths for deep learning reproduction
Run Trainlllllllama/rigorpilot-skills
Run deep learning training conservatively with structured logs and metrics
Explore Runlllllllama/rigorpilot-skills
Plan and rank quick deep learning exploration runs with clear boundaries
Powerbi Modelinggithub/awesome-copilot
Expert guidance for building optimized Power BI semantic models with star schemas and DAX
Power Bi Dax Optimizationgithub/awesome-copilot
Make your Power BI DAX formulas faster and easier to maintain
Power Bi Model Design Reviewgithub/awesome-copilot
Review your Power BI data model design to improve speed and reliability
Power Bi Performance Troubleshootinggithub/awesome-copilot
Find and fix Power BI performance issues with clear step by step guidance