Neural Network Design

This gives Claude knowledge of neural network architecture patterns across CNNs, RNNs, Transformers, and ResNets in PyTorch and TensorFlow. You'd reach for it when building custom architectures for vision tasks, sequence models for time series or NLP, or hybrid networks that mix different layer types. The skill focuses on practical decisions like layer composition, activation functions, normalization, and when to use skip connections. It's solid reference material if you're past tutorial level but want guidance on architecture choices without digging through papers. The 245 GitHub stars suggest it's been useful for others doing actual ML work, not just experiments.

GitHub stars: 317
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aj-geddes/useful-ai-prompts --skill 'Neural Network Design' --agent claude-code

Installs into .claude/skills of the current project.

Files

Neural Network Design

Overview

This skill covers designing and implementing neural network architectures including CNNs, RNNs, Transformers, and ResNets using PyTorch and TensorFlow, with focus on architecture selection, layer composition, and optimization techniques.

When to Use

Designing custom neural network architectures for computer vision tasks like image classification or object detection
Building sequence models for time series forecasting, natural language processing, or video analysis
Implementing transformer-based models for language understanding or generation tasks
Creating hybrid architectures that combine CNNs, RNNs, and attention mechanisms
Optimizing network depth, width, and skip connections for better training and performance
Selecting appropriate activation functions, normalization layers, and regularization techniques