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.