Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
8.7
Rating
0
Installs
Machine Learning
Category
Exceptional skill for PyTorch Geometric GNNs. The description clearly covers node/graph classification, link prediction, and various architectures (GCN, GAT, GraphSAGE), enabling effective CLI invocation. Task knowledge is outstanding with complete code examples for basic graphs, dataset loading, custom layers, training workflows (node/graph classification, neighbor sampling), heterogeneous graphs, transforms, explainability, and pooling. Structure is excellent—concise overview with well-organized sections and references to separate documentation files for layers, datasets, and transforms, avoiding clutter. Novelty is strong: GNN implementation requires specialized knowledge of message passing, graph batching, COO format, and neighbor sampling that would consume significant CLI agent tokens. Minor improvement possible: could add brief link prediction example in main doc. Overall, this is a production-ready, highly valuable skill.
davila7
Skill Author
Loading SKILL.md…
