graph-neural-networks
Implement graph neural networks with PyTorch Geometric for node, edge, and graph tasks
npx skills add majiayu000/claude-skill-registry --skill graph-neural-networks --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Graph Neural Networks ## Architecture Selection | Architecture | Best For | Key Property | Complexity | |-------------|----------|--------------|------------| | **GCN** | Homogeneous graphs, semi-supervised | Spectral convolution, fixed aggregation | Low | | **GAT** | Graphs with varying neighbor importance | Learned attention weights | Medium | | **GraphSAGE** | Large graphs, inductive learning | Sampling + aggregation, works on unseen nodes | Medium | | **GIN** | Graph classification, WL-test expressiveness | Injective aggregation, maximally powerful | Medium | | **HGT** | Heterogeneous graphs, multiple relations | Type-aware attention | High | | **TransE/RotatE** | Knowledge graph link prediction | Translation/rotation in embedding space | Low | | Task | Recommended | Reason | |------|-------------|--------| | **Node classification** | GAT or GraphSAGE | Attention captures varying neighbor relevance | | **Link prediction** | GraphSAGE + dot product | Inductive; generalizes to unseen nodes | | **Graph classification** | GIN + global pooling | Most expressive message passing for graph-level | | **Heterogeneous** | HGT or `to_hetero` wrapper | Handles multiple node/edge types nat
- Architecture Selection
- Core Layer Implementations
- GCN, GAT, GraphSAGE
- Message Passing Framework
- Knowledge Graph Embeddings
- Heterogeneous Graph Handling
- Mini-Batch Training with NeighborLoader
- Link Prediction Pipeline
- Gotchas
What does the graph-neural-networks skill do?
Implement graph neural networks with PyTorch Geometric for node, edge, and graph tasks
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill graph-neural-networks --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.