pytorch-geometric
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)
Profile →npx skills add majiayu000/claude-skill-registry --skill pytorch-geometric --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.
## Overview PyTorch Geometric (PyG) is built on top of PyTorch to simplify the implementation of Graph Neural Networks. It treats graphs as `Data` objects containing node features and edge indices, and provides a powerful `MessagePassing` base class for custom layer development. ## When to Use Use PyG for data that is naturally represented as a graph, such as social networks, molecular structures, or point clouds. Use it when you need to perform node classification, edge prediction, or graph-level regression. ## Decision Tree 1. Do you have a list of small graphs? - USE: `torch_geometric.loader.DataLoader` to create a single giant disjoint graph. 2. Do you need to pool node features into a graph-level feature? - USE: `global_mean_pool` or `global_max_pool` using the `batch` vector. 3. Are you building a custom convolution? - INHERIT: From `torch_geometric.nn.MessagePassing`. ## Workflows 1. **Defining a Custom GNN Layer** 1. Inherit from `torch_geometric.nn.MessagePassing`. 2. Set the aggregation scheme (`aggr='add'`, `'mean'`, or `'max'`) in `__init__`. 3. Implement the forward pass using `self.propagate()`. 4. Define the `message()` function to compute the transformation for each
- Overview
- When to Use
- Decision Tree
- Workflows
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the pytorch-geometric skill do?
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill pytorch-geometric --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.