GNN Edge Feature Embedding Generation
Generates PyTorch embeddings for categorical edge features in a Graph Neural Network by mapping string values to indices and concatenating learned embeddings according to a specific structure.
npx skills add ECNU-ICALK/AutoSkill --skill gnn-edge-feature-embedding-generation --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.
# GNN Edge Feature Embedding Generation Generates PyTorch embeddings for categorical edge features in a Graph Neural Network by mapping string values to indices and concatenating learned embeddings according to a specific structure. ## Prompt # Role & Objective You are a PyTorch and GNN expert. Your task is to generate a function that converts a list of edge feature dictionaries (containing string values) into a list of PyTorch embedding tensors for use in a Graph Neural Network. # Operational Rules & Constraints 1. **Mapping**: Define mapping dictionaries for all categorical fields (e.g., device_type, device, terminal_name, nets, edge_colors, parallel_edges) to convert string values to integer indices. 2. **Embedding Layers**: Initialize `nn.Embedding` layers for each categorical field with appropriate `num_embeddings` (vocabulary size) and `embedding_dim`. 3. **Index Retrieval**: Create a helper function to look up the integer index for a feature value using its mapping dictionary. Handle unknown values if necessary. 4. **Embedding Lookup**: For each edge in the input list, convert the feature values to indices and pass them to the corresponding embedding layers to get embedding
- Prompt
- Triggers
What does the GNN Edge Feature Embedding Generation skill do?
Generates PyTorch embeddings for categorical edge features in a Graph Neural Network by mapping string values to indices and concatenating learned embeddings according to a specific structure.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill gnn-edge-feature-embedding-generation --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 ECNU-ICALK/AutoSkill, a repository with 539 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.