Skill · em Dados, IA e pesquisa
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/skills/scientific/torch_geometric - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 1 download no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
7 arquivos · 104,5 KB · inclui 3 scripts que executam: scripts/benchmark_model.py, scripts/create_gnn_template.py, scripts/visualize_graph.py
Instalar na sua CLI
O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/skills/torch-geometric/.
d=".claude/skills/torch-geometric" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/torch_geometric" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/datasets_reference.md" "$u/references/datasets_reference.md" \ -o "$d/references/layers_reference.md" "$u/references/layers_reference.md" \ -o "$d/references/transforms_reference.md" "$u/references/transforms_reference.md" \ -o "$d/scripts/benchmark_model.py" "$u/scripts/benchmark_model.py" \ -o "$d/scripts/create_gnn_template.py" "$u/scripts/create_gnn_template.py" \ -o "$d/scripts/visualize_graph.py" "$u/scripts/visualize_graph.py" \ -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.claude/skills/torch-geometric/.
d="$HOME/.claude/skills/torch-geometric" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/torch_geometric" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/datasets_reference.md" "$u/references/datasets_reference.md" \ -o "$d/references/layers_reference.md" "$u/references/layers_reference.md" \ -o "$d/references/transforms_reference.md" "$u/references/transforms_reference.md" \ -o "$d/scripts/benchmark_model.py" "$u/scripts/benchmark_model.py" \ -o "$d/scripts/create_gnn_template.py" "$u/scripts/create_gnn_template.py" \ -o "$d/scripts/visualize_graph.py" "$u/scripts/visualize_graph.py" \ -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Codex
Neste projeto: instala em .agents/skills/torch-geometric/.
d=".agents/skills/torch-geometric" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/torch_geometric" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/datasets_reference.md" "$u/references/datasets_reference.md" \ -o "$d/references/layers_reference.md" "$u/references/layers_reference.md" \ -o "$d/references/transforms_reference.md" "$u/references/transforms_reference.md" \ -o "$d/scripts/benchmark_model.py" "$u/scripts/benchmark_model.py" \ -o "$d/scripts/create_gnn_template.py" "$u/scripts/create_gnn_template.py" \ -o "$d/scripts/visualize_graph.py" "$u/scripts/visualize_graph.py" \ -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.agents/skills/torch-geometric/.
d="$HOME/.agents/skills/torch-geometric" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/torch_geometric" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/datasets_reference.md" "$u/references/datasets_reference.md" \ -o "$d/references/layers_reference.md" "$u/references/layers_reference.md" \ -o "$d/references/transforms_reference.md" "$u/references/transforms_reference.md" \ -o "$d/scripts/benchmark_model.py" "$u/scripts/benchmark_model.py" \ -o "$d/scripts/create_gnn_template.py" "$u/scripts/create_gnn_template.py" \ -o "$d/scripts/visualize_graph.py" "$u/scripts/visualize_graph.py" \ -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Antigravity
Neste projeto: instala em .agents/skills/torch-geometric/.
d=".agents/skills/torch-geometric" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/torch_geometric" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/datasets_reference.md" "$u/references/datasets_reference.md" \ -o "$d/references/layers_reference.md" "$u/references/layers_reference.md" \ -o "$d/references/transforms_reference.md" "$u/references/transforms_reference.md" \ -o "$d/scripts/benchmark_model.py" "$u/scripts/benchmark_model.py" \ -o "$d/scripts/create_gnn_template.py" "$u/scripts/create_gnn_template.py" \ -o "$d/scripts/visualize_graph.py" "$u/scripts/visualize_graph.py" \ -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.gemini/antigravity-cli/skills/torch-geometric/.
d="$HOME/.gemini/antigravity-cli/skills/torch-geometric" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/torch_geometric" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/datasets_reference.md" "$u/references/datasets_reference.md" \ -o "$d/references/layers_reference.md" "$u/references/layers_reference.md" \ -o "$d/references/transforms_reference.md" "$u/references/transforms_reference.md" \ -o "$d/scripts/benchmark_model.py" "$u/scripts/benchmark_model.py" \ -o "$d/scripts/create_gnn_template.py" "$u/scripts/create_gnn_template.py" \ -o "$d/scripts/visualize_graph.py" "$u/scripts/visualize_graph.py" \ -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Peça ao Rook
Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.torch-geometric
Prévia do SKILL.md
---
name: torch-geometric
description: "Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning."
---
# PyTorch Geometric (PyG)
## Overview
PyTorch Geometric is a library built on PyTorch for developing and training Graph Neural Networks (GNNs). Apply this skill for deep learning on graphs and irregular structures, including mini-batch processing, multi-GPU training, and geometric deep learning applications.
## When to Use This Skill
This skill should be used when working with:
- **Graph-based machine learning**: Node classification, graph classification, link prediction
- **Molecular property prediction**: Drug discovery, chemical property prediction
- **Social network analysis**: Community detection, influence prediction
- **Citation networks**: Paper classification, recommendation systems
- **3D geometric data**: Point clouds, meshes, molecular structures
- **Heterogeneous graphs**: Multi-type nodes and edges (e.g., knowledge graphs)
- **Large-scale graph learning**: Neighbor sampling, distributed training
## Quick Start
### Installation
```bash
uv pip install torch_geometric
```
For additional dependencies (sparse operations, clustering):
```bash
uv pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-${TORCH}+${CUDA}.html
```
### Basic Graph Creation
```python
import torch
from torch_geometric.data import Data
…