Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.
安装
npx skills add K-Dense-AI/scientific-agent-skills --skill torch-geometricnpx skills add K-Dense-AI/scientific-agent-skills --skill torch-geometric -a claude-code -gnpx skills add K-Dense-AI/scientific-agent-skills --skill torch-geometric -a codex -ggemini skills install https://github.com/K-Dense-AI/scientific-agent-skills.git --path skills/torch-geometricgh skill install K-Dense-AI/scientific-agent-skills torch-geometricgit clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills /tmp/K-Dense-AI__scientific-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/K-Dense-AI__scientific-agent-skills/skills/torch-geometric ~/.claude/skills/torch-geometric # Claude Code
cp -R /tmp/K-Dense-AI__scientific-agent-skills/skills/torch-geometric ~/.agents/skills/torch-geometric # Codex, Cursor, Gemini CLI, Copilot, OpenCode