Skillzwave Logo
Skillzwave

torch-geometric

14011 stars 1210 forks
84
B

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

Marketplace
Also in: machine learning

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install davila7/claude-code-templates/torch-geometric
skilz install davila7/claude-code-templates/torch-geometric --agent opencode
skilz install davila7/claude-code-templates/torch-geometric --agent codex
skilz install davila7/claude-code-templates/torch-geometric --agent gemini

First time? Install Skilz: pip install skilz

Works with 14 AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/davila7/claude-code-templates
2. Copy the agent skill directory:
cp -r claude-code-templates/cli-tool/components/skills/scientific/torch_geometric ~/.claude/skills/
View on GitHub

Need detailed installation help? Check our platform-specific guides:

Claude Desktop Guide Claude Code Guide Troubleshooting

Related Agentic Skills

tailwind-shadcn-setup

by vanman2024

Setup Tailwind CSS and shadcn/ui component library for Next.js projects. Use when configuring Tailwind CSS, installing shadcn/ui, setting up design...

89
TECHjavascript
Marketplace

spanish-language-tutor

by sandraschi

Comprehensive Spanish language expert covering grammar, conversation, regional dialects, and language learning strategies

88
javascript
Marketplace

frontend-dev-guidelines

by diet103

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organiz...

85
TECHjavascript
Marketplace

skill-writer

by pytorch

Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help w...

76
javascript
Marketplace

Agentic Skill Details

Owner
davila7 (GitHub)
Repository
claude-code-templates
Stars
14011
Forks
1210
Type
Technical
Meta-Domain
development
Primary Domain
javascript
Market Score
84
Agentic Skill Grades →

Agent Skill Grade

B
Score: 84/100 Click to see breakdown

Score Breakdown

Spec Compliance
10/15
PDA Architecture
23/30
Ease of Use
22/25
Writing Style
9/10
Utility
17/20
Modifiers: +3

Areas to Improve

  • Description needs trigger phrases
  • Missing Table of Contents
  • Workflow Clarity in Training Sections

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-19

Developer Feedback

I took a look at your torch_geometric skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 84/100, solidly in B territory. This is based on Anthropic's skill best practices. Your strongest area is Writing Style (9/10) — the documentation is clear and uses consistent imperative voice. The weakest link is Spec Compliance (10/15), mainly around metadata and description clarity. The good news? These issues are totally fixable.

What's Working Well

  • Layered structure (9/10) — You nailed the reference pattern. Main SKILL.md gives overview, then separate files for layers, transforms, and datasets. That's how progressive disclosure should work.
  • Examples are solid (3/3) — You've got real code templates for node classification, link prediction, and graph-level tasks. Not just toy examples.
  • Consistent terminology — "PyTorch Geometric," "GNN," "edge_index" used consistently throughout. Makes it easy to follow.
  • Trigger discoverability — Clear terms like "Graph Neural Networks," "GNN," "molecular property prediction" naturally emerge in the content.

The Big One: Add Trigger Phrases to Description

Why it matters: Your frontmatter description currently reads like a feature list: "Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, hetero..."

The problem? When someone asks Claude "when should I use torch_geometric?", this description doesn't have explicit triggers. Triggers are the phrases that match user queries to your skill.

The fix:

description: Performs torch_geometric operations. Use when ask...

Browse Category

More development Agentic Skills

Report Security Issue

Found a security vulnerability in this agent skill?