Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

TorchDrug Workflow Assistant

Writes and debugs TorchDrug 0.2.1 code for molecular property prediction, generation, retrosynthesis, protein and knowledge-graph learning.

Dev & CodingAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Keeps Claude on the real TorchDrug 0.2.1 API using the four-step datasets → models → tasks → core.Engine pattern.

  • Version guard first: verifies Python 3.7–3.10 and PyTorch 1.8–2.0; flags Apple Silicon as CPU-only (no MPS).
  • Install guidance: matching torch-scatter / torch-cluster wheels to the exact PyTorch + CUDA build instead of copying random URLs.
  • Canonical workflows: property prediction (GIN + PropertyPrediction), self-supervised pretraining (InfoGraph, AttributeMasking), molecule generation (GCPN, GraphAF), retrosynthesis (CenterIdentification + SynthonCompletion), KG reasoning (RotatE, NeuralLP), protein modeling (ESM, GearNet).
  • Troubleshooting: feature-dimension mismatches, device mismatches, checkpoint loading with strict=False.

Who it's for

  • Drug-discovery / cheminformatics researchers and grad students using graph neural nets
  • Developers stuck on TorchDrug install or API errors
  • Anyone burned by hallucinated TorchDrug methods that don't exist

Examples

  1. "Train a toxicity classifier on ClinTox" → full script with GIN, tasks.PropertyPrediction, and core.Engine including a proper 80/10/10 split.
  2. "My torch-scatter import fails" → checks Python/PyTorch/wheel as one compatibility set and gives corrected install commands.
  3. "Build a retrosynthesis pipeline on USPTO50k" → creates seed-synchronized reaction and synthon dataset views, trains both tasks, then composes tasks.Retrosynthesis.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/torchdrug folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/torchdrug/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/torchdrug ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/torchdrug ~/.claude/skills/
  5. Confirm the references/ markdown files came along with it.
  6. Restart Claude Code and ask something like "write TorchDrug code for molecular property prediction" to trigger the skill.
  7. To actually run code, create a Python 3.10 environment and install in the skill's order: torch → torch-scatter/torch-cluster (matched wheels) → torchdrug==0.2.1.
View source on GitHub ↗License: MIT