DiffDock
SkillProductivityThis skill lets your AI run and plan DiffDock molecular docking, which predicts how a drug-like molecule binds to a protein. Once added, your AI can handle the workflow from preparing the inputs to checking the predicted binding results.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding the skill, tell your AI which protein and molecule you want to study and ask it to predict the binding pose or plan a docking workflow.
Then ask your AI: use the DiffDock skill
What your AI can do with it
- Predict where and how a drug-like molecule binds to a protein
- Plan a molecular docking workflow step by step
- Set up docking runs
- Prepare ligand and protein inputs for docking
- Rank predicted binding poses
- Verify docking results
What this skill tells your AI
The instructions your AI receives, as published by companion-inc/feynman in skills/diffdock/SKILL.md and read by ahel’s review.
Use this skill for protein-ligand docking and pose review.
Workflow:
- Record protein source, chain selection, binding site context, ligand identity, protonation/tautomer assumptions, and known cofactors.
- Verify the available execution path and dependency stack before claiming a docking run is possible.
- Preserve input PDB/mmCIF, ligand SDF/SMILES, prepared structures, command, seed, package version, and logs.
- Save ranked poses, confidence scores, contact summaries, and 3D previews as Feynman artifacts.
- Compare poses against known ligands, active-site residues, experimental structures, or orthogonal docking where the conclusion matters.
Report docking as a ranked hypothesis, not binding proof.
Signals
- GitHub stars
- 9k
- Forks
- 1k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
diffdock- Source
- github.com/companion-inc/feynman