DiffDock

SkillProductivity

Lets your agent run and plan DiffDock molecular docking to predict how a ligand binds a protein.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the DiffDock skill

About this capability

Run or plan DiffDock molecular docking workflows. Use when a task asks for protein-ligand pose prediction, docking setup, ligand/protein preparation, pose ranking, or docking-result verification.

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:

  1. Record protein source, chain selection, binding site context, ligand identity, protonation/tautomer assumptions, and known cofactors.
  2. Verify the available execution path and dependency stack before claiming a docking run is possible.
  3. Preserve input PDB/mmCIF, ligand SDF/SMILES, prepared structures, command, seed, package version, and logs.
  4. Save ranked poses, confidence scores, contact summaries, and 3D previews as Feynman artifacts.
  5. 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
10k
Forks
1k
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
diffdock-companion-inc
Source
github.com/companion-inc/feynman