Diffdock
OthersdiffdockDiffdock is an Agent Skill for general use published in the companion-inc/feynman repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
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.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/companion-inc/feynman/blob/HEAD/skills/diffdock/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/diffdock, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
DiffDock
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.