Ligandmpnn
OthersligandmpnnLigandmpnn 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.
Design protein sequences around ligand or small-molecule contexts with LigandMPNN-style workflows. Use when a task asks for ligand-aware protein design, residue redesign, constraints, or design ranking.
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/ligandmpnn/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/ligandmpnn, 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.
LigandMPNN
Use this skill for ligand-aware protein sequence design.
Workflow:
- Record the input structure, ligand identity, chain/residue design mask, fixed residues, symmetry, and design objective.
- Verify the execution route and model availability before running.
- Save input structure, ligand file, residue masks, command, seeds, model version, generated FASTA, and score tables.
- Filter outputs by constraint satisfaction, sequence diversity, known motifs, predicted structure confidence, and ligand-contact plausibility.
- Send shortlisted designs through an independent structural or literature/database check before presenting them as candidates.
Generated designs must remain tied to exact input structures and constraints.