# Proteinmpnn

> Proteinmpnn 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 from fixed backbone structures with ProteinMPNN-style workflows. Use when a task asks for backbone-conditioned sequence design, mutation suggestions, fixed residues, or design filtering.

- Skill name: `proteinmpnn`
- Category: [Others](https://www.openparable.com/skill/others/1)
- Source: https://github.com/companion-inc/feynman/blob/HEAD/skills/proteinmpnn/SKILL.md
- Repository: companion-inc/feynman (8,301 GitHub stars when collected)

## SKILL.md

# ProteinMPNN

Use this skill for fixed-backbone protein sequence design.

Workflow:

1. Record input structure, chain ids, designed positions, fixed residues, tied positions, symmetry, and design objective.
2. Verify the local or remote execution route before running.
3. Save PDB/mmCIF inputs, design masks, command, seeds, model version, FASTA outputs, and score tables.
4. Filter designs by constraints, diversity, motifs, structure prediction, conservation, and assay-ready feasibility.
5. Attach provenance and a verification plan before recommending candidates.

Treat generated sequences as candidates that require structural and experimental validation.

---

Source: https://www.openparable.com/skill/others/proteinmpnn (OpenParable). Cite the canonical URL above.