Agent Skills
› companion-inc/feynman
› ligandmpnn
ligandmpnn
GitHub用于配体感知蛋白质序列设计，涵盖残基重设计、约束设置及评分筛选。支持基于小分子环境的蛋白质结构优化与候选设计生成。
Trigger Scenarios
配体感知的蛋白质序列设计
残基重设计任务
带有特定约束的蛋白质设计
Install
npx skills add companion-inc/feynman --skill ligandmpnn -g -y
SKILL.md
Frontmatter
{
"name": "ligandmpnn",
"description": "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."
}
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.
Version History
- 54d08a3 Current 2026-07-25 07:15
