Agent Skills › companion-inc/feynman › fair-esm2

fair-esm2

GitHub

基于ESM2蛋白质语言模型进行序列嵌入、突变评分及功能分析，支持聚类与远程同源性检测。提供标准化FASTA处理、结果验证及质量标记工作流，适用于生物信息学特征提取与假设生成。

skills/fair-esm2/SKILL.md companion-inc/feynman

Trigger Scenarios

需要蛋白质序列嵌入向量进行零样本变异效应评分执行蛋白质序列聚类分析评估序列-功能关系

Install

npx skills add companion-inc/feynman --skill fair-esm2 -g -y

More Options

Use without installing

npx skills use companion-inc/feynman@fair-esm2

指定 Agent (Claude Code)

npx skills add companion-inc/feynman --skill fair-esm2 -a claude-code -g -y

安装 repo 全部 skill

npx skills add companion-inc/feynman --all -g -y

预览 repo 内 skill

npx skills add companion-inc/feynman --list

SKILL.md

Frontmatter

{
    "name": "fair-esm2",
    "description": "Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use when a task needs protein embeddings, zero-shot variant scores, clustering, or sequence-function triage."
}

Fair ESM2

Use this skill for ESM2-style protein language model analysis.

Workflow:

Normalize proteins into FASTA with stable identifiers and mutation notation.
Verify the local package, checkpoint, endpoint, or notebook route before execution.
Save embeddings, variant-score tables, clustering plots, model version, command, and runtime logs.
Compare model-derived rankings against UniProt, structures, conservation, assays, or literature.
Mark sequence regions with poor coverage, disorder, low homology, or domain-boundary ambiguity.

Use ESM2 outputs as features or hypotheses unless a source-backed validation step supports the conclusion.