Agent Skills
› Companion-Inc/feynman
› fair-esm2
fair-esm2
GitHub用于使用ESM2蛋白质语言模型进行嵌入、突变评分、远程同源性和表示分析。适用于需要蛋白嵌入、零样本变体评分、聚类或序列功能筛选的任务。
Trigger Scenarios
需要蛋白质嵌入向量
进行零样本变体评分
执行序列聚类分析
评估序列与功能关系
Install
npx skills add Companion-Inc/feynman --skill fair-esm2 -g -y
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.
Version History
- 54d08a3 Current 2026-07-25 07:15
