Agent Skills
› companion-inc/feynman
› fair-esm2
fair-esm2
GitHub利用ESM2蛋白质语言模型进行序列嵌入、突变评分、同源分析及表示分析，支持聚类与功能初筛，强调结果验证与数据完整性。
Trigger Scenarios
需要蛋白质嵌入向量
执行零样本变异评分
进行序列-功能分选
蛋白质序列聚类分析
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
