Agent Skills › companion-inc/feynman › evo2

evo2

GitHub

用于生物序列模型工作，涵盖DNA/RNA/蛋白质序列的生成、评分及变异效应分析。提供从定义目标、验证模型到保存结果、分离事实与预测、验证候选项的标准化工作流程，确保生成的序列可追溯且合规。

skills/evo2/SKILL.md companion-inc/feynman

触发场景

需要分析或生成DNA、RNA或蛋白质序列进行生物序列的似然度计算、编辑或设计执行长上下文生物建模任务

安装

npx skills add companion-inc/feynman --skill evo2 -g -y

更多选项

不安装直接使用

npx skills use companion-inc/feynman@evo2

指定 Agent (Claude Code)

npx skills add companion-inc/feynman --skill evo2 -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": "evo2",
    "description": "Use Evo2-style biological sequence models for generation, scoring, or variant-effect analysis. Use when a task asks about DNA\/RNA\/protein sequence likelihood, editing, design, or long-context biological modeling."
}

Evo2

Use this skill for biological sequence-model work.

Workflow:

Define the sequence type, coordinate system, genome/proteome source, objective, constraints, and evaluation metric.
Verify the model endpoint, checkpoint, tokenizer, max context, and license/access boundary before running.
Save input sequences, prompts or scoring windows, model version, parameters, seeds, raw outputs, and parsed tables.
Separate source-owned biological facts from model-owned scores, generated variants, or predictions.
Validate top candidates against databases, conservation, known motifs, structure, or experiments before presenting them as actionable.

Keep generated sequences bounded and auditable.