Agent Skills › advaitpaliwal/feynman › alphafold2

alphafold2

GitHub

用于AlphaFold2风格的蛋白质结构预测与审计，涵盖单体/多聚体预测、MSA处理及置信度评估。支持对比PDB参考数据，确保输入验证与结果可追溯性。

skills/alphafold2/SKILL.md advaitpaliwal/feynman

触发场景

需要预测蛋白质三维结构进行多聚体结构建模评估模型置信度指标如pLDDT和PAE 比对已知结构或AlphaFold DB记录

安装

npx skills add advaitpaliwal/feynman --skill alphafold2 -g -y

更多选项

不安装直接使用

npx skills use advaitpaliwal/feynman@alphafold2

指定 Agent (Claude Code)

npx skills add advaitpaliwal/feynman --skill alphafold2 -a claude-code -g -y

安装 repo 全部 skill

npx skills add advaitpaliwal/feynman --all -g -y

预览 repo 内 skill

npx skills add advaitpaliwal/feynman --list

SKILL.md

Frontmatter

{
    "name": "alphafold2",
    "description": "Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer\/multimer structure prediction, MSA\/template handling, confidence metrics, or comparison against PDB\/AlphaFold references."
}

AlphaFold2

Use this skill for protein-structure prediction or parity checks around AlphaFold2-style outputs.

Workflow:

Capture the biological question, sequence identifiers, FASTA input, oligomer state, organism, and expected cofactors or partners.
Verify the execution route before running: local install, managed endpoint, Modal/SSH job, or a documented public source. Do not assume weights, databases, or GPUs exist.
Save inputs, command or endpoint payload, model settings, stdout/stderr, and raw outputs under the active Feynman artifact folder.
Report pLDDT, PAE, ranking confidence, chain coverage, truncation, templates/MSA provenance, and any residues or interfaces that should not be trusted.
Compare against known structures or AlphaFold DB records when the claim depends on novelty, domain movement, interface geometry, or mutation impact.

Outputs should include the FASTA, predicted PDB/mmCIF, confidence files when available, a short method note, and a .provenance.md sidecar.