Agent Skills
› advaitpaliwal/feynman
› chai1
chai1
GitHub用于Chai-1生物分子复合物结构预测的技能。涵盖输入清单构建、执行路径验证、结果保存及置信度审查，确保结构证据的可靠性。
Trigger Scenarios
需要Chai-1进行多聚体或配体结构预测
要求审查生物分子结构的置信度和合理性
Install
npx skills add advaitpaliwal/feynman --skill chai1 -g -y
SKILL.md
Frontmatter
{
"name": "chai1",
"description": "Run or prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs, multimers, ligand\/nucleic acid structure prediction, or confidence review."
}
Chai-1
Use this skill for Chai-1-style biomolecular structure prediction and review.
Workflow:
- Convert the research question into an input manifest with chains, sequences, ligands, nucleic acids, templates, restraints, and seeds.
- Verify the available execution path before running: local model, managed endpoint, Modal job, SSH host, or documented remote API.
- Capture package/model version, exact input manifest, hardware, command or request body, and all raw output files.
- Save structure files and confidence artifacts in the active Feynman output folder.
- Review chain coverage, interface confidence, ligand plausibility, stereochemistry warnings, and conflicts with known structures.
Use the structure as evidence only after the provenance and confidence checks are attached.
Version History
- 54d08a3 Current 2026-07-25 07:15
