Agent Skills
› companion-inc/feynman
› openfold3
openfold3
GitHub用于运行或规划 OpenFold3 蛋白质结构预测工作流。涵盖输入标准化、环境验证、结果复现性报告及与 AlphaFold/ESMFold 等模型的对比分析，确保输出可追溯且准确。
Trigger Scenarios
需要预测蛋白质或复合物结构
进行模型结果对比
检查结构预测的可复现性
Install
npx skills add companion-inc/feynman --skill openfold3 -g -y
SKILL.md
Frontmatter
{
"name": "openfold3",
"description": "Run or plan OpenFold3-style structure prediction workflows. Use when a task asks for open protein or complex prediction, setup, model comparison, or reproducibility around OpenFold-family outputs."
}
OpenFold3
Use this skill for OpenFold-family structure prediction or comparison.
Workflow:
- Normalize FASTA, chains, templates, MSAs, ligands or partners, seeds, and expected output format.
- Verify model code, checkpoints, databases, and GPU route before running.
- Save the input manifest, environment lockfile, command, logs, structure outputs, confidence files, and runtime metadata.
- Compare against AlphaFold-style, ESMFold-style, PDB, or literature evidence when the result affects a decision.
- Report reproducibility gaps such as missing databases, unavailable weights, failed templates, or route-specific approximations.
Do not present an OpenFold-family output without version and input provenance.
Version History
- 54d08a3 Current 2026-07-25 07:15
