Agent Skills
› Companion-Inc/feynman
› ml-training-recipe
ml-training-recipe
GitHub从论文、文档和代码中查找可执行的机器学习训练配方，支持微调、训练复现及超参数选择，输出包含数据集、方法和代码的排名配方简报。
触发场景
用户希望进行模型微调或训练
需要复现论文中的实验方法
寻找实用的ML数据集或超参数配置
安装
npx skills add Companion-Inc/feynman --skill ml-training-recipe -g -y
SKILL.md
Frontmatter
{
"name": "ml-training-recipe",
"description": "Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe."
}
ML Training Recipe
Run the /recipe workflow. The slash command expands the full workflow instructions in the active session; do not try to read a relative prompt-template path from the installed skill directory.
Agents used: researcher, optionally verifier
Output: ranked recipe brief in outputs/ with dataset, method, code, and source provenance.
版本历史
- 54d08a3 当前 2026-07-25 07:15
