Agent Skills › advaitpaliwal/feynman › compute-env-setup

compute-env-setup

GitHub

为研究任务配置可复现的计算环境，涵盖包管理、GPU库及容器等。通过识别需求、选择运行路径、验证凭据并记录环境信息，最终执行冒烟测试以确保环境就绪和依赖完整。

skills/compute-env-setup/SKILL.md advaitpaliwal/feynman

触发场景

需要配置Python/R包或GPU库的研究任务涉及Modal、SSH或Slurm等运行时设置的任务

安装

npx skills add advaitpaliwal/feynman --skill compute-env-setup -g -y

更多选项

不安装直接使用

npx skills use advaitpaliwal/feynman@compute-env-setup

指定 Agent (Claude Code)

npx skills add advaitpaliwal/feynman --skill compute-env-setup -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": "compute-env-setup",
    "description": "Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python\/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup."
}

Compute Environment Setup

Use this skill before running a research job that needs a nontrivial runtime.

Workflow:

Identify the job type, hardware need, data size, package stack, secrets, and expected artifacts.
Choose the smallest working route: local notebook runtime, project virtualenv/conda, Modal, SSH/Slurm, or managed endpoint.
Verify credentials and CLIs through Feynman Settings or environment status without printing secret values.
Write an environment note containing package versions, install commands, cache paths, hardware, and failure modes.
Run a tiny smoke job before the expensive job and save the smoke logs.

The done state is a recorded, reproducible environment plus a successful smoke or a precise missing dependency.