Agent Skills › alphaXiv/OpenResearch › orx-instances

orx-instances

GitHub

用于通过 CLI 创建持久化的 OpenResearch 计算实例，支持 GPU/CPU 配置及不同云提供商，适用于需 SSH 手动操作的场景。

agent-skills/orx-instances/SKILL.md alphaXiv/OpenResearch

触发场景

用户需要创建持久化计算环境用户希望通过 SSH 连接并手动工作

安装

npx skills add alphaXiv/OpenResearch --skill orx-instances -g -y

更多选项

非标准路径

npx skills add https://github.com/alphaXiv/OpenResearch/tree/main/agent-skills/orx-instances -g -y

不安装直接使用

npx skills use alphaXiv/OpenResearch@orx-instances

指定 Agent (Claude Code)

npx skills add alphaXiv/OpenResearch --skill orx-instances -a claude-code -g -y

安装 repo 全部 skill

npx skills add alphaXiv/OpenResearch --all -g -y

预览 repo 内 skill

npx skills add alphaXiv/OpenResearch --list

SKILL.md

Frontmatter

{
    "name": "orx-instances",
    "description": "Create standalone OpenResearch compute instances with `orx instance create`. Use when the user wants a persistent machine for manual or ad-hoc work rather than an experiment run."
}

Standalone instances

Provision a persistent instance in an organization when the user wants to SSH in and work manually. Experiment runs use orx exp run instead.

orx instance create <orgId> --gpu H100_SXM --count 1 [--disk 100]
orx instance create <orgId> --gpu H100_SXM --provider runpod
orx instance create <orgId> --cpu cpu5g --vcpus 8

<orgId> comes from orx orgs.
Choose exactly one of --gpu or --cpu.
--count and --disk apply to GPU instances; --vcpus applies to CPU.
Omitting --provider chooses the cheapest matching offer; pass it to pin a provider.
Provisioning is asynchronous. The command prints the instance id and status; its SSH host appears when the machine becomes ready.