菜单
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.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/alphaXiv/OpenResearch --skill orx-instances命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use the `orx` CLI to run local OpenResearch projects from a terminal — create experiment branches, launch and supervise compute, inspect logs and evidence, and manage the experiment tree. Read this before driving `orx` programmatically.
Publication-quality figures in matplotlib or TikZ: learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, method diagrams. Covers the shared style module, sizing, uncertainty, and vector export. Use whenever you plot, chart, or visualize results, add a figure to a paper or report, or one looks unpolished; then read one reference.
Draft an academic paper or preprint as LaTeX. Create a .tex file in the project working tree, where it renders for the user and compiles to PDF. Use for a paper, preprint, manuscript, arXiv or submission draft, or a section of one; generic reports and result summaries belong to `orx-reports`.
正在显示 SKILL.md
| 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. |
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.--gpu or --cpu.--count and --disk apply to GPU instances; --vcpus applies to CPU.--provider chooses the cheapest matching offer; pass it to pin a
provider.