CoreWeave Skills 开启公测,Claude Code 可一键搭建 GPU 集群
这个技能包装好后,你在 Claude Code 里说一句话就能建出 CKS 集群、加 GPU 节点、用 vLLM 把模型跑起来,还会帮你确认 GPU 没闲着。以前要写一堆 kubectl 和 Terraform,现在省了,经常起推理环境的人可以直接试。
CoreWeave 发布 CoreWeave Skills 公开预览版,官方 GitHub 仓库提供一次性安装。安装后 Claude Code 可以直接操作 CoreWeave Kubernetes Service(CKS),完成搭建集群、添加 GPU Node Pool 等任务。
具体流程是:Claude Code 调用 CKS 创建集群,加入 GPU 节点池,再用 vLLM 部署模型服务,最后检查 GPU 的实际利用率是否打满。也就是说,从裸集群到模型推理服务这一整条链路都能通过对话完成。
这属于"AI 编程助手 + 云基础设施"的典型组合,此前用 Terraform 或 kubectl 手写配置的流程,现在变成技能包交给 Claude Code 执行。对需要在 CoreWeave 上快速起 GPU 推理环境的开发者来说,部署门槛明显降低。
Introducing CoreWeave Skills in public preview.
Claude Code can build a CoreWeave Kubernetes Service (CKS) cluster, add a GPU Node Pool, serve a model with vLLM, and check that the GPUs are actually busy.
Install once from CoreWeave's official GitHub repo: https://t.co/xREEB5Lqij
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include CoreWeave, Claude Code, vLLM, Kubernetes.
Source attribution: curated from CoreWeave (@CoreWeave).