# tpu-devops

> tpu-devops — xbill9-tpu-skill-claude. Use this tool when you need to manage Google Cloud TPU capacity and serve large language models like Gemma 4 with vLLM. It solves problems related to provisioning, debugging, and benchmarking of TPU resources, streamlining the development and deployment process. The tool accepts inputs for TPU configuration and model serving, and outputs include provisioned resources, debugging logs, and benchmarking results.

Canonical page: https://skillsregistry.net/skills/xbill9-tpu-skill-claude  
JSON: https://api.skillsregistry.net/v1/skills/xbill9-tpu-skill-claude

## Description

MCP server for managing Google Cloud TPU capacity and serving Gemma 4 with vLLM, including provisioning, debugging, benchmarking, and teardown.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/zljwfqzj4b)
- **Repository:** <https://github.com/xbill9/tpu-skill-claude>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "xbill9-tpu-skill-claude"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/xbill9-tpu-skill-claude` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/xbill9-tpu-skill-claude/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt