# runpod

> runpod — andrewharp-runpod. Use this tool when you need to manage and utilize cloud-based GPU instances for compute-intensive tasks, such as machine learning and data processing. It solves problems related to resource allocation, scalability, and remote access by providing a simple interface to create, start, stop, and connect to pods via SSH and API. Ideal for use cases requiring on-demand GPU computing, data science, and AI model training.

Canonical page: https://skillsregistry.net/skills/andrewharp-runpod  
JSON: https://api.skillsregistry.net/v1/skills/andrewharp-runpod

## Description

Manage RunPod GPU cloud instances - create, start, stop, connect to pods via SSH and API.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/andrewharp-runpod)

## 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": "andrewharp-runpod"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/andrewharp-runpod` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/andrewharp-runpod/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