# Cloud GPU with RunPod (/runpod)

/runpod is a Claude Code skill in the Video & Motion section. It is maintained by digitalsamba and published under the MIT license. Sets up RunPod serverless endpoints, deploys the toolkit's five Docker images, manages GPU resources and troubleshoots endpoint issues.

- Web version: https://skills.sgomez.dev/en/s/runpod
- Section: [Video & Motion](https://skills.sgomez.dev/en/video.md)
- Author: digitalsamba
- License: MIT
- Source: https://github.com/digitalsamba/claude-code-video-toolkit/tree/225c80a1c3a57c82d319ea6c73e0eff513787ae8/.claude/skills/runpod
- Updated 10 Sept 2026

## How to ask for it

- `Set up a RunPod endpoint to deploy my Docker image on GPU`
- `My RunPod endpoint is failing, help me troubleshoot it`
- `Explain how much running realesrgan on RunPod serverless will cost`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```


## Author's description

Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU resources, troubleshooting endpoint issues, or understanding costs. Covers all 5 toolkit images (qwen-edit, realesrgan, propainter, sadtalker, qwen3-tts).

- [How we review this](https://skills.sgomez.dev/en/methodology.md)