# init-gpu-server

init-gpu-server is a Claude Code skill that prepares a Draw Things GPU server by syncing GPUScript, installing server software, and mounting data disks.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 171 repo stars
- Author: drawthingsai
- License: GPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/drawthingsai/local-code-community/tree/HEAD/.agents/skills/init-gpu-server/SKILL.md
- Updated: 2026-11-17
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/init-gpu-server

## What it does

The skill sets up a new Draw Things server reachable over SSH as `root@HOST`. It syncs scripts to `/root/utils`, installs Docker, CUDA Toolkit, NVIDIA Container Toolkit, and mergerfs, then configures a Python environment and the Draw Things image. A separate helper checks whether Docker can access the GPUs.

Data disks mount at `/mnt/models` and `/mnt/loraModels`; the combined model path is `/mnt/official-models`. Partitioning and formatting two empty disks requires explicit approval because it destroys their data. Device names are inspected with `lsblk` rather than assumed.

SSH access as `root` and the scripts in `Scripts/ServerManagement/GPUScript` are needed. Setup also changes network settings and creates `/opt/draw-things-venv` with `tqdm`, `schedule`, and `boto3`.

## Requirements
- Works with: Docker

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/init-gpu-server/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/init-gpu-server/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/init-gpu-server/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/init-gpu-server/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install drawthingsai/local-code-community .agents/skills/init-gpu-server
```

2. **Manually: put the files in place**
- File: `.github/skills/init-gpu-server/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/drawthingsai/local-code-community --path .agents/skills/init-gpu-server
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/init-gpu-server/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/drawthingsai/local-code-community/tree/HEAD/.agents/skills/init-gpu-server/SKILL.md

## When to use it
- prepare a new server for Draw Things GPU workloads
- install Docker, CUDA, and NVIDIA Container Toolkit
- mount model disks and combine their paths
- check Docker access to the GPUs

## Example prompts
- Set up a new Draw Things GPU server over SSH as `root@HOST`.
- Install the server software and sync scripts from `Scripts/ServerManagement/GPUScript`.
- Inspect disks with `lsblk` and configure `/mnt/models` and `/mnt/loraModels`.

## Similar
- [tao-setup-nvidia-gpu-host](https://affpapa.org/en/nevibecode/skills/tao-setup-nvidia-gpu-host.md) — skill · 1700 installs
- [pod-doctor](https://affpapa.org/en/nevibecode/skills/pod-doctor.md) — skill · 3700 installs
- [cuopt-install](https://affpapa.org/en/nevibecode/skills/cuopt-install.md) — skill · 2600 installs
- [serverless-modal](https://affpapa.org/en/nevibecode/skills/serverless-modal.md) — skill · 515 installs
- [mojo-gpu-fundamentals](https://affpapa.org/en/nevibecode/skills/mojo-gpu-fundamentals.md) — skill · 2800 installs
- [optimize-for-gpu](https://affpapa.org/en/nevibecode/skills/optimize-for-gpu.md) — skill · 2200 installs

From the same set: [drawthingsai/local-code-community](https://affpapa.org/en/nevibecode/by/drawthingsai/local-code-community.md) — 20 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
