init-gpu-server — Claude Code skill: setup and installation
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.
GPL-3.0 ★ 171 updated 2026-11-17
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a claude-codeWhat init-gpu-server 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.
What it helps with
- 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 for the agent
- 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
lsblkand configure/mnt/modelsand/mnt/loraModels.
How to install init-gpu-server
1Skills CLI (Vercel)
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a claude-code2Manually: put the files in place
~/.claude/skills/init-gpu-server/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/init-gpu-server/
1Skills CLI (Vercel)
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a codex2Manually: put the files in place
.agents/skills/init-gpu-server/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a cursor2Manually: put the files in place
.cursor/skills/init-gpu-server/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install drawthingsai/local-code-community .agents/skills/init-gpu-server2Manually: put the files in place
.github/skills/init-gpu-server/SKILL.md1Skills CLI (Vercel)
npx skills add drawthingsai/local-code-community --skill init-gpu-server -a gemini-cli2Platform CLI
gemini skills install https://github.com/drawthingsai/local-code-community --path .agents/skills/init-gpu-serverManually: put the files in place
.devin/skills/init-gpu-server/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about init-gpu-server
How do I install init-gpu-server in Claude Code?
Run npx skills add drawthingsai/local-code-community --skill init-gpu-server -a claude-code. The skill file is placed at ~/.claude/skills/init-gpu-server/SKILL.md.
What does init-gpu-server do?
It configures a Draw Things server, installs GPU software, mounts model disks, and checks GPU access from Docker.
What does init-gpu-server need to run?
It needs SSH access as root@HOST and the files in Scripts/ServerManagement/GPUScript. Partitioning and formatting blank disks requires explicit approval because it destroys their data.