# Tao setup nvidia GPU host

> Tao setup nvidia GPU host is an open-source agent skill for developer tools. Host setup for TAO GPU backends. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/NVIDIA/skills/tree/main/skills/tao-setup-nvidia-gpu-host
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** tao-setup-nvidia-gpu-host
- **Collection:** https://github.com/NVIDIA/skills
- **Categories:** developer tools
- **Listing updated:** 2026-11-17

## About

Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit versions for Docker/local-Docker and Kubernetes GPU worker hosts. TAO-wide defaults can be overridden by the selected model's runtime profile. The `--check-only` path works on any Linux distribution; `--install` automates debian-family (Ubuntu/Debian/Pop!_OS/Mint/Zorin/Raspbian), rhel-family (Fedora/RHEL/Rocky/AlmaLinux), and suse-family (openSUSE/SLES) hosts, and prints actionable manual-install steps for everything else. Use when the user asks to "set up an NVIDIA GPU host", "check TAO Docker GPU runtime", or prepare a Kubernetes GPU worker for TAO.

## When your agent uses it

> Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit versions for Docker/local-Docker and Kubernetes GPU worker hosts. TAO-wide defaults can be overridden by the selected model's runtime profile. The `--check-only` path works on any Linux distribution; `--install` automates debian-family (Ubuntu/Debian/Pop!_OS/Mint/Zorin/Raspbian), rhel-family (Fedora/RHEL/Rocky/AlmaLinux), and suse-family (openSUSE/SLES) hosts, and prints actionable manual-install steps for everything else. Use when the user asks to "set up an NVIDIA GPU host", "check TAO Docker GPU runtime", or prepare a Kubernetes GPU worker for TAO.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs shell scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-setup-nvidia-gpu-host)
- [Asks for: Read, Bash](https://github.com/NVIDIA/skills/blob/HEAD/skills/tao-setup-nvidia-gpu-host/SKILL.md)
- [Network calls found in its scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-setup-nvidia-gpu-host)
- [License: Apache-2.0](https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-setup-nvidia-gpu-host)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/tao-setup-nvidia-gpu-host` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/tao-setup-nvidia-gpu-host &&
cp -R "$tmp/skills/tao-setup-nvidia-gpu-host" ~/.claude/skills/tao-setup-nvidia-gpu-host &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/tao-setup-nvidia-gpu-host` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/tao-setup-nvidia-gpu-host` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/tao-setup-nvidia-gpu-host &&
cp -R "$tmp/skills/tao-setup-nvidia-gpu-host" ~/.agents/skills/tao-setup-nvidia-gpu-host &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/tao-setup-nvidia-gpu-host` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/tao-setup-nvidia-gpu-host` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/tao-setup-nvidia-gpu-host &&
cp -R "$tmp/skills/tao-setup-nvidia-gpu-host" ~/.cursor/skills/tao-setup-nvidia-gpu-host &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/tao-setup-nvidia-gpu-host` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-setup-nvidia-gpu-host
```

Or copy the folder to `~/.gemini/skills/tao-setup-nvidia-gpu-host` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/tao-setup-nvidia-gpu-host`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/tao-setup-nvidia-gpu-host &&
cp -R "$tmp/skills/tao-setup-nvidia-gpu-host" ~/.copilot/skills/tao-setup-nvidia-gpu-host &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/tao-setup-nvidia-gpu-host` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/NVIDIA/skills.git
```

Then copy `skills/skills/tao-setup-nvidia-gpu-host` into your agent's skills folder as `tao-setup-nvidia-gpu-host`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Tao setup nvidia GPU host in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/tao-setup-nvidia-gpu-host to use it in all your projects, or to .claude/skills/tao-setup-nvidia-gpu-host in one project.

### Does Tao setup nvidia GPU host run scripts?

Yes. It runs shell scripts. Its scripts contain network calls. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Tao setup nvidia GPU host?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Tao setup nvidia GPU host?

The closest alternatives to Tao setup nvidia GPU host are Rea changelog update, Code review, Gem devops guidelines, PR screenshots and Make repo contribution.

## Alternatives

- [Rea changelog update](https://ai-powered.com/skills/rea-changelog-update): Rea changelog update is an open-source agent skill for developer tools.
- [Code review](https://ai-powered.com/skills/code-review-mattpocock): Code review is an open-source agent skill for developer tools.
- [Gem devops guidelines](https://ai-powered.com/skills/gem-devops-guidelines): Gem devops guidelines is an open-source agent skill for cloud and infrastructure.
- [PR screenshots](https://ai-powered.com/skills/pr-screenshots): PR screenshots is an open-source agent skill for developer tools.
- [Make repo contribution](https://ai-powered.com/skills/make-repo-contribution): Make repo contribution is an open-source agent skill for developer tools.
- [Create github issues for unmet specification requirements](https://ai-powered.com/skills/create-github-issues-for-unmet-specification-requirements): Create github issues for unmet specification requirements is an open-source agent skill for developer tools.
- [Github actions hardening](https://ai-powered.com/skills/github-actions-hardening): Github actions hardening is an open-source agent skill for developer tools.
- [Github codespaces efficiency](https://ai-powered.com/skills/github-codespaces-efficiency): Github codespaces efficiency is an open-source agent skill for developer tools.

---
Source: https://ai-powered.com/skills/tao-setup-nvidia-gpu-host
