Intel GPU AI Skills is a collection of agent skills for setting up, running, benchmarking, and profiling Hugging Face models on Intel GPUs. It supports workflows involving PyTorch, vLLM-XPU, SGLang-XPU, llama.cpp-SYCL, and migration from CUDA to XPU. The catalogue contains the project's skills, instructions, agent, and plugin.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/intel/gpu-ai-skills/xpu-system-setupnpx skills add intel/gpu-ai-skills --skill xpu-system-setupgit clone --depth 1 https://github.com/intel/gpu-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-system-setup)<a href="https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-system-setup"><img src="https://agentmods.dev/badge/skills/intel/gpu-ai-skills/xpu-system-setup.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00160 | $0.03076 |
| Opus 5 | $0.00080 | $0.01538 |
| Sonnet 5 | $0.00032 | $0.00615 |
| Haiku 4.5 | $0.00016 | $0.00308 |
Grade B, and why
xpu-system-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo sed -i 's/\bnomodeset\b//g' /etc/default/grub How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xpu-system-setup
First-time system setup for Intel GPU/XPU workloads on a bare OS install. Detects what's already configured and only installs what's missing.
This is a standalone skill — it has no dependencies on other skills and can be run independently.
When To Use
Run this on a fresh machine to prepare it for Intel GPU/XPU workloads.
Typical scenarios:
- New bare-metal or VM with Intel GPUs that hasn't been configured for compute workloads yet — the standard customer-onboarding entry point.
- System is missing packages, user groups, or Docker needed for GPU work.
xpu-smi discoveryshows "No device discovered" orclinforeports 0 platforms after a fresh install — common on Arc Pro B60/B70 (Battlemage) with Ubuntu 24.04 stock kernel. Runcheck_battlemage_prerequisites.shto diagnose and fix the underlying kernel/runtime issues, then re-run this skill.
The script is idempotent: it detects what's already installed and only acts on what's missing, so re-running it on a configured host is safe and finishes quickly.
How to Invoke
Always invoke this skill by running the script. Do not run apt install,
add-apt-repository, or usermod directly — even if the dry-run reports
exactly which package is missing. Confirm with the user before running —
the script installs system packages and modifies group membership.
The script:
- Detects what's installed (idempotent — safe to re-run)
- Installs only what's missing (with prompts unless
--auto) - Runs the post-setup verification gate (6 checks)
The raw commands shown in the table below are what the script runs internally — they are descriptive, not a manual checklist. Step 3 only runs when you go through the script. Manual installs leave the verification step skipped, which can hide problems (e.g., a package installed but the driver not loadable, or render group not effective).
If only one component is missing, use --only:
plugins/intel-gpu-ai-skills/skills/xpu-system-setup/scripts/setup_xpu_system.sh --only xpu-smi --auto
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 280 lines · 160 tokens per session scan B 90ce000cec37
xpu-system-setup is a skill published in the GitHub repository intel/gpu-ai-skills (21 stars, last pushed today), licensed Apache-2.0. It adds 160 tokens to every session and 3,076 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
holoscan-install-container
Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.
doca-urom-svc
Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using doca-urom: pull the NGC image, choose the UCX component, size queues, configure Comch pairing, and align host and service versions. SECURITY: the service has no…
hsb-setup
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.
holoscan-install-source
Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.
dakota-image
OCI layer assembly, boot testing, installer boundaries, VM work, and local OTA verification for Dakota images.
together-kueue
Install and use the Kueue job-queueing controller on a Together AI Kubernetes GPU cluster to gate jobs on quota. Covers installing Kueue, defining ResourceFlavor, ClusterQueue, and LocalQueue quota, submitting jobs to a queue, and watching quota admit or suspend them. Reach for it when a Together cluster's GPU pool…