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 skills add intel/gpu-ai-skills --skill xpu-discovergit 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-discover)<a href="https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-discover"><img src="https://agentmods.dev/badge/skills/intel/gpu-ai-skills/xpu-discover.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 168 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- high Privilege Escalation · line 169 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 5.1 | $0.00048 | $0.02227 |
| Opus 5 | $0.00024 | $0.01113 |
| Sonnet 5 | $0.00010 | $0.00445 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
xpu-discover scanned grade A with 0 findings 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xpu-discover
xpu-smi is Intel's nvidia-smi. Sees only Intel GPUs (Arc, Arc
Pro, Battlemage, Flex, Max).
Quickstart
Run in order. If step 1 is empty, stop.
xpu-smi discovery # 1. inventory
xpu-smi diag --precheck # 2. driver/firmware health
xpu-smi ps # 3. processes using each GPU
xpu-smi diag -d 0 -l 1 # 4. quick functional test
xpu-smi stats -d 0 # 5. utilisation snapshot
xpu-smi dump -d 0 -m 0,5,18 -i 1 # 6. live CSV stream (Ctrl-C)
All commands accept -j for JSON output (use when parsing).
CUDA -> Intel cheat sheet
| CUDA | Intel |
|---|---|
nvidia-smi |
xpu-smi discovery |
nvidia-smi -L |
xpu-smi discovery -j |
nvidia-smi pmon -c 1 |
xpu-smi ps |
nvidia-smi dmon |
xpu-smi dump -d <id> -m 0,5,18 -i 1 |
nvidia-smi --query-gpu=... |
xpu-smi stats -d <id> -j |
nvidia-smi topo -m |
xpu-smi topology -m |
CUDA_VISIBLE_DEVICES=0 |
ZE_AFFINITY_MASK=0 |
cuda-memcheck |
xpu-smi diag -d 0 -l 1 |
CUDA refugee footgun: CUDA_VISIBLE_DEVICES=99 silently hides
all GPUs; ZE_AFFINITY_MASK=99 crashes the Level Zero loader
with an assertion. Always check xpu-smi discovery for valid IDs
(start at 0) before setting the mask.
What each subcommand returns
discovery — inventory
One stanza per Intel GPU. Key fields:
-
Device ID — small integer, used as
-dand asZE_AFFINITY_MASKvalue. -
PCI BDF Address — stable across reboots (e.g.
0000:36:00.0). -
DRM Device —
/dev/dri/card0, used in--devicefor Docker. -
Device Name — Battlemage shows
Intel(R) Graphics [0xe2XX]rather than the marketing name; driver quirk, not a problem. Map the PCI device ID in brackets to the product SKU:PCI device ID Product SKU Confirmed 0xe20bArc B580 yes (lspci on hardware) 0xe211Arc Pro B60 yes (pci.ids) 0xe220Arc Pro B50 yes (pci.ids) 0xe221Arc Pro B65 yes (pci.ids) 0xe223Arc Pro B70 yes (lspci on hardware)
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.
- 8d ago First seen · 185 lines · 48 tokens per session scan A 96b4e19f7ed7
xpu-discover is a skill published in the GitHub repository intel/gpu-ai-skills (21 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,227 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.