xpu-discover SKILL.md skillA

xpu-discover from intel/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add intel/skills/xpu-discover@git:20260930.9cbbd40

Pins git:20260930.9cbbd40 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
intel/skills
Path
skills/xpu-discover/SKILL.md
Versions recorded
2
Latest version
git:20260930.9cbbd40, committed Sep 30, 2026
First version recorded
Sep 3, 2026
Size
9,441 bytes
Repository stars
29
License
Apache-2.0

Inventory Intel GPUs (Arc, Arc Pro) on a Linux host. Detect devices, collect driver, firmware and component-health evidence, list processes using each XPU, and read live utilisation.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# xpu-discover

`xpu-smi` is Intel's `nvidia-smi`. Sees only Intel GPUs (Arc, Arc
Pro, Battlemage, Flex, Max).

## Quickstart

Subcommands and flags differ between builds; `xpu-smi -h` lists what the
installed one supports (prefer `-h`: some builds reject `help`). Report an
absent subcommand rather than retrying it.

Run in order. If step 1 fails or has no devices, stop.

```sh
xpu-smi discovery                 # 1. inventory
xpu-smi health -l                 # 2. component health (power, frequency, temp)
journalctl -k --no-pager | grep -iE 'guc|huc|iommu|drm|\bxe\b|i915|level.?zero'
                                  # 3. driver/firmware log evidence
xpu-smi ps                        # 4. processes using each GPU
xpu-smi stats -d 0                # 5. utilisation snapshot
xpu-smi dump --device 0 --metrics MEMORY,POWER --interval 1
                                  # 6. live CSV stream (Ctrl-C)
```

The `xpu-smi` commands accept `-j` for JSON output (use when parsing).

Steps 2 and 3 are both needed: `health` covers power and thermals, the kernel
log covers driver and firmware. Neither certifies health, and a command that
runs is not a GPU that works.

## CUDA -> Intel cheat sheet
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add intel/skills/xpu-discover@sha256:1565519a9e9a0ea7

The line at the top of this page pins the label git:20260930.9cbbd40, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xkrxcvwdosqcsipg.svg)](https://markdownregistry.com/a/art_xkrxcvwdosqcsipg)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 3, 2026 and Sep 30, 2026, about one every 28 days.

versioncommittedcommitsizeaudit
git:20260930.9cbbd40 latest2026-09-30 9cbbd40 9,441 BA view · diff
git:20260903.b1ad0342026-09-03 b1ad034 7,278 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9441 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

intel/skills · 29 stars · license Apache-2.0 · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xkrxcvwdosqcsipg
GET https://markdownregistry.com/api/v1/resolve?ref=intel/skills/xpu-discover
GET https://markdownregistry.com/api/v1/blob/1565519a9e9a0ea73f63655c9528f62ccf4f82b276c949950b8e4025f12e12eb

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from intel/skills

ai-inference-deploy SKILL.md skill
intel/skills · skills/ai-inference-deploy/SKILL.md · Top-level router for an Intel GPU inference request that has not settled what it wants yet. Use for the bare ask —…
git:20261101.933b9e9 · audit A · 29 stars
cuda-to-xpu-migration SKILL.md skill
intel/skills · skills/cuda-to-xpu-migration/SKILL.md · Create a CUDA-to-XPU migration assessment for an existing AI repo. Identify CUDA-specific assumptions, route to the…
git:20260903.b1ad034 · audit A · 29 stars
dpnp-interop SKILL.md skill
intel/skills · skills/dpnp-interop/SKILL.md · Passing dpnp arrays to and from other Python libraries on Intel CPUs and GPUs. Use when dpnp numeric work has to feed…
v1.0 · audit A · 29 stars
dpnp-io SKILL.md skill
intel/skills · skills/dpnp-io/SKILL.md · Reading and writing files from dpnp code on Intel CPUs and GPUs. Use when the user needs to load an array into dpnp or…
v1.0 · audit A · 29 stars
dpnp-linalg-fft SKILL.md skill
intel/skills · skills/dpnp-linalg-fft/SKILL.md · Linear algebra and FFT with dpnp on Intel CPUs and GPUs, backed by oneMKL. Use when a matrix multiply, solve…
v1.0 · audit A · 29 stars
dpnp-memory SKILL.md skill
intel/skills · skills/dpnp-memory/SKILL.md · Device memory management for dpnp arrays on Intel CPUs and GPUs. Use when a dpnp script grows in memory until it fails…
v1.0 · audit A · 29 stars
dpnp-migration SKILL.md skill
intel/skills · skills/dpnp-migration/SKILL.md · Porting an existing NumPy or CuPy program to dpnp on Intel CPUs and GPUs. Use when deciding whether a codebase can run…
v1.0 · audit A · 29 stars
dpnp-quickstart SKILL.md skill
intel/skills · skills/dpnp-quickstart/SKILL.md · NumPy-compatible array operations optimized for Intel hardware. Use when the user wants to migrate or port NumPy code…
v1.0 · audit A · 29 stars
dpnp-random SKILL.md skill
intel/skills · skills/dpnp-random/SKILL.md · Random number generation with dpnp on Intel CPUs and GPUs, backed by oneMKL. Use when NumPy random calls move to dpnp…
v1.0 · audit A · 29 stars
dpnp-troubleshooting SKILL.md skill
intel/skills · skills/dpnp-troubleshooting/SKILL.md · Diagnosing dpnp failures on Intel CPUs and GPUs. Use when dpnp raises NotImplementedError or an unexpected TypeError…
v1.0 · audit A · 29 stars
linux-perf SKILL.md skill
intel/skills · skills/linux-perf/SKILL.md · Profile and fix Linux performance problems using `perf`. Workflows: (A) hardware counters -- IPC, cache-miss, branch…
git:20260903.b1ad034 · audit A · 29 stars
llamacpp-xpu-run SKILL.md skill
intel/skills · skills/llamacpp-xpu-run/SKILL.md · Run a GGUF model on an Intel GPU using llama.cpp's SYCL backend (Level Zero) with the official intel.Dockerfile. Covers…
git:20260903.b1ad034 · audit A · 29 stars

Every file in intel/skills

Browse by kind, by grade A, or by owner.