ai-inference-deploy SKILL.md skillA
ai-inference-deploy from intel/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add intel/skills/ai-inference-deploy@git:20261101.933b9e9Pins git:20261101.933b9e9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- intel/skills
- Path
skills/ai-inference-deploy/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261101.933b9e9, committed Nov 1, 2026
- Size
- 9,097 bytes
- Repository stars
- 29
- License
- Apache-2.0
Top-level router for an Intel GPU inference request that has not settled what it wants yet. Use for the bare ask — "deploy qwen", "serve a model on my Arc", "get llama running on my Intel graphics card", "which one do I use, vllm or sglang?", "what do I need to run this model on my GPU?" — where the runtime, the host OS, the install path and the readiness of the machine are all still open. It picks the runtime for a user who has no basis to pick one, translates the catalog's "xpu" skill names…
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
# ai-inference-deploy The entry point for "deploy a model on an Intel GPU" before anyone has said which runtime, which host, or which install path. It turns that request into a resolved set of inputs and the name of the skill that owns the next step. This skill **routes only**. It states no image tag, no serve flag and no environment variable, because those live in the runtime skills and change there. If you find yourself writing a launch command while in this skill, you have gone one stage too far — stop and hand off. ## Say "GPU", not "XPU" Nearly every skill this router hands off to has `xpu` in its name. **XPU is Intel's name for the GPU as a compute device** — the same Intel GPU the user is asking about, discrete card or laptop graphics. It is not a separate product, a separate device, or something they need to go and buy. Users do not type "XPU". They type GPU, graphics card, Arc, or the name on the box or laptop, and a request phrased that way is this catalog's request. So: - Recognise "XPU" when a user does say it, but **write "GPU"** back to them. - When handing off, say what the skill does before its name — "the skill that serves models …
Read the whole file at its exact version.
How to install
mdr add intel/skills/ai-inference-deploy@sha256:cacf20d5977b98f2The line at the top of this page pins the label git:20261101.933b9e9, 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.
[](https://markdownregistry.com/a/art_cn3py5icron4ffer)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Nov 1, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9097 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
intel/skills · 29 stars · license Apache-2.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cn3py5icron4ffer GET https://markdownregistry.com/api/v1/resolve?ref=intel/skills/ai-inference-deploy GET https://markdownregistry.com/api/v1/blob/cacf20d5977b98f23c55becc9db1eaaffa2dd12e2969b979208e1d4fd2bab647
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.