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-deploy-plangit 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-deploy-plan)<a href="https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-deploy-plan"><img src="https://agentmods.dev/badge/skills/intel/gpu-ai-skills/xpu-deploy-plan.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00149 | $0.01953 |
| Opus 5 | $0.00075 | $0.00977 |
| Sonnet 5 | $0.00030 | $0.00391 |
| Haiku 4.5 | $0.00015 | $0.00195 |
Grade A, and why
xpu-deploy-plan 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xpu-deploy-plan
End-to-end deployment planner for Intel XPU inference. This skill is
an orchestrator only: it chains the lower-level skills, captures their
outputs, and writes a single PLAN.md for the user. It does not
duplicate runtime guidance that lives in the called skills.
Default target: Arc Pro B70 (32 GiB) home-lab host, container-first, OpenAI-compatible HTTP serving through vLLM-XPU, unless the user's request points elsewhere.
Before invoking the plan builder, summarize the resolved inputs back to
the user (model, runtime, target XPU, ctx, concurrency, quant) so they
can correct anything before files are written. This is courtesy, not a
safety gate — the script is read/compute only and writes a markdown
plan to .out/skills/xpu-deploy-plan/; it does not pull images, launch
containers, claim a GPU, or modify the system.
When to use
Use when the user asks for a plan — wants the orchestration, not just to start a server:
- "Give me a deployment plan for Qwen2.5-7B on my Arc Pro B70 with vLLM."
- "Plan an end-to-end deployment of Llama-3.1-8B on my Intel GPU."
- "Which skills should I run, and in what order, to serve this model?"
- "I have two/four B70s; give me a launch plan."
Required entry point
Always invoke scripts/build_plan.sh. It is the single supported
entry point for this skill. Do not run the chained skills
(xpu-runtime-preflight, model-can-it-fit, model-config-recommend,
or the runtime launch emitters) by hand and assemble a plan yourself —
build_plan.sh already orchestrates them, captures their outputs, and
writes the canonical PLAN.md. Hand-rolled equivalents drift from the
artifact layout the rest of the toolchain expects and miss the halt
logic on a preflight FAIL.
If build_plan.sh fails or a chained skill returns a hard error,
report the failure and the routing skill from the preflight
SUMMARY.md; do not work around it by running the underlying scripts
directly.
Quick start
plugins/intel-gpu-ai-skills/skills/xpu-deploy-plan/scripts/build_plan.sh \
--model Qwen/Qwen2.5-7B-Instruct \
--runtime vllm \
--target-gpu 0 \
--ctx 4096 \
--concurrency 1 \
--out-dir .out/skills/xpu-deploy-plan
What ships with it
1 file 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.
- 8d ago First seen · 167 lines · 149 tokens per session scan A 446499f797ad
xpu-deploy-plan is a skill published in the GitHub repository intel/gpu-ai-skills (21 stars, last pushed 3d ago), licensed Apache-2.0. It adds 149 tokens to every session and 1,953 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…