A collection of AMD agent skills for running AI on Ryzen AI processors and Instinct GPUs, serving language models, and examining GPU and PyTorch performance data.

Use it for local image and audio AI, language-model serving with vLLM, inference optimization, and GPU-kernel or PyTorch trace analysis.

It helps developers use AMD hardware for local AI, host language models, and find performance bottlenecks in AI workloads.

amd-skills — Plugin for Claude Code by amd

Install

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.

Clone the repo

git clone --depth 1 https://github.com/amd/skills

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/amd/skills/amd-skills.svg)](https://agentmods.dev/plugins/amd/skills/amd-skills)

Your own site

<a href="https://agentmods.dev/plugins/amd/skills/amd-skills"><img src="https://agentmods.dev/badge/plugins/amd/skills/amd-skills.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 5 skills cost 877 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

amd-skills 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 4d 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.

.claude-plugin/marketplace.json#amd-skills · 14 lines

What it actually says

{
  "name": "amd-skills",
  "source": "./",
  "version": "0.2.0",
  "strict": false,
  "skills": [
    "./skills/local-ai-use",
    "./skills/local-ai-app-integration",
    "./skills/serving-llms-on-instinct",
    "./skills/tracelens-analysis-orchestrator",
    "./skills/hyperloom-workload-optimizer"
  ],
  "description": "AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance."
}

Contents

What it installs

The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 877 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#amd-skills 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.

marketplace.json 809 B

Changes

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.

4d ago First seen · 14 lines scan A 6dbe073a6887

Subscribe to this mod's changes

amd-skills is a plugin published in the GitHub repository amd/skills (335 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

Data and AI Hardware and IoT

dgx-spark-ops

NVIDIA DGX Spark (GB10 Grace Blackwell) environment operations: aarch64/CUDA-13 stack setup, training gotcha preflights, and unified-memory/thermal management for local ML workloads.

wshobson/agents · not measured

nvidia-skills

Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows.

NVIDIA/skills · not measured

coreai-skills

Skills for authoring, exporting, compiling, and running PyTorch models on Apple silicon via Core AI.

apple/coreai-models · not measured

intel-gpu-ai-skills

Agent Skills for running, benchmarking, profiling, and fixing arbitrary Hugging Face safetensors models on Intel GPUs. Container-first, upstream-only, Battlemage / Arc / Arc Pro / Data Center GPU Max.

intel/gpu-ai-skills · not measured

awesome-ascend-skills marketplace

A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed AI Agent Skills. Includes npu-smi device management, HCCL performance testing, and ATC model conversion.

ascend-ai-coding/awesome-ascend-skills · not measured

atc-model-converter

Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full.