amd-skills
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/amd/skills with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/amd/skills'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/amd--skills)HTML
<a href="/listings/amd--skills"><img src="/api/listings/amd--skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Install AMD Skills with the [`skills` CLI](https://github.com/vercel-labs/skills) via `npx`. No clone or manual copying required.
npx skills add amd/skills
This prompts you to pick a skill and an install destination. To install a specific skill into specific agents, pass `--skill` with one or more `--agent` flags (e.g. `cursor`, `claude-code`, `codex`):
npx skills add amd/skills --skill local-ai-use --agent claude-code
Browse everything available before installing:
npx skills add amd/skills --list
`npx` requires [Node.js](https://nodejs.org). Prefer to do it by hand? See [Manual installation](#manual-installation).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 26 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "amd-skills",
- "owner": {
- "name": "AMD"
- },
- "metadata": {
- "description": "Agent Skills for AMD-optimized workflows.",
- "version": "0.3.0"
- },
- "plugins": [
- {
- "name": "amd-skills",
- "source": "./",
- "version": "0.3.0",
- "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."
- }
- ]
- }
README.md · README · 200 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # AMD Skills
- <div align="center">
- 
- 
- 
- 
- [](https://cursor.com)
- [](https://www.anthropic.com/claude-code)
- [](https://openai.com/codex/)
- [](https://ai.google.dev/gemini-api/docs)
- [](LICENSE)
- <img src="assets/banner.gif" alt="AMD Skills"/>
- [**Browse the Skill Catalog ->**](#the-catalog)
- </div>
- AMD Skills provide agents with knowledge, scripts, and conventions for working with AMD hardware and software.
- Skills in this repository follow the standardized [Agent Skills](https://github.com/anthropics/skills) format and are designed to interoperate with the major coding agents like Cursor, Claude Code, OpenAI Codex, and Gemini CLI.
- > [!IMPORTANT]
- > This catalog is being built in the open and will evolve frequently as skills, categories, and descriptions take shape. Some skills may be in Tech Preview; see the underlying product for status.
- ## Installation
- Install AMD Skills with the [`skills` CLI](https://github.com/vercel-labs/skills) via `npx`. No clone or manual copying required.
- ```bash
- npx skills add amd/skills
- ```
- This prompts you to pick a skill and an install destination. To install a specific skill into specific agents, pass `--skill` with one or more `--agent` flags (e.g. `cursor`, `claude-code`, `codex`):
- ```bash
- npx skills add amd/skills --skill local-ai-use --agent claude-code
- ```
- Browse everything available before installing:
- ```bash
- npx skills add amd/skills --list
- ```
- `npx` requires [Node.js](https://nodejs.org). Prefer to do it by hand? See [Manual installation](#manual-installation).
- ## Using a skill
- Once a skill is installed, reference it in plain language while talking to your agent. For example:
- - "Use AMD Skills to learn how to generate images locally instead of burning cloud tokens."
- - "Use AMD Skills to deploy this LLM for inference on my AMD Instinct GPUs."
- In most cases the agent picks the right skill on its own from the description; explicit invocation is a fallback, not a requirement.
- For hands-on, step-by-step guides that show a skill in action, see the [walkthroughs](walkthroughs/README.md).
- ## The catalog
- The initial catalog is organized into three focus areas, spanning the full stack from client to cloud. This catalog is expected to grow significantly as more skills land.
- ### Client-native
- Run and optimize on Ryzen AI.
- | Skill | What it does | Source |
- | --- | --- | --- |
- | [`local-ai-use`](https://github.com/amd/skills/blob/main/skills/local-ai-use/SKILL.md) | Route image generation, text-to-speech, and speech-to-text through a local AI server to reduce token cost. | [Lemonade](https://github.com/lemonade-sdk/skills) |
- | [`local-ai-app-integration`](https://github.com/amd/skills/blob/main/skills/local-ai-app-integration/SKILL.md) | Integrate local AI into cloud LLM apps for offline support, better privacy, and lower API costs. | [Lemonade](https://github.com/lemonade-sdk/skills) |
- ### Cross-stack
- Cross-stack skills, from client to cloud.
- | Skill | What it does | Source |
- | --- | --- | --- |
- | [`rocm-doctor`](https://github.com/amd/skills/blob/main/skills/rocm-doctor/SKILL.md) | Diagnose and fix common ROCm, HIP, PyTorch, and llama.cpp failures and misconfigurations on AMD GPUs. | [rocm-cli](https://github.com/ROCm/rocm-cli) |
- | [`moat-cuda-to-rocm`](https://github.com/amd/skills/blob/main/skills/moat-cuda-to-rocm/SKILL.md) | Add a ROCm/HIP backend to a CUDA project so it runs on AMD GPUs while the CUDA build keeps working side by side. | [moat](https://github.com/AMD-Ecosystem/moat) |
- | [`lemonade-router-builder`](https://github.com/amd/skills/blob/main/skills/lemonade-router-builder/SKILL.md) | Set up a Lemonade model router that handles requests based on content, sensitivity, or required capabilities. | [Lemonade](https://github.com/lemonade-sdk/skills) |
- | [`quark-install`](https://github.com/amd/skills/blob/main/skills/quark-install/SKILL.md) | Install or verify AMD Quark with an accelerator-matched PyTorch, from PyPI, a native-wheel index, a local wheel, or source, then verify imports, kernels, and `quark-cli`. | [Quark](https://github.com/amd/Quark) |
- | [`quark-torch-llm-ptq`](https://github.com/amd/skills/blob/main/skills/quark-torch-llm-ptq/SKILL.md) | Quantize PyTorch / Hugging Face LLMs with AMD Quark post-training quantization: inspect the model, pick a scheme (FP8, INT4, and more), and produce a verified quantized model. | [Quark](https://github.com/amd/Quark) |
- ### Server-native
- Run and optimize on AMD Instinct.
- | Skill | What it does | Source |
- | --- | --- | --- |
- | [`serving-llms-on-instinct`](https://github.com/amd/skills/blob/main/skills/serving-llms-on-instinct/SKILL.md) | Deploy LLM inference on AMD Instinct GPUs end-to-end: detect hardware (or onboard via AMD Developer Cloud), validate model fit, apply the right vLLM recipe, and launch a benchmarked endpoint. SGLang and engine or backend selection in later phases. | in-repo |
- | [`serving-llms-on-epyc`](https://github.com/amd/skills/blob/main/skills/serving-llms-on-epyc/SKILL.md) | Serve LLMs on AMD EPYC CPUs with vLLM and zentorch, in a container (Docker or Podman) or conda. Handles CPU detection, runtime and env validation, vLLM model-support and RAM-fit checks, hardware-sized threads and KV, launch, and health verification. Single instance; reports and stops on failure. | [ZenDNN-pytorch-plugin](https://github.com/amd/ZenDNN-pytorch-plugin) |
- | [`hyperloom-workload-optimizer`](https://github.com/amd/skills/blob/main/skills/hyperloom-workload-optimizer/SKILL.md) | Set up Hyperloom and autonomously optimize end-to-end LLM inference throughput on AMD Instinct GPUs, reporting a validated gain. | [Hyperloom](https://github.com/AMD-AGI/Hyperloom) |
- | [`magpie-kernel-evaluator`](https://github.com/amd/skills/blob/main/skills/magpie-kernel-evaluator/SKILL.md) | Evaluate GPU kernel correctness and performance, compare kernel implementations, and benchmark vLLM or SGLang inference with profiling, TraceLens, and torch-trace gap analysis. | [Magpie](https://github.com/AMD-AGI/Magpie) |
- | [`tracelens-analysis-orchestrator`](https://github.com/amd/skills/blob/main/skills/tracelens-analysis-orchestrator/SKILL.md) | Orchestrate modular PyTorch profiler trace analysis with TraceLens: generate perf reports, run system-level and compute-kernel subagents in parallel, and write a prioritized stakeholder report. | [TraceLens](https://github.com/AMD-AGI/TraceLens) |
- | [`rocprofiler-pc-sampling`](https://github.com/amd/skills/blob/main/skills/rocprofiler-pc-sampling/SKILL.md) | Profile a GPU application with rocprofv3 program counter (PC) sampling, then analyze the samples to surface hotspots and stall reasons. | [rocprofiler-sdk](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-sdk) |
- | [`rocprofiler-systems-choosing-a-profiling-preset`](https://github.com/amd/skills/blob/main/skills/rocprofiler-systems-choosing-a-profiling-preset/SKILL.md) | Pick the right rocprofiler-systems profiling preset for a workload and goal (GPU kernels, MPI, OpenMP, AI/ML training, and more), and return a ready-to-run command. | [rocprofiler-systems](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-systems) |
- | [`rocprofiler-systems-discovering-profiling-options`](https://github.com/amd/skills/blob/main/skills/rocprofiler-systems-discovering-profiling-options/SKILL.md) | Discover rocprofiler-systems settings, hardware counters, ROCm API tracing domains, and GPU metrics, and how to configure them. | [rocprofiler-systems](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-systems) |
- | [`rocprofiler-systems-instrumenting-binaries`](https://github.com/amd/skills/blob/main/skills/rocprofiler-systems-instrumenting-binaries/SKILL.md) | Instrument programs and libraries with `rocprof-sys-instrument`: choose runtime instrumentation or binary rewrite, filter functions and modules, preview with a dry run, and debug missing or noisy trace entries. | [rocprofiler-systems](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-systems) |
- | [`flydsl-kernel-authoring`](https://github.com/amd/skills/blob/main/skills/flydsl-kernel-authoring/SKILL.md) | Write, review, and understand FlyDSL GPU kernels for AMD GPUs: layout algebra, tiled copy and MMA, LDS allocation, and autotuning. | [FlyDSL](https://github.com/ROCm/FlyDSL) |
- | [`flydsl-kernel-trace-analysis`](https://github.com/amd/skills/blob/main/skills/flydsl-kernel-trace-analysis/SKILL.md) | Collect rocprofv3 instruction-level traces and counters for a GPU kernel, map the top stall hotspots back to source lines, and produce an optimization plan. | [FlyDSL](https://github.com/ROCm/FlyDSL) |
- ## What is a skill?
- A skill is a self-contained folder that bundles everything an agent needs to perform a focused task: instructions, helper scripts, prompts, templates, and references. At its core is a `SKILL.md` file with YAML frontmatter, a `name`, and a short `description` that tells the agent *when* the skill should activate, followed by the guidance the agent reads while the skill is in use.
- ```
- skills/
- <skill-name>/
- SKILL.md
- skill-card.md
- scripts/ # optional
- references/ # optional
- ```
- When an agent decides a skill is relevant (or you invoke it explicitly), it loads that `SKILL.md` and follows the instructions inside. Descriptions stay in context cheaply; the full body of a skill only loads when the task actually matches.
- Every skill also ships a `skill-card.md`: a short, human-facing governance card (Description, Owner, License) that tells a reviewer what the skill is and who stands behind it without reading the source. See [docs/skill-requirements.md](https://github.com/amd/skills/blob/main/docs/skill-requirements.md#skill-cardmd).
- ## Why a skill, not a doc?
- Documentation describes an API surface: every flag, every option, neutral by design. A skill encodes the opinionated path: which flags, which container image, which `gfx` target, which environment variables, in what order. It captures the decisions a senior AMD engineer makes without thinking, in a form the agent can apply consistently across teams and repositories.
- Skills earn their keep on repeated, opinionated workflows, exactly where the AMD stack lives.
- ## Catalog federation
- The AMD stack is large and moves fast. ROCm, HIP, Ryzen AI, and framework integrations each have their own team, release cadence, and validation matrix. So skills here are **federated**: each skill is owned and versioned by the team that owns the product it describes, and this repository is the catalog that brings them together.
- ```
- ┌─────────────────────────────────────────────────────┐
- │ amd/skills (this repo) │
- │ │
- │ skills/ .github/ .*-plugin/ │
- │ vendored copies federation.json agent manifests │
- └──────────────────────┬──────────────────────────────┘
- │ one install
- ▼
- your AI coding agent
- ▲
- │ resolves pointers to
- ┌───────────────┬───────────────┼───────────────┬────────────────┐
- │ │ │ │ │
- ROCm/ROCm ROCm/HIP Ryzen AI repo lemonade-sdk ...more
- rocm-doctor/ cuda-to-hip/ ryzen-ai-tools/ local-ai-app- product
- gfx-target-... triton-amd-... ... integration/ repos
- ```
- [`.github/federation.json`](https://github.com/amd/skills/blob/main/.github/federation.json) is the whole registry: each
- entry names a source repo and the exact path of every skill folder to vendor
- from it.
- The `federate-skills` workflow runs nightly and on demand. It clones each
- declared repo, compares a content hash of the upstream skill folder against the
- hash recorded in the vendored copy's `.federated.json`, and re-vendors only the
- skills that actually changed. For each skill that did change it regenerates the
- agent manifests and opens a separate pull request titled
- `Bump <skill> to <short commit>`, where the usual `validate` checks apply as they would to any other pull
- request. A quiet night produces no diff and therefore no pull request, so every
- bump that lands is a reviewed commit.
- A vendored skill mirrors its upstream folder, `evals/` included, so the
- datasets this repo grades a federated skill against are maintained in its
- product repo. Files over 100 KB, such as trace archives, stay upstream.
- See [CONTRIBUTING.md](https://github.com/amd/skills/blob/main/CONTRIBUTING.md) to register a repo.
- ## Manual installation
- Until marketplace integration lands, install skills manually: clone this repo, then copy (or symlink) the skill folders you want from `skills/` into your agent's skills directory. Each agent discovers `SKILL.md` automatically.
- ```bash
- git clone https://github.com/amd/skills.git amd-skills
- cp -r amd-skills/skills/local-ai-use <agent-skills-dir>/
- ```
- | Agent | Skills directory (personal / project) |
- | --- | --- |
- | Cursor | `~/.cursor/skills/` or `.cursor/skills/` |
- | Claude Code | `~/.claude/skills/` or `.claude/skills/` |
- | Codex | `$HOME/.agents/skills` or `$REPO_ROOT/.agents/skills` |
- ## Contributing
- Contributions are welcome from AMD engineers and selected partners.
- See [CONTRIBUTING.md](CONTRIBUTING.md) for the step-by-step instructions, then
- [docs/skill-requirements.md](docs/skill-requirements.md) for the rules CI enforces,
- [docs/best-practices.md](docs/best-practices.md) for writing guidance, and
- [docs/evals.md](docs/evals.md) for how skills are graded. The graders themselves
- are [amd/skillscope](https://github.com/amd/skillscope), which you can point at
- your own repo to get the same verdict before you submit.
- ## License
- Released under the MIT License. See [LICENSE](https://github.com/amd/skills/blob/main/LICENSE) for details.
- Copyright (C) 2026 Advanced Micro Devices, Inc. All rights reserved.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.