Updated 1d ago
by amd
skills
Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.
420 GitHub stars (420)
+43 in 20 days
| Period | New stars |
|---|---|
| Sep 27–28 (2 days) | +1 |
| Sep 29 | 0 |
| Sep 30 | +5 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | +3 |
| Oct 4 | 0 |
| Oct 5 | −1 |
| Oct 6 | +2 |
| Oct 7 | +8 |
| Oct 8 | +3 |
| Oct 9 | +8 |
| Oct 10 | +1 |
| Oct 11 | +4 |
| Oct 12 | +1 |
| Oct 13 | +4 |
| Oct 14 | +2 |
| Oct 15 | +1 |
| Oct 16 | +1 |
- 13 skills (13 skills found in its SKILL.md files)
- 42 forks (42 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add amd/skills
Asks which skills and agents to install. Just one: npx skills add amd/skills --skill hyperloom-workload-optimizer — add -g for every project.
Claude Code
git clone https://github.com/amd/skillscp -r "skills/skills/hyperloom-workload-optimizer" ~/.claude/skills/
Copies the hyperloom-workload-optimizer skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add amd/skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
hyperloom-workload-optimizer
Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a model, framework, workload (TP/EP, concurrency, ISL/OSL, precision), an objective and a time budget, it explores per-workload which levers to pull (serving/config parameters and env, framework enablement and source patches, and hot GPU-ke…
skills/hyperloom-workload-optimizer/SKILL.md on GitHub (opens in a new tab) -
lemonade-router-builder
Turns a natural-language description of routing intent into a valid Lemonade `collection.router` policy JSON. The skill generates and validates the JSON only - it does not register it or call the live server. Use when the user wants to route requests between models ("route sensitive queries to X and everything else to Y"), generate a router/hybrid-router config or policy, author a collection.rout…
skills/lemonade-router-builder/SKILL.md on GitHub (opens in a new tab) -
local-ai-app-integration
Integrates local AI capabilities into applications using Embeddable Lemonade. Use when the user wants to add local AI, offline AI, private AI, on-device AI, a local LLM, local chat, embeddings, image generation, speech-to-text, or text-to-speech to an existing app; replace or supplement OpenAI, Anthropic, Ollama, or other cloud AI APIs with a local backend; only use to convert user apps. Do not u…
skills/local-ai-app-integration/SKILL.md on GitHub (opens in a new tab) -
local-ai-use
Makes this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API. Use it above all to change that routing persistently, from now on — keep generating pictures locally while chat stays on the cloud; set this workspace up to make images on my own machine — even when the user asks for no image or file in t…
skills/local-ai-use/SKILL.md on GitHub (opens in a new tab) -
magpie-kernel-evaluator
Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process inference traces with TraceLens into prefill/decode and roofline reports; identify top bottleneck kernels or map profiler names to source; analyze or compare HIP, CUDA, PyTorch, or Triton kernels; validate and rank optimized varian…
skills/magpie-kernel-evaluator/SKILL.md on GitHub (opens in a new tab) -
serving-llms-on-epyc
Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda. Use for "vLLM on CPU", "zentorch serving", or an EPYC CPU endpoint, including on a host that also has AMD Instinct GPUs. Detects the EPYC generation, validates the runtime, checks model support and RAM fit, sizes threads/KV/NUMA, confirms the plan, launches, and verifies the endpoint. Runs one…
skills/serving-llms-on-epyc/SKILL.md on GitHub (opens in a new tab) -
serving-llms-on-instinct
Serves AI models on AMD Instinct GPU hardware using vLLM. Use this skill whenever the user wants to run, serve, deploy, start, host, or launch a language model on an AMD GPU, AMD Instinct, MI300X, MI325X, MI350X, or MI355X. Also use when the user mentions vLLM on ROCm, vLLM on AMD, serving on HBM, or asks how to get a model running on AMD data center hardware. Use when the user asks "run Qwen3",…
skills/serving-llms-on-instinct/SKILL.md on GitHub (opens in a new tab) -
tracelens-analysis-orchestrator
Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs, and writes a prioritized stakeholder report (analysis.md). Use when the user asks to follow the analysis orchestrator, run the agentic analysis workflow, analyze a trace, compare two traces, or mentions…
skills/tracelens-analysis-orchestrator/SKILL.md on GitHub (opens in a new tab) -
apu-memory-tuner
Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the CPU. Use when the user mentions Ryzen AI, Strix Halo / Strix Point / Krackan / Phoenix / Hawk Point, Ryzen AI Max, gfx1150 / gfx1151 / gfx1152, integrated Radeon, iGPU memory, UMA Frame Buffer Size, AM…
staging/apu-memory-tuner/SKILL.md on GitHub (opens in a new tab) -
rocm-doctor
Diagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux or Windows, then applies a low-risk fix with consent or hands back the exact next step. Also routes Lemonade, LM Studio, and Ollama problems to the right upstream channel. Use when the user reports that ROCm or HIP "isn't working", torch.cuda.is_available() is False, rocminfo / hipInfo can't see the GPU, or hi…
staging/rocm-doctor/SKILL.md on GitHub (opens in a new tab) -
eval-post-processing
No description in the SKILL.md.
skills/tracelens-analysis-orchestrator/evals/skills/eval-post-processing/SKILL.md on GitHub (opens in a new tab) -
quality-llm-eval
No description in the SKILL.md.
skills/tracelens-analysis-orchestrator/evals/skills/quality-llm-eval/SKILL.md on GitHub (opens in a new tab) -
workflow-llm-eval
No description in the SKILL.md.
skills/tracelens-analysis-orchestrator/evals/skills/workflow-llm-eval/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills