AMD
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 k...
From the developer
Skills
Claude Code
From the marketplace listing
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.
Oct 27, 2026 · 18:00 UTC
Web → Id: “wf.6a5a60c359e76e4bb0764701” → “directoryPlugin.4d5f9ff4-bb3c-4dd3-a095-7aac7616cd6e”
Web → Anthropic verified: “false” → “true”
Web → Made by: “AMD” → “not provided”
Web → Subheading: “AMD Agent Skills: Ryzen AI for images/audio, Instinct GPUs for LLMs via vLLM, GPU kernel & PyTorch trace analysis.” → “not provided”
Oct 3, 2026 · 22:13 UTC
Catalogs updated; open the comparison for details.
Find competitors to follow as you develop your plugin.
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Cove...
Shared terms: audio, image, inference, agent
AI agent skills for 150+ models via inference.sh CLI - generate images with FLUX, create videos with Veo, call LLMs, search the web, and ...
Shared terms: image, inference, llms, agent
A collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video,...
Shared terms: audio, image, inference, agent
Run Codeflash as a background agent in Claude Code to automatically optimize Python, Java, JavaScript, and TypeScript code for performanc...
Shared terms: optimize, agent, analyze, performance
Optimize your prompts with one command - analyzes weaknesses, applies best practices, and reconstructs with a changelog.
Shared terms: optimize, one, analyze
[ "./local-ai-use", "./local-ai-app-integration", "./serving-llms-on-instinct", "./tracelens-analysis-orchestrator", "./hyperloom-workload-optimizer" ]
{
"name": "amd-skills",
"author": {
"name": "AMD"
},
"skills": [
"./local-ai-use",
"./local-ai-app-integration",
"./serving-llms-on-instinct",
"./tracelens-analysis-orchestrator",
"./hyperloom-workload-optimizer"
],
"source": {
"ref": "main",
"sha": "6916fb371d1cba40757b223cf16b4cd4912b202f",
"url": "https://github.com/amd/skills.git",
"path": "skills",
"source": "git-subdir"
},
"strict": false,
"category": "development",
"homepage": "https://developer.amd.com/",
"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."
}
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.