marketplace.json

{
  "name": "amd-skills",
  "owner": {
    "name": "AMD"
  },
  "description": "Agent Skills for AMD-optimized workflows.",
  "metadata": {
    "description": "Agent Skills for AMD-optimized workflows.",
    "version": "0.1.0"
  },
  "plugins": [
    {
      "name": "local-ai-app-integration",
      "source": "./skills/local-ai-app-integration",
      "description": "Integrate local AI into cloud LLM apps for offline support, better privacy, and lower API costs."
    },
    {
      "name": "local-ai-use",
      "source": "./skills/local-ai-use",
      "description": "Route image generation, text-to-speech, and speech-to-text through a local AI Server to reduce token/cost usage."
    },
    {
      "name": "magpie-kernel-evaluator",
      "source": "./skills/magpie-kernel-evaluator",
      "description": "Performs GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie. Analyzes single or multiple kernels (HIP/CUDA/PyTorch), compares kernel implementations, runs vLLM/SGLang benchmarks with profiling and TraceLens, and runs gap analysis on torch traces."
    },
    {
      "name": "serving-llms-on-instinct",
      "source": "./skills/serving-llms-on-instinct",
      "description": "Serve LLMs on AMD Instinct GPUs (MI300X/MI325X/MI350X/MI355X) with vLLM on ROCm. Handles GPU detection, environment validation, vLLM configuration, launch, and health verification."
    },
    {
      "name": "tracelens-analysis-orchestrator",
      "source": "./skills/tracelens-analysis-orchestrator",
      "description": "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)."
    },
    {
      "name": "vllm-multiinstance",
      "source": "./skills/vllm-multiinstance",
      "description": "Multi-instance vLLM CPU benchmark on AMD EPYC: runs N vLLM instances behind NGINX, drives load with guidellm, and reports peak memory and end-to-end throughput/latency across models, concurrency rates, and instance counts."
    }
  ]
}