skills

AMD Skills <div align="center"> <img src="assets/banner.gif" alt="AMD Skills"/> **Browse the Skill 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 format and are designed to interoperate with the major coding agents like Cursor, Claude Code, OpenAI Codex, and Gemini CLI. > [!IMPORTANT] > **Tech Preview:** We’re building the catalog in the open, sharing progress as the foundations take shape. Expect frequent changes as skills, categories, and descriptions evolve. Installation Install AMD Skills with the `skills` CLI via `npx`. No clone or manual copying required. 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`): Browse everything available before installing: Please note that `npx` requires Node.js. Prefer to do it by hand? See 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. 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` | Route image generation, text-to-speech, and speech-to-text through a local AI server to reduce token cost. | in-repo | | `local-ai-app-integration` | Integrate local AI into cloud LLM apps for offline support, better privacy, and lower API costs. | in-repo | Cross-Stack Cross-stack skills, from client to cloud. | Skill | What it does | Source | | --- | --- | --- | | `rocm-doctor` | Diagnose ROCm / PyTorch / llama.cpp failures on AMD GPUs against a fixed list of known misconfigurations. | _planned_ | | `hyperloom-workload-optimizer` | Autonomously optimizes LLM inference on AMD GPUs. | _planned_ | | `lemonade-router-builder` | Set up a Lemonade model router that handles requests based on content, sensitivity, or required capabilities. | in-repo | | `hrr-replay-analysis` | Record, replay, and analyze GPU workload behavior on ROCm across AMD Instinct, Radeon, and Ryzen hardware using HIP Record and Replay archives. | _planned_ | Server-Native Run and optimize on AMD Instinct. | Skill | What it does | Source | | --- | --- | --- | | `serving-llms-on-instinct` | 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/backend selection in later phases. | in-repo | | `serving-llms-on-epyc` | Serve LLMs on AMD EPYC CPUs with vLLM + zentorch, in a container (Docker/Podman) or conda. Handles CPU detection, runtime/env validation, vLLM model-support and RAM-fit checks, hardware-sized threads/KV, launch, and health verification. Single instance; reports and stops on failure. | in-repo | | `magpie-kernel-evaluator` | Evaluate GPU kernel correctness and performance, compare kernel implementations, and benchmark vLLM / SGLang inference with profiling, TraceLens, and torch-trace gap analysis. | Magpie | | `tracelens-analysis-orchestrator` | 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 | 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. When an agent decides a skill is relevant (or you invoke it explicitly), it loads that `SKILL.md` and follo