# skills: a set by amd

The amd/skills repository on GitHub: 18 cards with a description and an install command. Inside: 17 skills and 1 plugin. They install into Claude Code, Codex and Cursor.

18 cards

- HTML: https://affpapa.org/en/nevibecode/by/amd/skills
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [local-ai-use](https://affpapa.org/en/nevibecode/skills/local-ai-use.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1700 installs — The local-ai-use skill routes image generation, text-to-speech and speech-to-text through a local Lemonade Server instead of a paid cloud API.
- [lemonade-router-builder](https://affpapa.org/en/nevibecode/skills/lemonade-router-builder.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1300 installs — lemonade-router-builder — a Claude Code skill that turns plain-English routing requirements into valid collection.router policy JSON for Lemonade Server.
- [serving-llms-on-epyc](https://affpapa.org/en/nevibecode/skills/serving-llms-on-epyc.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1300 installs — serving-llms-on-epyc deploys a vLLM endpoint with the zentorch backend on AMD EPYC CPUs using Docker, Podman, or conda.
- [magpie-kernel-evaluator](https://affpapa.org/en/nevibecode/skills/magpie-kernel-evaluator.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1300 installs — magpie-kernel-evaluator benchmarks LLM inference with Magpie, turns torch traces into stage and roofline reports, and carries an optimization from a hot kernel to a validated variant.
- [serving-llms-on-instinct](https://affpapa.org/en/nevibecode/skills/serving-llms-on-instinct.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1300 installs — serving-llms-on-instinct is a Claude Code skill that serves language models on AMD Instinct with vLLM.
- [tracelens-analysis-orchestrator](https://affpapa.org/en/nevibecode/skills/tracelens-analysis-orchestrator.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1300 installs — tracelens-analysis-orchestrator orchestrates modular PyTorch profiler trace analysis with TraceLens, running parallel subagents and generating a prioritized report.
- [local-ai-app-integration](https://affpapa.org/en/nevibecode/skills/local-ai-app-integration.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1300 installs — local-ai-app-integration integrates Embeddable Lemonade into apps that currently call cloud AI APIs.
- [hyperloom-workload-optimizer](https://affpapa.org/en/nevibecode/skills/hyperloom-workload-optimizer.md) — skill · amd · Claude Code, Codex, Cursor +5 · 1200 installs — hyperloom-workload-optimizer bootstraps Hyperloom on an AMD Instinct host and kicks off multi-agent throughput optimization for LLM serving.
- [quark-install](https://affpapa.org/en/nevibecode/skills/quark-install.md) — skill · amd · Claude Code, Codex, Cursor +5 · 966 installs — quark-install installs or verifies AMD Quark and makes sure the Python environment has a PyTorch build that matches the accelerator.
- [quark-torch-llm-ptq](https://affpapa.org/en/nevibecode/skills/quark-torch-llm-ptq.md) — skill · amd · Claude Code, Codex, Cursor +5 · 965 installs — quark-torch-llm-ptq walks a PyTorch or Hugging Face model through AMD Quark post-training quantization: intake, plan, manifest, run.
- [rocprofiler-pc-sampling](https://affpapa.org/en/nevibecode/skills/rocprofiler-pc-sampling.md) — skill · amd · Claude Code, Codex, Cursor +5 · 592 installs — rocprofiler-pc-sampling profiles AMD GPU applications with rocprofv3 program counter sampling to uncover execution hotspots and GPU stall reasons.
- [flydsl-kernel-authoring](https://affpapa.org/en/nevibecode/skills/flydsl-kernel-authoring.md) — skill · amd · Claude Code, Codex, Cursor +5 · 437 installs — flydsl-kernel-authoring — a skill for Claude Code and Cursor serving as a reference manual for authoring and reviewing FlyDSL GPU kernels on AMD GPUs.
- [flydsl-kernel-trace-analysis](https://affpapa.org/en/nevibecode/skills/flydsl-kernel-trace-analysis.md) — skill · amd · Claude Code, Codex, Cursor +5 · 436 installs — The flydsl-kernel-trace-analysis Claude Code skill profiles GPU kernels and analyzes their instruction-level traces to locate stalls.
- [rocprofiler-systems-choosing-a-profiling-preset](https://affpapa.org/en/nevibecode/skills/rocprofiler-systems-choosing-a-profiling-preset.md) — skill · amd · Claude Code, Codex, Cursor +5 · 266 installs — rocprofiler-systems-choosing-a-profiling-preset is a Claude Code skill that selects a runtime preset by workload and profiling goal.
- [rocprofiler-systems-discovering-profiling-options](https://affpapa.org/en/nevibecode/skills/rocprofiler-systems-discovering-profiling-options.md) — skill · amd · Claude Code, Codex, Cursor +5 · 266 installs — rocprofiler-systems-discovering-profiling-options is a Claude Code skill that finds the right command for exploring ROCPROFSYS profiling options.
- [rocprofiler-systems-instrumenting-binaries](https://affpapa.org/en/nevibecode/skills/rocprofiler-systems-instrumenting-binaries.md) — skill · amd · Claude Code, Codex, Cursor +5 · 266 installs — rocprofiler-systems-instrumenting-binaries is a Claude Code skill for binary instrumentation with rocprof-sys-instrument, activated when selecting trace targets or investigating missing or excessive entries.
- [moat-cuda-to-rocm](https://affpapa.org/en/nevibecode/skills/moat-cuda-to-rocm.md) — skill · amd · Claude Code, Codex, Cursor +5 · 104 installs — The moat-cuda-to-rocm skill for Claude Code ports CUDA projects to ROCm and HIP for AMD GPUs.
- [amd-skills](https://affpapa.org/en/nevibecode/plugins/amd-skills.md) — plugin · AMD · Claude Code · ★ 510 repo stars — The plugin adds AMD skills to Claude Code: route image and audio generation through local AI on Ryzen, deploy LLMs on Instinct GPUs with vLLM, and analyze GPU kernel performance.

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
