全部 Agent Skills
41,263 个结果
- Hyperloom Workload OptimizerAMDAutonomously 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…
- Lemonade Router BuilderAMDTurns 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.
- Local Ai App IntegrationAMDIntegrates 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.
- Local Ai UseAMDMakes 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…
- Magpie Kernel EvaluatorAMDBenchmarks 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…
- Manga Dramafreestylefly漫剧生成器 - 基于 Seedance 的漫画风格短剧生成工具。支持以主角图片为基础，自动生成漫剧分镜脚本并生成视频。适用于创作漫画风格的短视频、角色故事、动画短片等。当用户想要生成漫画风格的视频短剧、角色故事或漫剧时使用此技能。
- Manga Style Videofreestylefly漫画风格视频生成器 - 专门生成日式治愈系、国风水墨、美式卡通等漫画风格的动画视频。内置8种漫画风格模板，支持图生视频，一键生成高质量漫画动画。当用户需要生成漫画风格、动画风格、手绘风格的视频时使用此技能。
- Quark InstallAMDInstalls or verifies AMD Quark and ensures the selected Python environment has an accelerator-matched PyTorch. Applies to "install Quark", "set up Quark", "pip install amd-quark", Quark dependency or import failures, ModuleNotFoundError for quark, and Quark kernel compiler errors. Defaults to GPU and requires explicit confirmation before CPU mode.
- Quark Torch Llm PtqAMDRuns an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request execution approval, and produce a quantized model. Applies to Llama, Qwen, Mistral, and similar transformer LLM requests involving FP8, INT4, or another Quark scheme.
- Release SkillsfreestyleflyUniversal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送".
- Rocm DoctorAMDDiagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux, Windows, or WSL2, 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.
- Rocprofiler Pc SamplingAMDProfiles a target application using rocprofv3 with program counter sampling enabled and then analyzes the results. Use when the user has a program that runs on an AMD GPU and asks to perform PC sampling, to determine the runtime performance characteristics of their application, to determine stall reasons, or to determine hotspots in the code.
- Seedance Videofreestylefly使用字节跳动 Seedance 模型生成视频。支持文生视频和图生视频功能，通过 volcengine-ark SDK 调用 API。当用户需要生成视频、创建视频内容或基于文字/图片制作视频时激活此技能。
- Serving Llms On EpycAMDServes 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.
- Serving Llms On InstinctAMDServes 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.
- Tracelens Analysis OrchestratorAMDOrchestrates 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).
- Volcengine Video Understandingfreestylefly火山视频理解 - 使用火山方舟视频理解 API 分析视频内容。通过 Files API 上传视频（推荐），支持大文件（最大512MB），可用于视频内容分析、物体识别、动作理解等。当用户需要分析视频、理解视频内容、提取视频信息时激活此技能。
- Component SearchdiodeincSearch for and add electronic components and reusable subcircuits to a Zener PCB project. Use when designing a board, module, or subsystem and you need a part package, a reusable module, or a component package that may already include application circuitry.
- Datasheet ReaderdiodeincRead datasheets and technical PDFs with `pcb scan`.
- Ecommerce Image Suitewzj177电商套图生成助手。用户明确提出需要生成电商套图、商品主图、卖点图、场景图、模特图等图片内容时触发。 支持国内平台（淘宝、京东、拼多多、抖音）与国际跨境平台（Amazon、独立站）的尺寸规范。 触发示例：「帮我生成这件T恤的电商套图」「做一套淘宝主图」「生成亚马逊listing图片」。 不应在用户仅上传图片但未明确提出图片生成需求时触发。
- Idiomatic ZenerdiodeincStyle rules and idioms for writing high-quality Zener HDL code. Use when writing, reviewing, or refactoring `.zen` files — modules, reference designs, or board files. Covers DNP patterns, typed configs, voltage checks, component naming, computation style, and common gotchas.
- Kubernetes SkilllukasniessenPrevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and platform-specific Kubernetes work for EKS, GKE, AKS, OpenShift, GitOps…
- LibrariandiodeincCreate or repair reusable component and module packages in a PCB registry.
- PcbdiodeincWork with PCB designs in the Zener hardware description language. Use when writing or editing .zen files, building schematics, searching for components, or searching for Zener packages.