amd
- 45 skills
- 0 followers
- yesterday last updated
- ▌ Newsletter Digest · amdCondense newsletters, promotions, and other bulk mail into one short digest and clear them out. Use when the user asks what they missed in their subscriptions, wants a digest of bulk mail, or asks to clean up promotions.
- ▌ Gaia Harness Engineering · amdHelp a developer report a GAIA TUI, WebUI or agent problem, explicitly share a snapshot with Claude Code or Codex through MCP, and validate isolated worktree fixes.
- ▌ Escalation Routing · amdDecide which messages need attention now, which can wait, and which belong to someone else. Use when the user asks what is urgent, what needs escalating, what they should look at first, or who should handle something.
- ▌ Meeting Scheduling · amdTurn meeting requests in email into calendar decisions — accept, decline, or propose another time. Use when a message asks to meet, when the user asks about invitations, or when checking whether a proposed time is free.
- ▌ Action Item Extraction · amdPull the concrete commitments out of a thread — who owes what, by when. Use when the user asks what they need to do, what they promised, what is outstanding, or for action items from a conversation.
- ▌ Github Triage · amdAnswer GitHub questions and triage GitHub work with the gh CLI — PRs, issues, commits, CI runs, releases, the notification inbox or a repo's backlog. Links every item; posts a reply only once you approve it. Use for any request about a GitHub repo, PR, issue, commit, CI run or release — what is open, merged, failing or changed — or to triage, check the inbox, see what needs attention or what you are blocking, comment on or label an issue, or decide what to fix first.
- ▌ Document Brief · amdIndex a document or folder and answer questions about it with quotes from the source. Use when the user points at a PDF, contract, spec, report, or folder of files and asks what it says, what changed, or what they should worry about.
- ▌ Meeting Actions · amd bundlePull every action item out of meeting notes, minutes or transcripts, including commitments made in passing ("I'll send it"), with owner, due date and status, merged across meetings, plus a separate decision log. Use when the user asks for action items, follow-ups, to-dos, owners, next steps, decisions or what is still open from meetings.
- ▌ Recommendations · amdRecommend films, books, games, restaurants, or gear using what the user has already said they like and dislike, plus a web search for current options. Use when the user asks what to watch, read, play, buy, or try next.
- ▌ Research Report · amdResearch a topic on the open web and write a cited Markdown report. Use when the user asks for a report, a literature scan, a competitive landscape, or a "what's the current state of X" answer that needs sources.
- ▌ Analyze Recording · amd bundleBreak down a long video or audio recording that is not a meeting — a class, lecture, tutorial, webinar, podcast, interview — from a file or a link such as YouTube, into a timestamped transcript, a structured list of what it contains, and answers about it. Use when the user asks to list every topic, step, tip or recipe in a recording, wants timestamps, chapters or subtitles, or asks what was said and when. For meeting minutes use transcribe-meeting.
- ▌ Transcribe Meeting · amdTranscribe and summarize a meeting recording — timestamped, speaker-attributed transcript, then a brief with decisions and action items. Use whenever the user points at an audio or video file (.mp4, .mkv, .mov, .m4a, .mp3, .wav) or a Teams/Zoom transcript export and asks to transcribe it, summarize it, take notes, write minutes, say what was discussed, who said what, what was decided, or what the action items and follow-ups are.
- ▌ Report From Sources · amdBuild a report, deck, brief, workbook or chart from the user's own files without missing what the sources stress. Use when the user asks to turn documents, spreadsheets or exports into a report, slides, a one-pager, a summary or charts. Uses the newest file per dataset, cites source and period on every figure, and checks every requested item before handing over.
- ▌ Gaia Voice · amdHow GAIA talks and what it must never claim. Always on — the agent's voice and its honesty floor, not a task recipe.
- ▌ Document Extract · amdEnumerate every requested item in long text documents or transcripts, with fields and source evidence. Use for exhaustive inventories such as every exercise, action item, or finding; not ordinary summaries, general knowledge lists, or code symbols.
- ▌ Inbox Triage 2 · amdSort an inbox into what needs a reply, what needs a decision, and what is just noise. Use when the user asks to triage, catch up on, clean up, or make sense of their inbox.
- ▌ Travel Itinerary · amdAssemble scattered booking confirmations into one chronological itinerary. Use when the user asks about an upcoming trip, their flight or hotel details, or wants an itinerary built from their email.
- ▌ Music Gen · amdGenerate original local music and sound effects (WAV) with Lemonade ACE-Step and ThinkSound for games, interactive stories, videos, and audio assets.
- ▌ Summarize · amdSummarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half. Use when the user pastes or points at a transcript, email, PDF, or long document and asks for a summary, action items, or key decisions.
- ▌ Log Triage · amdFind what actually went wrong in log files. Use when the user asks for a root cause, an incident summary, anomalies, errors, failures or "what happened" in system, application, server, device or audit logs. Covers each file's full time range, ranks message templates by severity, rarity and hosts hit rather than volume, and pins burst timestamps.
- ▌ Rss Digest · amd bundleRead an RSS or Atom feed and summarize the newest entries. Use when the user gives a feed URL, asks what a blog or release feed has published lately, or wants a digest of a site that offers a feed.
- ▌ Send Email · amd bundleDraft, reply to, forward and send email from the user's connected Gmail or Outlook account, with their approval of the exact message. Use when the user asks to send, write, reply to, answer, forward or draft an email, or to change, send or delete a saved draft.
- ▌ Automations · amdReminders, alerts, triggers, summaries and the heartbeat — work GAIA does on its own and reports later. "Remind me at 5pm", "alert me if main breaks", "tell me when a good weather window opens", "summarize my inbox every morning", "check in every 30 minutes", "what are you watching?", "pause that", "stop those updates". Use whenever the user wants something done later, repeatedly, or only when something changes, or wants to see or change what is set up.
- ▌ Calculators · amd bundleShow a tip or loan calculator card that does the math. Use for tipping, splitting a bill, mortgages, car loans, monthly payments and loan interest.
- ▌ Daily Brief · amdCompose a short briefing from several sources at once — headlines, tracked topics, and the user's own open items — as one digest instead of separate answers. Use when the user asks for a briefing, a digest, a rundown, or "what do I need to know today".
- ▌ Price Watch · amdCheck product pages for a price drop, comparing against the lowest price seen before and alerting only on a new low. Use when the user asks to watch a price, track a deal, or tell them when something gets cheaper.
- ▌ Data Explore · amdLoad messy tabular data into SQL scratchpad tables and answer questions with real queries instead of eyeballing. Use when the user has a CSV, spreadsheet, export, or pasted table and asks for totals, trends, outliers, or a breakdown.
- ▌ Inbox Triage · amdTriage a mailbox — group what arrived, judge what is urgent and what actually needs the user, and say what to do about it. Use when asked to triage or check mail, deal with email, go through the inbox, see what is unread, get a rundown of what came in, find what needs a reply, or work out which messages matter today.
- ▌ Source Watch · amdCheck a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats. Use when the user asks to watch, monitor, or check a URL for changes, new items, or a condition being met.
- ▌ Coding · amdWork on a codebase — read, search, edit and verify source files. Use when the user asks to fix a bug, add a feature, refactor, explain code, make a test pass, or change anything in a repository. Covers finding the right file, editing safely, and proving the change works before reporting it.
- ▌ Guides · amd bundleShow a recipe, workout, how-to, checklist or trip itinerary as an interactive card. Use for recipes and cooking or baking, workouts, fixing, installing or setting something up, shopping, packing or to-do lists, and travel plans.
- ▌ Calendar · amd bundleSee and change the user's Google or Outlook calendar with their approval. Use when the user asks what is on their calendar, when they are free, or to schedule, book, move or cancel a meeting or event.
- ▌ Check In · amdRun a short personal check-in that picks up where the last one left off, following up on what the user said they would do and recording what changed. Use when the user says good morning, asks for a check-in, or asks what they were working on.
- ▌ File Ops · amdRead, write, and edit files on disk safely — locate the right file, change only what was asked, and confirm before anything destructive. Use when the user wants a file read, created, modified, or searched for by name or content.
- ▌ Image Gen · amdTurn a description into an image with a downloaded Lemonade model (Stable Diffusion or TheNoise), then iterate on it. Use for draw, sketch, paint, render, "make a picture of", "generate an image", concept art, game art, backgrounds, thumbnails, logos, wallpapers, mockups, and requests to change the last image rather than replace it.
- ▌ Local AI Use · amd bundleMakes 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 the same breath. Also use it for a single request the user wants done locally, offline, on-device, or kept private: transcribe this recording, make this picture, read this text aloud. Applies in Claude, Cursor, Codex, or any agent harness. Use when the user wants to cut cost or tokens on image, audio, or voice API calls, or to drop DALL-E, hosted Whisper, ElevenLabs, or other paid multimodal APIs; or mentions Lemonade Server, OmniRouter, SD-Turbo, kokoro, Ryzen AI, or NPU/iGPU/dGPU inference. Changes no application source code; do not use it if the user is adding local AI to an app they ship.
- ▌ Rocm Doctor · amd bundleDiagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux or Windows, 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. Use when the user reports that ROCm or HIP "isn't working", torch.cuda.is_available() is False, rocminfo / hipInfo can't see the GPU, or hits hipErrorNoBinaryForGpu, HSA_STATUS_ERROR_INVALID_ISA, "invalid device function", "no kernel image is available", cannot open /dev/kfd, permission denied on /dev/kfd, "ROCk module is NOT loaded", a missing libamdhip64.so / amdhip64_6.dll / hipblas.dll / vcruntime140_1.dll, an HSA_OVERRIDE_GFX_VERSION page fault, an iGPU+dGPU crash, a container that can't see the GPU, or an amdgpu-install / DKMS failure. Backed by the `rocm` CLI (`rocm examine` / `rocm diagnose` / `rocm fix`); this skill is a thin driver over those commands, not a re-implementation.
- ▌ Apu Memory Tuner · amd bundleInspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the CPU. Use when the user mentions Ryzen AI, Strix Halo / Strix Point / Krackan / Phoenix / Hawk Point, Ryzen AI Max, gfx1150 / gfx1151 / gfx1152, integrated Radeon, iGPU memory, UMA Frame Buffer Size, AMD Variable Graphics Memory, VGM, GTT, GART, TTM, pages_limit, amd-ttm, amd-debug-tools, "shared GPU memory", "dedicated GPU memory", carve-out, "not enough VRAM", "out of VRAM", "GPU OOM", llama.cpp on iGPU, ROCm on APU; or asks how much memory the iGPU can use, how to give the iGPU more memory, how to balance memory between CPU and GPU on UMA, or how to change the BIOS UMA reservation. Read-only diagnostics work everywhere; tuning runs automatically on Linux via `amd-ttm` and prints guided BIOS steps on Windows. Do not use for discrete Radeon cards, Intel iGPUs, or Apple Silicon -- it is APU-only.
- ▌ Serving Llms On Epyc · amd bundleServes 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. Runs one instance on one socket and its memory. Reports and stops on failure; does not retry or debug. Use serving-llms-on-instinct when the endpoint should run on a GPU. Excludes multi-node, EPYC 4000, and pre-Zen4 EPYC without AVX-512.
- ▌ Lemonade Router Builder · amd bundleTurns 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. Use when the user wants to route requests between models ("route sensitive queries to X and everything else to Y"), generate a router/hybrid-router config or policy, author a collection.router JSON, split traffic between a small local model and a big/cloud model, add PII/jailbreak/topic classifiers to routing, or mentions Lemonade Router, routing rules, routing.router, candidates/default_model, keywords_any, semantic_similarity, or LLM-as-router. Fills every field the user did not specify with safe defaults.
- ▌ Magpie Kernel Evaluator · amd bundleBenchmarks 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 variants; run local, container, or Ray workloads; or mentions Magpie, TraceLens, gap analysis, TTFT, TPOT, kernel evaluation, or AMD GPU optimization.
- ▌ Local AI App Integration · amd bundleIntegrates 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. Do not use when the user just wants the agent itself to generate images, transcribe, or speak locally in the current workspace, even to cut their own API bill.
- ▌ Serving Llms On Instinct · amd bundleServes 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. Use when the user asks "run Qwen3", "serve DeepSeek", "start a vLLM endpoint", "get a model running on my AMD machine", or any similar phrasing. Handles the full flow: GPU detection, environment validation, vLLM configuration, launch, and health verification. Do not use for NVIDIA GPUs, consumer AMD GPUs (RX series, Radeon), Ryzen AI, NPU, MI250X, or MI100.
- ▌ Hyperloom Workload Optimizer · amd bundleAutonomously 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 GPU-kernel rewrites), benchmarks each candidate, and returns the optimization stack that produced the gain. Use when the user wants to make a model serve faster, raise tokens/sec or throughput, optimize or tune vLLM or SGLang on MI300X/MI325X/MI355X, run Hyperloom, run the kernel-agent, quantize-then-optimize with Quark, set up Hyperloom from scratch, or resume a Hyperloom session. Do not use to stand up a server for plain serving, diagnose a broken ROCm install, or run a one-off kernel/benchmark or trace analysis without the optimization loop.
- ▌ Tracelens Analysis Orchestrator · amd bundleOrchestrates 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). Use when the user asks to follow the analysis orchestrator, run the agentic analysis workflow, analyze a trace, compare two traces, or mentions standalone or comparative TraceLens analysis.