Agent skills by amd

Adds a release eval scorecard to a GAIA hub agent by writing a harness adapter, running a real eval, and wiring the result into the agent's README and release gate.

amd/gaia

Inspects 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…

amd/skills

Walks through releasing a GAIA sidecar agent as a frozen binary plus npm client through the tag-triggered Agent Hub CI pipeline, with a human gate before publishing.

amd/gaia

Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.

amd/skills

Build the standalone ZenDNN native library (zendnnl) from source with the alternate compute backends OFF (no oneDNN, libxsmm, parlooper, fbgemm), keeping AOCL DLP, which is the GEMM backend zendnnl…

amd/ZenDNN

Author or restructure a Quark Agent Skill so it conforms to this project's template, contracts, and layer rules.

amd/Quark

Mines local Claude Code session transcripts with a deterministic Python pipeline to show what the agent is actually used for, how often it fails and what it costs.

amd/gaia

Makes 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.

amd/skills

Benchmarks AMD's GAIA agent against Claude Code and across models on quality, honesty, steps, tokens, time and real cost, using gaia eval tasks.

amd/gaia

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

amd/ZenDNN

Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.

amd/skills

Guides safe code changes by finding the right file with grep or semantic search, reading before editing, reproducing bugs first, and proving a fix with a real test run.

amd/gaia

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

amd/Quark

Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda.

amd/skills

Author a new ShapeShifter graph-transformation pass for AMD Quark (ONNX or PyTorch) so it conforms to the pass framework's conventions and auto-registers.

amd/Quark

Walks through scaffolding, writing and testing a new GAIA agent as a Python class with the SDK, from the base Agent subclass to registered tool methods.

amd/gaia

Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer.

amd/skills

Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.

amd/Quark

Turns a source document such as a README or spec into an executive slide deck as one self-contained HTML file that prints to PDF, one slide per page.

amd/gaia

Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

amd/skills

Install or verify the AMD Quark package and its dependencies.

amd/Quark

Turns a source document such as a README or spec into a technical slide deck for engineers, as one self-contained HTML file that prints to PDF with one slide per page.

amd/gaia

L3 recipe that runs quark.onnx.AutoSearchPro end-to-end on a user .onnx model: intake → preset selection (or custom search space) → calibration / eval data reader → standalone autosearch script…

amd/Quark

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…

amd/skills

Diagnose failed Quark ONNX installation, calibration, quantization, custom-op compilation, or export attempts.

amd/Quark

Compare ONNX skill contracts and guidance against current Quark ONNX documentation and source entry points.

amd/Quark

Embeds one of this repo's pre-built hub agents (under hub/agents/) into a developer's own application.

amd/gaia

Integrates local AI capabilities into applications using Embeddable Lemonade.

amd/skills

Manually verify that the Quark ONNX skill family behaves correctly across the four contract categories (routing, planning, artifact, recovery).

amd/Quark

Interactively clear a backlog of open amd/gaia PRs to zero (or to a short, justified human-review list) by fanning out one isolated subagent per PR.

amd/gaia

Assess a reported security vulnerability in GAIA and fill a PSIRT / JIRA triage: decide if it is valid & exploitable, whether it needs a CVE + bulletin, and produce the CVSS 4.0 score, CWE, and CVE…

amd/gaia

Transcribe and summarize a meeting recording — speaker-attributed transcript, corrected mis-hearings, then a brief with decisions and action items.

amd/gaia

A skill your agent uses when integrating the @amd-gaia/agent-email npm package — embedding the GAIA email agent (a local triage/draft/send sidecar) into a Node, TypeScript, or Electron app.

amd/gaia

Cut a GAIA release end-to-end: draft notes, open release PR, run pre-tag verification, push the tag, monitor the publish pipeline, and produce the Discord announcement.

amd/gaia

GAIA's multi-tier regression harness — runs unit, integration, and real-world (on-machine) tiers and brings back screenshots, logs, traces, planted-fact retrieval proof, and per-operation timing…

amd/gaia

Test the flagship GAIA agent end-to-end through the Go TUI — launch it, drive it without colliding with other agents, run the capability ladder, verify skills really call their tools instead of…

amd/gaia

Install or verify the correct ONNX Runtime build (and the onnx package) for a user's accelerator backend before Quark's ONNX-to-ONNX flow.

amd/Quark

Triage GitHub work with the gh CLI — your unread notification inbox, or one repository's issue backlog.

amd/gaia

Run 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.

amd/gaia

Compose 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.

amd/gaia

Load messy tabular data into SQL scratchpad tables and answer questions with real queries instead of eyeballing.

amd/gaia

Index a document or folder and answer questions about it with quotes from the source.

amd/gaia

Read, write, and edit files on disk safely — locate the right file, change only what was asked, and confirm before anything destructive.

amd/gaia

The GAIA terminal UI (gaia-tui) — how to build it, launch it with a real pty, drive it through the loopback control API, choose a local or cloud model provider, and read its logs.

amd/gaia

Turn a description into an image file with local Stable Diffusion, then iterate on it.

amd/gaia

Triage a mailbox — group what arrived, judge what is urgent and what actually needs the user, and say what to do about it.

amd/gaia

Patterns, gotchas, and conventions for threading changes through LemonadeClient, its callers, and the GAIA test suite.

amd/gaia

A skill your agent uses when taking an existing in-repo GAIA agent to a published, day-one-usable hub package — porting a legacy agent under hub/agents/<id/, deciding whether an agent should ship at…

amd/gaia