NVIDIA AI Platform

Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models.

yzlnew/infra-skills

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.

Orchestra-Research/AI-Research-SKILLs

Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.

Orchestra-Research/AI-Research-SKILLs

Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count.

Orchestra-Research/AI-Research-SKILLs

Detects CPU, GPU, memory and disk resources before heavy scientific tasks and writes a JSON file with advice on parallelism, out-of-core work and GPU use.

davila7/claude-code-templates

Initialize a Draw Things GPU server with GPUScript, including script sync, Docker/CUDA/NVIDIA runtime setup, 7T data disk mounting, mergerfs, and end-to-end GPU verification.

drawthingsai/draw-things-community

Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI.

brevdev/workshop-build-an-agent

Runs the Megatron-LM autoformat script and its linting tools before a pull request, and keeps Python imports in order with isort.

NVIDIA/Megatron-LM

Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia embedding models for RAG, semantic search, similarity.

mydisha/keirouter

Set up a K3s cluster on an NVIDIA GPU host, connect it to Azure Arc, and configure Azure ML to use it as a Kubernetes compute target.

microsoft/physical-ai-toolchain

Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.

wuisabel-gif/MemWhale

Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

NVIDIA/skills

Inventory and explain the patch (monkey-patch) optimizations Primus layers over upstream training backends such as Megatron-LM, TorchTitan, and MaxText, including their version compatibility…

AMD-AGI/Primus

Validate the staging NemoClaw Brev Launchable through its web journey or a deployed environment.

NVIDIA/NemoClaw

Query current NVIDIA CUDA, PTX ISA, Runtime API, Driver API, Programming Guide, Best Practices, Nsight Compute, and Nsight Systems references.

slowlyC/agent-gpu-skills

Run the Nemotron-3.5 Lightning Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on a single node: data prep, checkpoint conversion, LoRA fine-tuning of the 30B-A3B…

NVIDIA-NeMo/Nemotron

Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

NVIDIA/skills

Scaffold a new CV-CUDA operator — a complete, wired, building skeleton — and delegate the implementation to a human or another AI.

CVCUDA/CV-CUDA

Calculate training costs for Tinker fine-tuning jobs. An agent skill from sundial-org/skills.

sundial-org/skills

Run NVIDIA compute-sanitizer (memcheck, racecheck, initcheck, synccheck) against a Triton/TLX kernel to find runtime memory and synchronization bugs.

facebookexperimental/triton

Run, monitor, stop and report Primus convergence tests -- training a model on a real corpus and checking that the loss curve is healthy -- from a plain-language request such as "run convergence test…

AMD-AGI/Primus

A skill your agent uses when reviewing the weekly AICR component drift report — the Slack digest and drift-report.json artifact produced by Registry Drift Report (registry-drift.yaml) listing which…

NVIDIA/aicr

Quick install and deploy vLLM, start serving with a simple LLM, and test OpenAI API.

vllm-project/vllm-skills

Optimize fused cross-entropy loss kernels in Triton for NVIDIA and AMD GPUs.

ZJLi2013/awesome-kernel-skills

Author or edit NeMo Relay documentation or examples when repository-specific MDX, public API, integration, or release-history conventions matter.

NVIDIA/NeMo-Relay

A skill your agent uses when deploying or operating standalone RTVI-CV-3D / MV3DT multi-camera 3D tracking for calibrated MP4/file inputs and live RTSP streams: missing-calibration handoff to AMC…

NVIDIA-AI-Blueprints/video-search-and-summarization

为 AutoResearch 的双 Agent 轨迹、付费 GPU 长跑、Docker 执行、可信评测与恢复建立共享协议、成本决策和隔离边界。用于小时/包日选择、启动或恢复 campaign、设计证据与防止题目或轨迹串用；不替代具体任务算法或最终平台 QA。

bosprimigenious/autoresearch-skills

Uses Meta's LlamaGuard moderation model to screen prompts and model replies against six safety categories, with vLLM, FastAPI and NeMo Guardrails setups.

Orchestra-Research/AI-Research-SKILLs

Run the Nemotron-3 Ultra Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on their SLURM cluster: data prep, distributed checkpoint conversion, and packed LoRA…

NVIDIA-NeMo/Nemotron

Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

NVIDIA/skills

This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

brevdev/workshop-build-an-agent

Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate).

CVCUDA/CV-CUDA

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

amd/Quark

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/Megatron-LM

Optimize FlashAttention-style fused attention kernels in Triton for NVIDIA and AMD GPUs.

ZJLi2013/awesome-kernel-skills

Reference desk for NVIDIA Nemotron 3 Ultra (550B-A55B) — architecture, NVFP4 pretraining, SFT, MOPD (multi-teacher on-policy distillation), MTP boosting, quantization, inference.

NVIDIA-NeMo/Nemotron

A skill your agent uses when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.

BBuf/AI-Infra-Auto-Driven-SKILLS

Upgrade focused runtime dependencies in AReaL. An agent skill from areal-project/AReaL.

areal-project/AReaL

MemoryWhale debugging; compiler failures; terminal diagnostics.

wuisabel-gif/MemWhale

Runs TAO Data Services gap analysis that compares ground-truth and predicted boxes to find weak images by per-class recall, precision and AP50.

NVIDIA/skills

This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

brevdev/workshop-build-an-agent

Review a CV-CUDA operator's BENCHMARK coverage — drivers, layout axis, baselines, the basic-tier floor, row counts, and coverage statistics.

CVCUDA/CV-CUDA

Classify one failed NemoClaw GitHub Actions job using bounded, redacted logs and optional retained artifacts.

NVIDIA/NemoClaw

Research and draft a response to a GitHub issue or question from an external contributor.

NVIDIA/Megatron-LM

Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full…

cua-lite/cua-lite

Optimize Fused Mixture-of-Experts (MoE) kernels in Triton for NVIDIA and AMD GPUs.

ZJLi2013/awesome-kernel-skills

Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling.

Orchestra-Research/AI-Research-SKILLs

Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.

Orchestra-Research/AI-Research-SKILLs