NVIDIA AI Platform agent skills, page 7

Optimize AlpaSim Slurm topology throughput using persistent local Prometheus/Grafana telemetry and run artifacts.

NVlabs/alpasim

Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.

wshobson/agents

Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.

BBuf/AI-Infra-Auto-Driven-SKILLS

Drive NVIDIA Nsight Graphics 2026.1+ from the command line for GPU performance analysis, frame capture, frame trace inspection, draw-call inspection, NVTX/D3DPERF stage timing, replay metadata…

Luna5ama/Alpha-Piscium

Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary.

CVCUDA/CV-CUDA

A skill your agent uses when asked to run deep research or Deep Researcher Agent research through a reachable NVIDIA Deep Researcher Agent Blueprint backend.

NVIDIA-AI-Blueprints/deep-researcher-agent

Add agent-ready vision capabilities — dense captioning, detection, search, alerting, summarization — to an agent or application through a customizable, self-contained vision stack built on the…

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

Route NVIDIA Parabricks pbrun tools, assess GPU/runtime readiness, and provide version-aware command guidance for FASTQ/BAM processing, RNA-seq, variant calling, BAM QC, and GVCF workflows.

NVIDIA-BioNeMo/bionemo-agent-toolkit

Add a new step under src/nemotron/steps/<category/<stepid/ — manifest (step.toml), runner glue, configs, and per-step README.md.

NVIDIA-NeMo/Nemotron

Separate a person, product or hand from the background in a video, on the user's own computer with SAM 2.

Barty-Bart/motion-graphics

A skill your agent uses when the user wants to anonymize a text dataset, redact PII, de-identify free-text data, or rewrite text to remove sensitive or inferable identifying information.

NVIDIA-NeMo/Anonymizer

Integrates a hosted API or local/open-weight model end-to-end across OpenTryOn (adapter, CLI registry, MCP, docs) and TryOn Studio (catalog, Connect keys, planner).

tryonlabs/opentryon

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

EGalahad/sim2real

Builds a NeMo Gym (NVIDIA) variant of an RL environment. An agent skill from adithya-s-k/FineEnvs.

adithya-s-k/FineEnvs

This skill should be used when the user wants to set up, install, deploy, bootstrap, or "spin up" the Build-an-Agent workshop (a.k.a.

brevdev/workshop-build-an-agent

Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format.

dstackai/dstack

Prepare, install and commission NVIDIA GPU hosts for Vast.ai using host-specific safety gates, XFS storage checks, cgroup/runtime testing and optional VM qualification.

jjziets/vasttools

Review a CV-CUDA operator end-to-end (support / test / bench / docs coverage).

CVCUDA/CV-CUDA

Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters.

NVIDIA-NeMo/Nemotron

A skill your agent uses for GPU-accelerated machine learning on tabular data using NVIDIA cuML.

wahyudesu/Fastapi-AI-Production-Template

Create safe, privacy-preserving Windows 11 C-drive cleanup, storage migration, cache relocation, package-manager policy, and maintenance plans.

Nongfsq/win11-storage-governance-kit

YOLO 2026 — state-of-the-art real-time object detection. An agent skill from SharpAI/DeepCamera.

SharpAI/DeepCamera

A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

sgl-project/sglang

Generate Triton Runner ttir, ttgir, llir, ptx, cubin, and metadata artifacts inside examples/runner/vX.Y.Z for the active Triton version and the current machine's GPU capability.

toyaix/triton-runner

Query and write durable debugging memory recorded by MemoryWhale.

wuisabel-gif/MemWhale

Write, debug, and optimize CUTLASS, CuTe, and CuTeDSL GPU kernels from local upstream source, examples, and headers.

slowlyC/agent-gpu-skills

Install and run erm, the local CLI that removes filler words / disfluencies (um, uh, er, erm, ah, hmm, mhm, mm, uh-huh and elongations) from spoken-audio recordings.

dougcalobrisi/erm

Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.

brevdev/workshop-build-an-agent

Optimizes and serves LLMs on NVIDIA GPUs with TensorRT-LLM, covering quantization, in-flight batching, multi-GPU parallelism and the trtllm-serve command.

Orchestra-Research/AI-Research-SKILLs

Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment.

NVIDIA-NeMo/Nemotron

基于 helpfile 工程经验，协助 agent 配置 CV 主机和边缘设备环境、编译视觉与推理依赖、接入摄像头视频并打包部署服务。适用于 Ubuntu、CentOS、Windows、macOS、Jetson、树莓派和 RK3399 的 CV 工程实施与故障排查，以及相关移动端配套工具；模型训练和纯算法设计不属于本技能主线。

LMIXR/CV_Deployment_skill

Verify a CV-CUDA optimization campaign's deterministic definition-of-done and concise versioned MR summary per .agents/guidance/OPTIMIZATIONGUIDELINES.md.

CVCUDA/CV-CUDA

Install KimodoUnityBridge and route Unity animation work through its cooperating capability tools.

OneYoungMean/KimodoUnityBridge

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.

mydisha/keirouter

GGUF format and llama.cpp quantization for efficient CPU/GPU inference.

Orchestra-Research/AI-Research-SKILLs

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.

Orchestra-Research/AI-Research-SKILLs

Interactively build, push or load, and deploy an airunway component (controller or any provider) to the cluster

ai-runway/airunway

Write, debug, and optimize TileLang kernels from local upstream language, JIT, autotuning, profiling, compiler, test, and example source.

slowlyC/agent-gpu-skills

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

amd/skills

Reference desk for NVIDIA Nemotron 3 Super — architecture, training data, recipes (pretrain/SFT/RL/eval/quantization), and deployment notes.

NVIDIA-NeMo/Nemotron

dstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.

dstackai/dstack

Choose and run ACU-only, adaptive PPU in-kernel timeline, or optional bounded joint analysis for a PPU kernel.

alibaba/atrex-kernel-agent

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

Write, debug, and optimize Triton and Gluon GPU kernels from local upstream tutorials, production kernels, language definitions, and compiler source.

slowlyC/agent-gpu-skills

Compare a Primus backend against an upstream repository or reference, verify git state, dependencies, directory changes, and integration coupling, then generate comparison reports, dashboard…

AMD-AGI/Primus

Add a new CV-CUDA operator end-to-end per .agents/guidance/MAKEOPGUIDELINES.md, with a deterministically-enforced definition-of-done.

CVCUDA/CV-CUDA