NVIDIA AI Platform agent skills, page 6

Top-level workflow skill for USD performance diagnosis and optimization.

NVIDIA/skills

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage.

NVIDIA/skills

Filesystem RAG benchmarks: corpus/, train.json, evaluaterag.py (RAGAS quality).

NVIDIA/skills

How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2dcv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer config, runtime TRT…

NVIDIA/skills

How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-agent), and health checks.

NVIDIA/skills

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).

NVIDIA/skills

Deploy and operate the RTVI-CV-3D microservice as MV3DT (MODE=mv3dt): per-camera DeepStream perception plus BEV Fusion over calibrated cameras.

NVIDIA/skills

Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA.

intel/torch-xpu-ops

Build Holoscan SDK from source via the in-tree ./run script.

NVIDIA/skills

Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit.

NVIDIA/skills

Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree.

NVIDIA/skills

Entry skill for Jetson / IGX BSP customization. An agent skill from NVIDIA/skills.

NVIDIA/skills

Switch the active Jetson target-platform pointer to an existing profile YAML.

NVIDIA/skills

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

NVIDIA/skills

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data.

NVIDIA/skills

Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.

NVIDIA/skills

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

NVIDIA/skills

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.

NVIDIA/skills

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

NVIDIA/skills

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

NVIDIA/skills

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM…

NVIDIA/skills

MoE expert-parallel communication overlap in Megatron Bridge.

NVIDIA/skills

Long-context MoE training guidance for Megatron Bridge. An agent skill from NVIDIA/skills.

NVIDIA/skills

Evidence-gated workflow for MoE performance optimization in Megatron Bridge.

NVIDIA/skills

Practical guidance for training MoE VLMs in Megatron Bridge.

NVIDIA/skills

Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.

NVIDIA/skills

Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon online packing, and CP constraints.

NVIDIA/skills

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

NVIDIA/skills

Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

NVIDIA/skills

A skill your agent uses when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS…

NVIDIA/skills

Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod for one node, Indexed Jobs for multi-node distributed training.

NVIDIA/skills

Expert cuTile programming assistant. An agent skill from NVIDIA/skills.

NVIDIA/skills

Mod or remaster a game with RTX Remix - open and edit projects, swap textures and models.

NVIDIA/skills

One-time session setup and orchestration map for the TAO skill bank.

NVIDIA/skills

Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block.

NVIDIA/skills

Audit, prepare, and deploy PAIDF Orchestration on a Kubernetes GPU cluster - single-GPU H100/L40S hosts, managed Kubernetes, kubeadm, and similar.

NVIDIA/skills

Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

sgl-project/sglang

Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

decolua/9router

Shows how to call NEAR AI Cloud through an OpenAI-compatible API and verify that inference ran in a TEE, using attestation checks and signed chat responses.

internet-court/internet-court-skill

Transcribes audio files into text or subtitles through 9Router's Whisper-compatible endpoint, using models from OpenAI, Groq, Gemini, Deepgram and others.

decolua/9router

Reviews recent code changes and checks if documentation needs updates.

NVlabs/alpasim

Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code).

CVCUDA/CV-CUDA

Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.

dstackai/dstack

Workflow for porting an existing Triton kernel in fla/ops/ to Gluon (triton.experimental.gluon) to gain explicit control over tensor layouts, shared memory, async data movement (cp.async / TMA), MMA…

fla-org/flash-linear-attention

Extract text from local images (PNG, JPEG) with precise coordinates, confidence scores, and stable error handling using the light-ocr CLI.

arcships/light-ocr

Plans memory headroom, works through out-of-memory failures and watches temperature and power during long ML training jobs on NVIDIA DGX Spark.

wshobson/agents

Run a complete protein binder design campaign with NVIDIA Proteina-Complexa: resolve a target structure and hotspots from a name/sequence/PDB, co-design binder sequence+structure with reward-guided…

NVIDIA-BioNeMo/bionemo-agent-toolkit

Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

graphsignal/graphsignal