AI Skills

nemo-rl-session-memory

Manage durable working-session memory for coding agents

nemoclaw-user-guide

Guides human users' AI agents to the NemoClaw docs MCP server

nemotron-customize

Plan, configure

nemotron-policy-generator

Generates BYO custom safety policies

nemotron-retrieval-recipes

Planning, debugging, tuning, evaluating, exporting

nemotron-speech

Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks

nv-generate-ct-rflow

Used for generating synthetic CT volumes and masks

nv-generate-mr

Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr

nv-generate-mr-brain

Used for generating synthetic T1, T2, FLAIR, SWI, or MRA brain MRI volumes

nv-generate-mr-brain-finetune

Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI

nv-generate-vae-finetune

Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists

nv-reason-cxr

Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests

nv-segment-ct

Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes

nv-segment-ct-finetune

Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT

nv-segment-ctmr

Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes

obsidian-canvas-creator

Create Obsidian Canvas files from text content

obsidian-wiki-ingest

Automates ingestion of documents into the Obsidian wiki

omniverse-cad-to-simready

Coordinate the end-to-end CAD/source-asset to SimReady workflow

omniverse-realtime-viewer

Use as the top-level router for Omniverse Realtime Viewer USD app requests

omniverse-usd-performance-tuning

Top-level workflow skill for USD performance diagnosis and optimization

openclaw-history-ingest

Ingest OpenClaw session/history data into Obsidian as distilled knowledge

physical-ai-defect-image-generation

Orchestrate defect image generation with NVIDIA Cosmos AnomalyGen

physical-ai-infrastructure-setup-and-resilient-scaling

Set up, scale, validate, or harden NVIDIA physical AI infrastructure

physical-ai-neural-reconstruction

Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS

physical-ai-video-data-augmentation

Running video data augmentation

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo

rag-blueprint

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

rag-eval

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

rag-perf

Performance benchmarking

skill-card-generator

Use only to generate or update a governance skill card

tag-taxonomy

Apply and maintain the wiki's controlled tag vocabulary

tao-analyze-changenet-rca

Performs deep Root Cause Analysis

tao-convert-dataset-format

Run `tao-daft convert`

tao-finetune-clip

CLIP vision-language model for image-text retrieval, zero-shot classification

tao-finetune-cosmos-embed

Cosmos-Embed1 video-text embedding for text-to-video retrieval

tao-finetune-cosmos-reason

Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL

tao-finetune-huggingface-model

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an

tao-generate-image-grounding

Two-step image grounding pipeline: extracts referring expressions

tao-generate-referring-expressions

Four-step image referring-expression pipeline: turns images plus KITTI

tao-generate-video-reasoning-annotations

Multi-step video annotation pipeline

tao-launch-workflow

The mandatory pre-launch gate and four-verb execution contract

tao-list-capabilities

Answer what the TAO Skill Bank plugin can do by generating the response

tao-mine-aoi-images

Runs the DEFT embed-then-mine workflow for VCN AOI iterations

tao-port-huggingface-model

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit

tao-route-visual-changenet-samples

Routes the weakest VCN samples

tao-run-automl

Run container-backed AutoML / hyperparameter optimization

tao-run-automl-deft-pipeline

Run the canonical NVIDIA AOI three-phase training pipeline

tao-run-deft-aoi

Run the full DEFT AOI improvement loop

tao-run-inference-service

Start, query, and stop a network-specific TAO inference microservice

tao-run-on-brev

Run a TAO training/evaluation/inference container on an NVIDIA Brev GPU instance