Official Agent Skills
Skills published by verified organisations. Every one is reviewed before listing, and the publisher's identity is checked, not just claimed.
-
nvidia Bundle Dicom Metadata Extract 2Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
2.2k - nvidia Bundle Dicom Series Preflight 2
Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.
2.2k - nvidia Bundle Dicom Series To Volume 2
Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.
2.2k - nvidia Bundle Holoscan Install Conda 2
Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.
2.2k - nvidia Bundle Holoscan Install Wheel 2
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
2.2k - nvidia Bundle Nv Segment Ct Finetune 2
Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with optional MONAI-native MLflow tracking and checkpoint evidence. Uses softmax for predefined, mutually exclusive classes; keeps the standard workflow when point prompts or runtime-variable classes are needed. Not for clinical validation.
2.2k - nvidia Bundle Cuopt Server API Python 2
cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
2.2k - nvidia Bundle Earth2studio Data Fetch 2
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
2.2k - nvidia Bundle Holoscan Install Debian 2
Install Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for Python.
2.2k - nvidia Bundle Holoscan Install Source 2
Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.
2.2k - nvidia Bundle Cuopt Routing API Python 2
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
2.2k - nvidia Bundle Nv Generate Vae Finetune 2
Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.
2.2k - nvidia Bundle Amc Run Video Calibration 2
Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`.
2.2k - nvidia Bundle Nemotron Policy Generator 2
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.
2.2k - nvidia Bundle Amc Run Sample Calibration 2
Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
2.2k - nvidia Bundle Holoscan Install Container 2
Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.
2.2k - nvidia Bundle Nemotron Retrieval Recipes 2
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
2.2k - nvidia Bundle Deepstream Profile Pipeline 2
Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.
2.2k - nvidia Bundle Vss Manage Video Io Storage 2
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.
2.2k - nvidia Bundle Deepstream Generate Pipeline 2
Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).
2.2k - nvidia Bundle Mcore Linting And Formatting 2
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
2.2k - nvidia Bundle Vss Setup Behavior Analytics 2
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
2.2k - nvidia Bundle Nv Generate Mr Brain Finetune 2
Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist. Not for clinical or production data approval.
2.2k - nvidia Bundle Vss Setup Video Analytics API 2
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
2.2k - nvidia Bundle Cupynumeric Parallel Data Load 2
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.
2.2k - nvidia Bundle Deepstream Import Vision Model 2
Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
2.2k - nvidia Bundle Earth2studio Create Datasource 2
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
2.2k - nvidia Bundle Earth2studio Create Diagnostic 2
Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and generative or diffusion diagnostics. Do NOT use for prognostic time-stepping models, data sources, or installation.
2.2k - nvidia Bundle Earth2studio Create Prognostic 2
Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.
2.2k - nvidia Bundle Nemo Automodel Launcher Config 2
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
2.2k - nvidia Bundle Cupynumeric Migration Readiness 2
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
2.2k - nvidia Bundle Nemo Mbridge Perf Memory Tuning 2
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 fixes.
2.2k - nvidia Bundle Cuopt Numerical Optimization API 2
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
2.2k - nvidia Bundle Digital Health Clinical Asr Eval 2
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).
2.2k - nvidia Bundle Nemo Mbridge Mlm Bridge Training 2
Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.
2.2k - nvidia Bundle Cuopt Multi Objective Exploration 2
Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).
2.2k