- Tilegym Improve Cutile Kernel PerfIteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.NVIDIA/skills2,205
- Tilegym Monkey Patch Kernels To TransformersIntegrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.NVIDIA/skills2,205
- Vss Ask VideoUse this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.NVIDIA/skills2,205
- Vss Deploy Dense CaptioningUse this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.NVIDIA/skills2,205
- Vss Deploy Detection Tracking 2dUse this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill.NVIDIA/skills2,205
- Vss Deploy Detection Tracking 3dDeploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video files, and RTSP streams, and chains to `vss-generate-video-calibration` when calibration is missing. Use `vss-deploy-profile` for the full warehouse blueprint and `vss-deploy-detection-tracking-2d` for single-camera 2D detection.NVIDIA/skills2,205
- Vss Deploy ProfileUse to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not for standalone microservices — use the vss-deploy-* skill.NVIDIA/skills2,205
- Vss Deploy Video EmbeddingUse this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown.NVIDIA/skills2,205
- Vss Generate Video CalibrationUse to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC calibration or runtime analytics.NVIDIA/skills2,205
- Vss Generate Video ReportUse this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.NVIDIA/skills2,205
- Vss Manage AlertsUse for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.NVIDIA/skills2,205
- Vss Manage Video Io StorageUse to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.NVIDIA/skills2,205
- Vss Query AnalyticsUse this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.NVIDIA/skills2,205
- Vss Search ArchiveUse this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).NVIDIA/skills2,205
- Vss Setup Behavior AnalyticsUse to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.NVIDIA/skills2,205
- Vss Setup Video Analytics ApiUse to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.NVIDIA/skills2,205
- Vss Summarize VideoUse to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.NVIDIA/skills2,205
- Trt Cpp Runtime QuickstartLoad and run a TensorRT engine (.plan / .engine) from C++ using the TensorRT 11 / 10.x **modern Runtime API**, avoiding the deprecated TRT 8.x binding-index APIs that older guidance still promotes. Use whenever the user asks about loading or running a TensorRT .plan/.engine from C++, even on "minimal example" requests — without this skill the default reply uses deprecated enqueueV2-style code. Also use when the user hits "Engine plan file is generated on an incompatible device", deserializeCudaENVIDIA/trt-samples-for-hackathon-cn1,660
- Trt Onnx QuickstartBuild and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against ONNX Runtime. Use when the user imports a non-LLM model to TensorRT, needs a verified engine from ONNX, hits trtexec "unsupported operator", must verify the engine matches ONNX numerically, debugs a polygraphy parity failure (large max abs diff at FP16), or configures multi-input dynamic shapes. Triggers: convert ONNX to TensorRT, Hugging Face to TensorRT, trtexec onnx, trtexec unsNVIDIA/trt-samples-for-hackathon-cn1,660
- Trt Perf AnalysisValidate and analyze TensorRT performance data from paired layer-info JSON and profile/latency JSON files. Use when asked to inspect TensorRT, TRT, torch-tensorrt, or ONNX-TensorRT perf reports, verify that layer/profile JSON files are valid and from the same model, infer basic model information, find likely fusion or latency optimization opportunities, and produce a concise Markdown performance report or structured JSON data.NVIDIA/trt-samples-for-hackathon-cn1,660
- Trt Strong Typing MigrationMigrate a TensorRT build from weak typing (deprecated 10.12, removed 11.0) to strong typing — across Python INetworkDefinition builders, the trtexec CLI, and C++ builder code. Use when a TRT 11 upgrade breaks a weakly-typed build. Triggers: weakly typed to strongly typed, kSTRONGLY_TYPED, weak typing deprecated, kFP16/kINT8 removed, setPrecision rejected, setComputePrecision deprecated, do I still need --stronglyTyped, how to add the kSTRONGLY_TYPED flag, ModelOpt autocast, INT8 on TRT 11. NOT fNVIDIA/trt-samples-for-hackathon-cn1,660
- Trt Torch QuickstartCompile a PyTorch model to a TensorRT engine via Torch-TensorRT — AOT or JIT — under the new strong-typing default. Use when the user compiles PyTorch to TensorRT without ONNX, hits "enabled_precisions should not be used when use_explicit_typing=True", sees Dynamo graph breaks or PyTorch fallback, debugs ABI errors at import torch_tensorrt, or needs the compatible torch / torch_tensorrt / tensorrt-cu13 version pins for TensorRT 11. Triggers: torch_tensorrt, torch_tensorrt.dynamo.compile, torch.cNVIDIA/trt-samples-for-hackathon-cn1,660
- Cudaq GuideCUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.NVIDIA/cuda-quantum1,082
- Analysis MethodsTeaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.NVIDIA/dgx-spark-playbooks1,043
- Case SummaryPrepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.NVIDIA/dgx-spark-playbooks1,043
- Clinical DelegationHow to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.NVIDIA/dgx-spark-playbooks1,043
- Clinical KnowledgeTeaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal values and identify care gaps.NVIDIA/dgx-spark-playbooks1,043
- Cohort CompareAnalyze a cohort of patients from FHIR endpoints to find care gaps and patterns. Use when asked to compare patients, find quality gaps, or analyze a population.NVIDIA/dgx-spark-playbooks1,043
- Dgx DiagnoseDiagnose common DGX Station GB300 issues — CUDA crashes, wrong-GPU targeting, vLLM/SGLang container bugs, MIG state problems, NVLink/Fabric Manager errors, X/Vulkan failures, HuggingFace auth, and port conflicts. Use when the user reports a GPU error, inference server crash, MIG problem, or any unexplained DGX Station failure.NVIDIA/dgx-spark-playbooks1,043
- Fhir BasicsTeaches agents how FHIR R4 APIs work, what resources are available, how to query them with search parameters, and how to correctly parse all response formats including component Observations.NVIDIA/dgx-spark-playbooks1,043
- Mig ConfigureConfigure NVIDIA MIG (Multi-Instance GPU) partitions on the DGX Station GB300, including enabling MIG mode, choosing a profile layout, creating instances, and retrieving MIG UUIDs. Use when the user asks to partition the GB300, set up MIG, run multiple models in isolation on one GPU, or reconfigure existing MIG instances.NVIDIA/dgx-spark-playbooks1,043
- Molecular VizVisualize drug-protein complexes using build_viewer.py, PubChem, and OpenFold3 NIM. Use when asked to show a molecular structure, drug target, or protein visualization.NVIDIA/dgx-spark-playbooks1,043
- Sglang SetupDeploy an SGLang inference server on an NVIDIA DGX Station GB300 with the cu130 container, RadixAttention prefix caching, and structured JSON output support. Use when the user asks to serve a model with SGLang, start an SGLang endpoint, or needs structured-output inference on DGX Station.NVIDIA/dgx-spark-playbooks1,043
- Vllm SetupDeploy a vLLM inference server on an NVIDIA DGX Station GB300 with validated container, GPU targeting, and tuning parameters. Use when the user asks to serve a model with vLLM, start a vLLM endpoint, or set up OpenAI-compatible inference on DGX Station.NVIDIA/dgx-spark-playbooks1,043
- Developer Release RebasePrepare a new minor alpha release of Earth2Studio by rebasing the release candidate branch onto main, bumping the version, updating the changelog, updating the README latest-news highlights, stripping example version tags, and pushing for PR. Use when releasing, cutting a release, preparing a release branch, rebasing a release, or bumping the version for a new development cycle.NVIDIA/earth2studio1,015
- Earth2studio Create DatasourceCreate 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.NVIDIA/earth2studio1,015
- Earth2studio Create DiagnosticCreate 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.NVIDIA/earth2studio1,015
- Earth2studio Create PrognosticCreate Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.NVIDIA/earth2studio1,015
- Earth2studio Data FetchFetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.NVIDIA/earth2studio1,015
- Earth2studio Deterministic ForecastBuild deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.NVIDIA/earth2studio1,015
- Earth2studio DiscoverFind Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.NVIDIA/earth2studio1,015
- Earth2studio InstallGuide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.NVIDIA/earth2studio1,015
- Udf BenchmarkAssists with benchmarking and profiling the performance of an Apache Spark UDF on the GPU. This is step 3 of 3 in the UDF conversion workflow (udf-gen-test -> udf-convert-to-* -> udf-benchmark). Use this skill when you have a CPU UDF and a RapidsUDF or SQL implementation, and need to benchmark the performance of the CPU UDF against the GPU implementation.NVIDIA/cudf-spark985
- Udf Convert To CudaAssists with converting a non-aggregating Apache Spark UDF to a native CUDA RapidsUDF using JNI and libcudf. This is step 2 of 3 in the UDF conversion workflow (udf-gen-test -> udf-convert-to-cuda -> udf-benchmark). Use this skill when you have a CPU UDF with a unit test and need to convert it to a native CUDA implementation. Prefer udf-convert-to-cudf unless a CUDA implementation is necessary for performance or correctness, or if requested by the user.NVIDIA/cudf-spark985
- Udf Convert To CudfAssists with converting an Apache Spark UDF to a GPU-accelerated RapidsUDF using cuDF Java APIs. This is step 2 of 3 in the UDF conversion workflow (udf-gen-test -> udf-convert-to-cudf -> udf-benchmark). Use this skill when you have a CPU UDF with a unit test and need to convert it to a RapidsUDF.NVIDIA/cudf-spark985
- Udf Convert To SqlAssists with converting an Apache Spark UDF to a functionally equivalent Spark SQL expression. This is step 2 of 3 in the UDF conversion workflow (udf-gen-test -> udf-convert-to-sql -> udf-benchmark). Use this skill when you have a CPU UDF with a unit test and need to convert it to SQL for GPU acceleration.NVIDIA/cudf-spark985
- Udf Gen TestAssists with generating a unit test for an Apache Spark UDF. This is step 1 of 3 in the UDF conversion workflow (udf-gen-test -> udf-convert-to-* -> udf-benchmark). Use this skill when you have a CPU UDF and need to create a unit test for the UDF before converting it into a GPU-compatible implementation.NVIDIA/cudf-spark985
- Udf Judge ConversionReviews generated UDF tests and GPU/SQL implementations for robustness, anti-cheating, and GPU execution integrity. Use when the user requests a judge/review-agent pass, or when manually reviewing a completed conversion.NVIDIA/cudf-spark985
- Udf Optimize CudfIteratively optimizes a cuDF RapidsUDF implementation for GPU performance. Use after testing and benchmarking with udf-benchmark. Runs a loop of profiling, optimizing, testing, and benchmarking until performance converges or the iteration budget is exhausted.NVIDIA/cudf-spark985
- Cuopt DeveloperModify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.NVIDIA/cuopt961
- Cuopt InstallInstall cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.NVIDIA/cuopt961
- Cuopt Multi Objective ExplorationTrace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).NVIDIA/cuopt961
- Cuopt Numerical Optimization ApiLP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.NVIDIA/cuopt961
- Cuopt Numerical Optimization FormulationLP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.NVIDIA/cuopt961
- Cuopt Routing Api PythonVehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.NVIDIA/cuopt961
- Cuopt Server Api PythoncuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.NVIDIA/cuopt961
- Cuopt Skill EvolutionAfter solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.NVIDIA/cuopt961
- Cuopt User RulesBase rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.NVIDIA/cuopt961
- Autofl NvflareHelp coding agents work on an NVFlare-based Auto-FL harness that follows an autoresearch-style loop. Use when the user wants to create, edit, debug, or extend program.md, task folders such as tasks/cifar10/ and tasks/vlm_med/, task-local job.py, client.py, model.py, shared custom_aggregators.py, mutation policies, results.tsv logging, or coding-agent prompts for a bounded federated-learning research loop. This skill is specifically for NVFlare harness work where the Client API loop, DIFF upload NVIDIA/NVFlare944
- Autofl Nvflare ReportGenerate and commit a markdown report after an Auto-FL NVFlare autoresearch experiment has been manually stopped. Use when the user asks to summarize a stopped campaign, report achieved improvements, explain implemented literature-derived ideas and sources, refresh progress plots, capture pasted agent model/effort/cost context when available, or commit the final report and progress plot to the current experiment branch.NVIDIA/NVFlare944