kumo-model-persistencePublish and reload Kumo models through the Snowflake registry, reconstruct compatible scoring inputs, and retain or retrieve run diagnostics and output files through a Snowflake stage. Use for saved-model scoring and artifact retention without retraining by…kumo-training-diagnosticsEvaluate an existing Kumo training run in a Python notebook using aggregate metrics, trial results, learning curves, refit evidence, and training progress. Use for model-quality questions or training diagnostics; inspect existing results without automatically…kumo-custom-populationsTrain with caller-supplied labels, weights and splits or score exact entity/anchor rows through Snowflake source tables using the local Kumo API. Use when generated populations do not represent the requested rows.kumo-data-scienceUse for KumoAI graphs and predictive models on relational data in a warehouse, an object store or local files: inspect, visualize or export a graph's schema and relationships; train a model, score data with a trained one, explain its predictions, diagnose its…kumo-model-explanationsInspect and interpret gradient attribution (including requests called radiant attribution), column analysis and sampled explanation subgraphs from a Kumo model trained in a Python notebook. Locate the correct run's explanation artifacts, explain feature…kumo-graph-visualizationProvide graph visuals in Kumo notebooks and SDK scripts, display or export relationships on request, and inspect Markdown schemas during model iteration.kumoai-referenceReference for translating a validated ML request into KumoAI graph configuration, PQL (predictive query language), and Kumo Predict SDK code. Normally loaded by the kumo-data-science skill after its intake checks pass, rather than invoked directly. Triggers:…kumo-model-tuningConfigure a Kumo model plan for a user-defined task, including encoders, run mode, bounded experiments, sampling, optimization, architecture, metrics and refits. Preserve target and evaluation constraints and use existing diagnostics for comparisons.
مستكشف المستودعات
NVIDIA · المستودعات و skills الممثلة - الصفحة ٢
عرض على مستوى المستودعات لـ ١٬٣٣١ skills مجمعة عبر ١١٧ مستودعات GitHub.
sop-data-augmentationUse when the user wants to run data augmentation on an annotated dataset, configure augmentation parameters, check augmentation status, or understand what each QA augmentation type does (BCQ, MCQ, GQA, DMCQ, DSQA, ENQA, WMCQ)sop-by-action-evalUse when running by-action VLM evaluation (per-action-clip inference + accuracy metrics) against the BP evaluation-ms HTTP API. Invoked as /sop-by-action-eval <inputs.yaml> [natural language parameter overrides]sop-e2e-inferenceUse when running the e2e evaluation pipeline (temporal segmentation + action recognition + accuracy) against the BP evaluation-ms HTTP API. Invoked as /sop-e2e-inference <inputs.yaml> [natural language parameter overrides]sop-ft-orchestrateAutonomous end-to-end orchestrator for SOP fine-tuning. Runs the full Import → Augment → DDM Train → VLM Train → Evaluate → RCA loop. Interprets RCA findings across DDM, VLM and augment axes, applies config fixes autonomously, and iterates until success…sop-rcaRoot cause analysis for SOP monitoring pipeline failures. Analyzes end-to-end evaluation logs, DDM temporal segmentation, VLM action recognition, training data, and fine-tuning configs to identify failure patterns and produce an evidence-driven RCA report…vss-sop-buildBuild a custom VSS SOP blueprint from the VSS 3.1 base, then deploy and test in a loop until fully operational. Use when asked to create the SOP blueprint structure, customize VSS compose for SOP, configure SOP services, set up the VSS agent for SOP, or…vss-sop-deployBuild the DS-SOP Docker image and deploy the VSS SOP blueprint end-to-end. Use when asked to deploy SOP, build DS SOP, install SOP, set up the SOP pipeline, verify SOP models, start the SOP blueprint, simulate RTSP for SOP, run the SOP API test, or tear down…deepstream-sopUse this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary…
batch-and-test-mergequeue-prsBatch fully approved Megatron-LM PRs that are actual merge-queue entries, approve their batch CI gate, and validate with Run Merge-Queue jobs. Squash-merge the originals after Nemo_CICD_Test succeeds and queue membership and approvals are rechecked. Excludes…mcore-testingTest system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity. Use when adding or running a unit or functional test; understanding the test layout; writing a…pr-reviewReview rubric for the `/review` pull-request command. The formal reviewer reads it as a file and it is not an interactive skill — do not load it to answer questions or to review code outside that command.nightly-syncDomain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues. Use when working on the nightly sync PR; investigating a nightly sync failure; resolving merge conflicts between main…mcore-cicdCI/CD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a pull-request/BRANCH ref — always dry-run and verify the destination first; never run against shared or…mcore-determinism-debugRoot-cause method when two Megatron runs that should be bit-identical diverge: fingerprint every op, diff the two traces, first mismatch is the culprit. Use when two identical training runs give different loss; a run is bit-exact at N nodes but not 2N; you…mcore-build-and-dependencyContainer-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and updating uv.lock. Use when adding, removing, or updating a dependency; editing pyproject.toml or…mcore-bump-base-imageBump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker/.ngc_version.dev` and GitLab CI in `.gitlab/stages/01.build.yml`), the post-bump CI loop (re-run functional tests,…
reproduce-ciReproduce cudf CI failures locally. Provide a GitHub Actions job URL to auto-discover parameters, or supply the container image and CI script directly.update-cudf-polars-polars-tests-selectionRegenerates the versioned GPU-executing test selection for the upstream Polars suite. Use after a Polars upgrade, when the minimum supported Polars version is raised, or when the nightly cudf-polars run-list audit reports drift.update-pandas-testingUse when updating pandas for cudf.pandas testing in CI, or when updating the skip and expected-failure lists in python/cudf/cudf/pandas/scripts/pandas-testing-plugin.pyupgrade-polarsUse when raising the supported Polars version range for cudf-polars (for example 2.0 to 2.1). Covers the version pins, adapting the translator to new IR/expression changes, the cudf-polars unit tests with 100% coverage, the upstream polars test suite…contribute-cudfUse this skill before writing or changing code or tests in the cudf repository, and again before opening or updating a pull request, to reuse existing code and keep the change small.build-test-cudf-javaBuild and test cudf Java bindings (cudf-java) inside a cudf devcontainer. Use when the user asks to build, compile, or test Java code in the cudf repository.retarget-prRetarget a cuDF PR to a different base branch (e.g. main to release/YY.MM) by rebasing its commits and changing the PR base. Use when asked to retarget a cuDF PR; not for plain rebases onto the same base.review-udf-mlir-migrationReviews and explains cuDF UDF migration changes from numba-cuda to numba-cuda-mlir from first principles. Use for PRs or code touching cudf.core.udf, mlir_backend, MaskedType, NAType, mlir_string, string UDFs, NRT, row/groupby/rolling apply kernels,…
dgx-stationInspect and guide NVIDIA DGX Station GB300 development using the local dgx-assist CLI and pinned NVIDIA playbooks. Use for general Station platform questions, Software 1.0 or 2.0 compatibility, GB300 or RTX GPU selection, UUID ordering, mixed ATS/HMM…dgx-station-diagnoseRun and interpret the complete read-only dgx-assist diagnostic suite for NVIDIA DGX Station GB300, correlate findings with pinned NVIDIA playbooks, export a redacted support bundle, and apply one separately approved allowlisted fix. Use when the user reports…dgx-station-inferenceResolve, tune, preflight, launch, verify, inspect, and stop exact-model inference on NVIDIA DGX Station through dgx-assist. Use for vLLM or SGLang container selection, NGC versus upstream, GPU memory utilization, CPU or KV offload, HBM fit, KV-cache sizing,…dgx-station-migInspect NVIDIA DGX Station GB300 MIG state and installed-driver profiles, create a digest-bound layout plan, disclose disruption and restoration, and apply an approved still-valid plan. Use when the user asks to enable, disable, partition, reconfigure,…analysis-methodsTeaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.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.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.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.
edge-llm-accuracy-debuggingLocalize a TensorRT Edge-LLM accuracy mismatch against the model provider's PyTorch reference after few-layer validation identifies a failing component or layer.edge-llm-add-modelImplement TensorRT Edge-LLM support for a new Hugging Face checkpoint or model family. Use for a new `model_type`, architecture, text/vision/audio/action component, checkpoint tensor layout, speculative draft, model-specific custom operation, or runtime…edge-llm-benchmark-accuracyMeasure dataset accuracy (MMLU and other NeMo Evaluator benchmarks) of a TensorRT Edge-LLM deployment through its OpenAI-compatible chat endpoint with NeMo Evaluator. Use for "benchmark accuracy", "run MMLU/GSM8K/IFEval on this checkpoint", comparing a…edge-llm-benchmark-performanceBenchmark TensorRT Edge-LLM serving performance (TTFT, inter-token latency, request latency, output throughput, concurrency scaling) through the OpenAI-compatible server with AIPerf. Use for "benchmark performance", "measure TTFT/ITL/tokens per second",…edge-llm-convert-modelConvert and run one supported Hugging Face checkpoint with TensorRT Edge-LLM. Use for quantization, checkpoint-to-ONNX export, `llm_build`/`visual_build`/`audio_build`, C++ `llm_inference`, the experimental checkpoint-direct `trtedge build`, engine profile…edge-llm-cpp-testWrite or change a C++ test under unittests/. Covers the BDD comment contract, mutation testing, and the substitute engines that drive LLMInferenceRuntime without a serialized engine. Apply whenever adding, migrating, or repairing a GTest case in this…edge-llm-cutedsl-kernelAdd or change a TensorRT Edge-LLM CuTe DSL kernel end to end, from the Python kernel source through the KERNEL_VARIANTS registry in kernelSrcs/build_cutedsl.py, GPU-free AOT artifact generation (native or AArch64 cross build), the metadata-driven…edge-llm-documentationWrite, edit, or review TensorRT Edge-LLM documentation using the Google developer documentation style guide. Apply to READMEs, tutorials, how-to guides, conceptual and design documents, API and CLI references, and release notes; not ordinary code changes or…
developer-bump-versionBump the Earth2Studio version on main to start a new development cycle. This unblocks commits on main after a release branch has been merged. Performs a CHANGELOG update (new blank section) and a hatch version bump. Use when main already has the release merge…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…earth2studio-couple-modelsUse when running two or more Earth2Studio models together so one feeds another (e.g. StormScope GOES to MRMS, atmosphere and ocean at different cadences, a weather model driving an impact model): wires components and connectors into a CoupledRunner, checks…earth2studio-create-assimilationCreate, migrate, or review Earth2Studio data assimilation model wrappers and their unit tests, including independent analyses and explicit-state rollouts with DataFrame observations. Use for DA test alignment; not for fetching data or pure…earth2studio-create-datasourceCreate and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Use for local Python projects or contributions to Earth2Studio. Do NOT use for fetching data with existing sources,…earth2studio-create-diagnosticUse when creating or migrating Earth2Studio diagnostic model wrappers, including derived quantities, packaged models, generative diagnostics, and multi-input or multi-output transformations. Not for prognostic forecasts, data sources, or installation.earth2studio-create-prognosticUse when creating or migrating Earth2Studio prognostic time-stepping model wrappers, including explicit-state, forced, coupled, stochastic and multi-output forecasts. Not for diagnostic models, data sources, or installation.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.
kit-app-streaming-debugUse when investigating Kit app livestream performance bottlenecks, WebRTC/native StreamSDK lag, freezes, dropped frames, browser WebRTC stats, copy fence timeouts, NVST_R_BUSY, disconnects, or resolution mismatch warnings in omni.kit.livestream.nvtx-pythonProfile Python functions with NVTX in non-Kit environments (Isaac Lab 3.0+ standalone, any Python app without Carbonite). Uses a bundled PYTHONPATH-scoped sitecustomize.py with sys.setprofile hook, NVTX push/pop ranges, module include/exclude filtering, and…perf-tuningResolve common Kit/Isaac Sim/Isaac Lab performance issues using specific settings and configuration changes. Covers PresentFrame stalls, resolveSamplerFeedback, headless mode, multi-GPU tradeoffs, DLSS/DLSS-G, PhysX tuning, RTX presets…install-profilersInstall profiling tools for Isaac Sim / Isaac Lab / Kit-based applications. Covers Nsight Systems (`nsys` CLI), `sqlite3`, Tracy `csvexport`, canonical Tracy `capture`/`capture-release`, and `update` for memory strip tests, with optional…nsys-analyzeAnalyze profiling data from Kit-based apps. Covers Omniverse-specific NVTX zone interpretation, phase detection using sqlite3, Tracy Statistics/Range Limit analysis, csvexport fallback queries, and two-version comparison methodology. Use after capturing…profiling-apiAdd profiling zones, metrics, and annotations to Kit-based C++ and Python code. Covers Carbonite macros (CARB_PROFILE_ZONE, CARB_PROFILE_FUNCTION, GPU zones), Python profiler API (decorators, begin/end), profiler masks, channels, Tracy plot data, event…profilingCapture performance traces using CPU ChromeTrace, Tracy, and Nsight Systems/NVTX for Kit-based applications (Isaac Sim, Isaac Lab, Kit SDK). Covers COLD/WARM/TRACY measurement separation, canonical Tracy capture sequence, last-resort force-kill handling, nsys…tracy-memoryProfile CPU and GPU memory allocations using Tracy in Kit-based applications after Tracy capture tooling is installed. Covers LD_PRELOAD setup for liballocwrapper.so, Kit memory-channel flags, capture binary isolation (unset LD_PRELOAD), tracy-update…
amc-run-auto-calibrationRun or tune NVIDIA AutoMagicCalib from DeepStream using sample data, local MP4s, or RTSP streams. Use for AMC setup and calibration artifacts. Do not use for general calibration theory, target-based stereo calibration, or runtime analytics.deepstream-audit-configUse only when auditing or sanity-checking a supplied or pre-existing deepstream-app/deepstream-test5 config, performing an explicitly requested independent post-generation audit, or reviewing a supplied design/code change that affects DeepStream config…deepstream-devNVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.deepstream-import-vision-modelImport detection, classification, segmentation, pose, and depth models into DeepStream with task routing and evidence-gated validation.deepstream-inspect-stackUse when diagnosing NVIDIA DeepStream SDK installation, version compatibility, container tag, JetPack, CUDA, TensorRT, driver, GPU/Jetson, WSL2, pyservicemaker, or pyds issues; also use to reroute DeepStream pipeline-building or model-import requests to…deepstream-setup-on-wslSet up and verify NVIDIA DeepStream in Docker inside WSL2 on a local or remote Windows machine. Use when a user wants to install WSL2, Ubuntu, Docker, NVIDIA Container Toolkit, and a requested DeepStream image; validate a supported WDDM workstation GPU; or…rtvi-cv-scaffold-vss-serviceScaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw. The shipped scaffold script is a YOLO26 reference implementation (ONNX, labels, custom parser required). Use when building a new perception…inference-builderGenerate deployable Vision AI pipelines with high-performance video and streaming capabilities on NVIDIA GPUs. Activate when users want to: create GPU-accelerated inference microservices or standalone apps for vision, video, or streaming workloads; write or…
submit-github-prUse when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR…optimize-model-precisionEvaluate supported precision, quantization, or selected FP32-layer choices for one TensorRT-Model-Connect family with matched correctness and timing.profile-modelMeasure one TensorRT-Model-Connect model through its public Task API or run a checked-in performance-matrix entry with comparable evidence.review-trtmc-prReview a TensorRT-Model-Connect GitHub PR or local contributor branch against the current post-#1093 model-family isolation architecture, repository rules, behavioral correctness, third-party dependency and license obligations, and exact-head validation…pr-babysitterUse when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.debug-trt-mismatchDiagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.doc-syncAudit and update TensorRT-Model-Connect documentation when code, public APIs, family ownership, commands, or model support have changed.fp16-trt-networkImplement or review FP16 and BF16 behavior in one family-owned, strongly typed TensorRT network without changing unrelated families.
nat-installationUse when installing or configuring NVIDIA NeMo Agent Toolkit, verifying the `nat` CLI, setting up optional extras, or creating a first hello-world workflow.nat-evaluationUse when designing, configuring, running, or troubleshooting NeMo Agent Toolkit evaluations, datasets, evaluator selection, ATIF surfaces, quality gates, custom evaluators, and `nat eval`.nat-optimizationUse when configuring or running NeMo Agent Toolkit optimization with `nat optimize`, including Optuna parameter tuning, prompt evolution, optimizer sizing, output interpretation, and optimizer datasets.nat-workflow-creationUse when creating, editing, validating, running, or troubleshooting NeMo Agent Toolkit workflow YAML, component discovery, LLM configuration, and common `nat` CLI commands.nat-user-rulesUse first for general NVIDIA NeMo Agent Toolkit coding-agent behavior, task routing, naming conventions, component discovery rules, and cross-skill guidance.nat-telemetryUse when adding, configuring, or troubleshooting NeMo Agent Toolkit logging, tracing, telemetry exporters, OpenTelemetry, Langfuse, LangSmith, Weave, Phoenix, profiling, or observability provider integrations.skill-evolutionUse before creating, editing, or deciding whether to update any AI coding agent skill in this repository, including corrections to existing skill behavior, references, or routing.nat-agent-configurationUse when selecting, configuring, composing, or troubleshooting NeMo Agent Toolkit agents and control-flow components, including ReAct, tool-calling, ReWOO, reasoning, router, sequential, parallel, and sub-agent patterns.
serve-modelUse when serving a cached model on one GPU with vLLM, checking a local completion endpoint, or diagnosing startup and inference failures in the single-node quickstart.manage-model-cacheUse when preparing a shared Hugging Face model cache for Slurm or Kubernetes, pinning downloaded model revisions, validating offline model files, or diagnosing missing snapshots and cache permissions.finetune-modelUse when checking whether one DeepOps Slurm GPU node is prepared for fine-tuning, diagnosing missing cached training inputs or container prerequisites, or distinguishing readiness from actual training success.deploy-airgappedPrepare mirrors and transfer artifacts, configure DeepOps, deploy Slurm or Kubernetes GPU clusters without Internet access, and validate them with machine-readable gates. Use for disconnected, restricted-egress, offline, or air-gapped DeepOps installations…deploy-runai-kaiUse when adding or removing the optional KAI Scheduler or Run:ai platform on a DeepOps Kubernetes GPU cluster, enabling fractional-GPU scheduling, or diagnosing KAI/Run:ai install or scheduling failures.model-workflowsUse when choosing a DeepOps model workflow, combining shared model caching with single-node serving, or determining whether a fine-tuning or multi-node request has a supported procedure.validate-gpu-clusterCheck whether a DeepOps-deployed Slurm or Kubernetes GPU cluster is healthy and report a machine-readable verdict. Use for health checks, post-deploy verification, "is the cluster working?" questions, and after any node or driver change.provision-with-maasProvision or reinstall bare-metal servers and test VMs through Canonical MAAS, map deployed machines into DeepOps Ansible inventory with MAAS tags, validate access, or release them safely. Use when operating DeepOps with a MAAS-owned machine lifecycle.