nemo-clinical-data-designerUse when generating synthetic tabular datasets via Data Designer — sampler columns, LLM columns, custom generators. Not for ASR audio.riva-nim-setupUse when getting started with NVIDIA Riva Speech NIMs: NGC access, Docker login for nvcr.io, NVIDIA Container Toolkit, GPU verification, Riva Python client.riva-ttsUse when the user wants to deploy, run, or test a TTS (speech-synthesis) Riva NIM — cloud-hosted (build.nvidia.com) or self-hosted Magpie / voice cloning.riva-asr-customUse when the user wants to deploy a custom-trained ASR model as a Riva NIM, or convert a NeMo model via nemo2riva / riva-build / riva-deploy / RMIR.riva-asrUse when the user wants to deploy, run, or test an ASR (speech-to-text) Riva NIM — cloud-hosted (build.nvidia.com) or self-hosted Parakeet/Canary/Whisper.
Repository-Explorer
NVIDIA · Repositories und repräsentative Skills - Seite 5
Repository-Ansicht von 1.331 gesammelten Skills in 117 GitHub-Repositories.
code-reviewUse before MR handoff or when reviewing DCGM Exporter changes.comprehensive-testingUse when adding or selecting tests for DCGM Exporter changes.local-gpu-kubernetes-validationUse when validating DCGM Exporter in a local GPU-backed k3d/Kubernetes environment.metric-contract-changesUse when changing metric CSV files, exporter-owned counters, Prometheus labels, or metric rendering.
pair-test-styleWrite, refactor, or review tests in PAIR using focused cases, descriptive subtests, explicit error handling, and structured assertions. Use when adding or changing Go service or desktop tests; apply to the tests in scope rather than starting a repository-wide…pair-github-prFills GitHub pull request descriptions with the required PAIR pair-release-intent:v1 block so the release-intent check passes. Use when opening, updating, or rewriting a PR description, when the user mentions release intent, version bumps, changelog for a PR,…kaizen-uiKaizen UI (KUI) component library and design-pattern advisor for NVIDIA applications. Use whenever someone describes a UI to build, modify, or improve — even without explicit mention of KUI, "design pattern," or "best practice." Covers forms, filters, search,…sync-backendRefresh services/ from upstream, resolve JSON-RPC drift, update contract docs, rebuild cli-bin, and verify. Use when the backend changed or the user asks to sync dhc-modular / services.
cudnn-compile-and-serializeExplain or implement cuDNN Frontend C++ parallel plan compilation, graph serialization, cached plan loading, and deviceless ahead-of-time compilation. Adapt the C++ samples into application code with explicit plan selection, tensor bindings, and error…cudnn-installInstall, verify, or upgrade the cuDNN backend and Python or C++ frontend. Check existing PyTorch, JAX, and NVIDIA NGC installations, select package extras, and diagnose cuDNN library conflicts.determinism-testsAdd and run L0 bitwise determinism and batch-invariance tests for new or changed cuDNN Frontend numerical APIs, kernel paths, datatypes, or GPU targets, then update docs/operations/determinism.md from measured evidence.cutedsl-kernel-integrationUse when integrating a CuTeDSL/CUTE DSL kernel into cuDNN Frontend as a frontend-only Python API, including the public op functions, lazy cudnn exports, optional cutedsl dependencies, FE OSS documentation, and pytest coverage.
processor-developmentCreate or modify reusable SDM processors and focused tests. Use when adding a processor or changing processor behavior.port-external-modelsImplement or review a port of an external model in SDM, from upstream inference behavior and checkpoints through public prediction parity and reviewable PRs.recipe-developmentCompose or restructure SDM model recipes. Use when changing a `Recipe` pipeline.docstringWrite or review docstrings for public modules, classes, and functions in sdm/. Use when adding or reviewing docstrings to follow repo best practices (Args sections, paper citations, tensor shape notation).
nvrx-attrOrchestration layer over nvidia_resiliency_ext attribution modules. Provides log-analysis, fr-analysis, and a Megatron-LM-oriented fault-injection feedback loop for benchmarking attribution quality on SLURM workloads.fault-injection-loopClosed-loop fault injection and attribution accuracy benchmark. Draws from a prioritized pool of (fault_type, rank, iter, nodes) experiments and submits them 2 at a time via sbatch — waiting for each pair to finish before submitting the next — to bound…fr-analysisAnalyze PyTorch NCCL flight-recorder (FR) dumps to identify collective operation hangs and isolate the responsible ranks using CollectiveAnalyzer. Use when a distributed training job hangs due to an NCCL collective timeout and FR dump files are available.…log-analysisAnalyze a SLURM job log file for failure root-cause attribution and restart decisions using the packaged NVRx restart-agent. Use when you have a SLURM training job log and need to determine why the job failed and whether it should be restarted. Performs…
nurec-onboardUse to onboard a raw autonomous-driving dataset to NVIDIA Omniverse NuRec end to end, launched with `run.sh` from a minimal input YAML: audit the raw data, write an NCore V4 converter from the bundled template, validate and evaluate its output, then run a…nurecUse to drive NVIDIA Omniverse NuRec / Neural Reconstruction Engine from released source in a development image built on the matching GitHub-hosted nurec_dev_deps image — train 3DGUT Gaussian reconstructions from NCore clips, generate aux data, adapt an…physical-ai-av-benchmarkUse when the user wants to run the NuRec AV benchmark workflow on one NVIDIA PhysicalAI-Autonomous-Vehicles clip on a new Brev GPU instance, from a source checkout and the pinned dev dependencies image. Thin pointer to the existing docs, skills and workflow.…physical-ai-datasetsUse when the user wants to find, download, or pick a NVIDIA Physical AI dataset on Hugging Face for autonomous-vehicle, robotics, spatial intelligence, manipulation, or neural-reconstruction workflows. Catalog of the NVIDIA `PhysicalAI-` datasets on Hugging…
nvidia-ontology-managementModel and publish Auto Ontology semantics. Use for terms, relationships, measures, imports, MCP write requests, and governed results; not deployment or querying.nvidia-ontology-queryQuery Auto Ontology and validate what it returns. Use for MCP or REST access, readiness, auth, conversations, empty or unanswered ask_question results, and checking generated SQL and rows for wrong measures, units, populations, lineage, joins, source columns,…nvidia-ontology-setupSet up or troubleshoot the Auto Ontology runtime. Use for Helm (the official install), Docker Compose, developer setup, and MCP connection to an existing deployment.
trt-debug-mismatchFind where a TensorRT engine's output starts to disagree with its reference, by bisecting the pipeline to the first divergent boundary. Use when a TRT result differs from ONNX Runtime, PyTorch or a saved golden output. Triggers: TensorRT output is wrong,…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…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…
torch-harmonics-skillsIndex of project-local Claude Code skills for torch-harmonics. Use this to discover which skills are available for this codebase. Individual skills live in the .skills/ directory at the project root.disco-kernel-devExpert guide for adding, optimizing, or debugging DISCO convolution kernels in torch-harmonics. Use this skill whenever the user mentions: adding a new kernel variant or GPU arch path, wiring up a kernel through the Python dispatch layer, fixing…test-writingGuide for writing tests in torch-harmonics. Use this skill whenever the user asks to add tests, check or extend test coverage, write a new test class, test a new layer or kernel, or add distributed tests. Also use when the user asks about tolerance values,…
cuequivariance-jaxExecute equivariant polynomials in JAX using segmented_polynomial (naive/uniform_1d), the ir_dict workflow with IrDictPolynomial and dict[Irrep, Array], and Flax NNX layers (IrrepsLinear, SphericalHarmonics, IrrepsIndexedLinear). Use when writing JAX code…cuequivariance-torchExecute equivariant tensor products in PyTorch using SegmentedPolynomial (naive/uniform_1d/fused_tp/indexed_linear), high-level operations (ChannelWiseTensorProduct, FullyConnectedTensorProduct, Linear, SymmetricContraction, SphericalHarmonics, Rotation), and…cuequivarianceDefine custom groups (Irrep subclasses), build segmented tensor products with CG coefficients, create equivariant polynomials and IrDictPolynomials, and use built-in descriptors (linear, tensor products, spherical harmonics). Use when working with…
cmake-structureIsaac Capture CMake target layout and #include conventions. Use whenever you create or edit a CMakeLists.txt, add or move a module/library/executable/test target, set up target_include_directories or target_link_libraries, decide where a header file goes…rebot-orin-setupUse when initializing a reBot B601-RS (RobStride 6-DOF, seven motors) arm from an NVIDIA Jetson AGX Orin using the Orin's built-in CAN (mttcan) via an external SN65HVD230 transceiver — no USB-CAN/PCAN adapter. Covers the uv/motorbridge env, bringing up can0 @…rebot-orin-setupUse when initializing a reBot B601-RS (RobStride 6-DOF, seven motors) arm from an NVIDIA Jetson AGX Orin using the Orin's built-in CAN (mttcan) via an external SN65HVD230 transceiver — no USB-CAN/PCAN adapter. Covers the uv/motorbridge env, bringing up can0 @…