- 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.NVIDIA/nvidia-resiliency-ext338
- Torch OptimizeThree-role optimization loop for a PyTorch training workload: the Main Loop Agent owns the end-to-end run, authoritative profiling, and hotspot selection; a disposable Optimizer subagent reworks one hotspot per round in an isolated context; a Judge subagent renders an evidence-based verdict driving iterate/pass. All cross-role state lives in files.NVIDIA/recsys-examples334
- Torch Perf AnalysisAnalyze an existing nsys trace of a PyTorch workload (training or inference, NVTX-instrumented) and produce an end-to-end performance diagnosis. Uses the bundled `veloq` CLI for evidence extraction.NVIDIA/recsys-examples334
- Debug Trt MismatchDiagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.NVIDIA/TensorRT-Model-Connect270
- Doc SyncAudit and update TensorRT-Model-Connect documentation when code, public APIs, family ownership, commands, or model support have changed.NVIDIA/TensorRT-Model-Connect270
- Fp16 Trt NetworkImplement or review FP16 and BF16 behavior in one family-owned, strongly typed TensorRT network without changing unrelated families.NVIDIA/TensorRT-Model-Connect270
- Optimize Model PrecisionEvaluate supported precision, quantization, or selected FP32-layer choices for one TensorRT-Model-Connect family with matched correctness and timing.NVIDIA/TensorRT-Model-Connect270
- 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.NVIDIA/TensorRT-Model-Connect270
- Profile ModelMeasure one TensorRT-Model-Connect model through its public Task API or run a checked-in performance-matrix entry with comparable evidence.NVIDIA/TensorRT-Model-Connect270
- 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, and exact-head validation evidence. Use for contributor self-review before marking a PR ready, or when deciding whether a community PR is compliant, decoupled, merge-ready, or needs maintainer feedback. The review is read-only unless the user separately asks to publish it or change the contribution.NVIDIA/TensorRT-Model-Connect270
- Setup Trtmc EnvironmentPrepare a TensorRT-Model-Connect development or validation environment from a fresh checkout on a host without a known working setup.NVIDIA/TensorRT-Model-Connect270
- Submit Github Bug IssueUse when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the bug label, and verifying the created issue.NVIDIA/TensorRT-Model-Connect270
- 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 without merging it.NVIDIA/TensorRT-Model-Connect270
- Transform ModelAdd a Hugging Face or local checkpoint to TensorRT-Model-Connect as a self-contained family, or extend the family that already owns it.NVIDIA/TensorRT-Model-Connect270
- Write Git MessagesDraft, revise, or review Git commit messages, PR titles, PR descriptions, and squash or rebase merge messages. Use when Codex needs to summarize a diff for reviewers, convert rough notes into a commit or PR message, check a message against Git and Conventional Commits style, or prepare repository contribution text before pushing/opening a PR.NVIDIA/TensorRT-Model-Connect270
- Osmo AdminUse only for offline/local OSMO service-config admin requests involving explicit config folders or values files, or to ask for one when a file-specific config request omits it. Do not inspect the workspace to infer a path. Do not use for live workflow support, resource capacity, pod/node diagnostics, or cluster operations, except live service-config paths that must be refused.NVIDIA/OSMO266
- Osmo DeployDeploy OSMO using the unified chart on Azure AKS, AWS EKS or an existing Kubernetes cluster. Use for cluster provisioning, deployment storage, KAI Scheduler or GPU Operator installation, and post-install smoke tests. General workflow usage and running-cluster diagnosis belong to osmo-user.NVIDIA/OSMO266
- Osmo UserDrive the OSMO CLI for cloud-robotics compute on behalf of an end user: check resources, submit/monitor/debug/explain workflows, fetch logs and Grafana/Kubernetes links, inspect direct data storage, manage workflow apps, and set workflow credentials. Use whenever the user asks about OSMO pools, quota, GPUs, or nodes, or about submitting, listing, querying, monitoring, or troubleshooting workflows — including failed, PENDING, queued, stuck, or image-pull-blocked workflows, or when they ask to insNVIDIA/OSMO266
- Asset HarvesterUse to install and run NVIDIA Asset Harvester (Apache-2.0) to extract per-object 3D Gaussian Splat assets (`gaussians.ply`) from AV NCore V4 clips or masked single images via SparseViewDiT + TokenGS, optionally producing `metadata.yaml` for NuRec object insertion. Do NOT use for full-scene reconstruction (use the `nurec` skills), or for maskless inputs outside the bundled segmentation model's classes (masks for AV objects can be generated with `image_segment`).NVIDIA/asset-harvester257
- Rest Core Grpc ProxyBuild or migrate infra-controller REST API endpoints that call on-site NICo Core through the generic Core gRPC proxy. Use when working on REST-to-Core operations, ExecuteCoreGRPC, grpcproxy, forge.Forge methods, creating new proxied REST endpoints, or migrating bespoke workflows to the gRPC proxy.NVIDIA/infra-controller247
- Rest Flow Grpc ProxyBuild or migrate infra-controller REST API endpoints that call on-site Flow through the generic Flow gRPC proxy. Use when working on REST-to-Flow operations, ExecuteFlowGRPC, grpcproxy, v1.Flow methods, or migrating bespoke TaskRun/Flow workflows to the gRPC proxy.NVIDIA/infra-controller247
- Amc Run Rtsp CalibrationCalibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.NVIDIA/DeepStream237
- Amc Run Sample CalibrationRun 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'.NVIDIA/DeepStream237
- Amc Run Video CalibrationCalibrates 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`.NVIDIA/DeepStream237
- Amc Setup Calibration StackLaunch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.NVIDIA/DeepStream237
- 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.NVIDIA/DeepStream237
- Deepstream Eval And FinetuneEvaluate and improve an object detector in NVIDIA DeepStream. Use for deployed mAP, FPS and latency measurement, TAO Skill Bank fine-tuning or AutoML, redeployment, and before/after reporting on HuggingFace, NGC, ONNX, or local models and KPI datasets. Object detection only; do not use for classification or non-vision models.NVIDIA/DeepStream237
- Deepstream Generate PipelineBuild 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.).NVIDIA/DeepStream237
- Deepstream Import Vision ModelUse 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.NVIDIA/DeepStream237
- Deepstream Profile PipelineProfile 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.NVIDIA/DeepStream237
- Deepstream Run Mv3dtRun and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View 3D Tracking on custom synchronized MP4 datasets, import camera calibration, delegate missing calibration to AutoMagicCalib, inspect OSD or BEV visualization, consume MV3DT Kafka metadata, or clean up MV3DT run state in the DeepStream MV3DT app directory.NVIDIA/DeepStream237
- 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 detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on inNVIDIA/DeepStream237
- Rtvi Cv Customize ModelHow to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2d_cv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer config, runtime TRT engine build, deployment, and a segmentation-capable model addendum handoff.NVIDIA/DeepStream237
- 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 microservice repo, validating the VSS integration contract, extending that scaffold for segmentation frame-mask payloads, or scaffolding with placeholders before customer YOLO26 assets exist. For swapping the detector in the stock vss-rt-cv container,NVIDIA/DeepStream237
- Rtvi Vlm Customize ModelHow to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-agent), and health checks.NVIDIA/DeepStream237
- Add FeatureAdd a new UI feature to the nvcf-ui app — folder structure, routing, data loading, lazy-loading, testing, and completion checklist. Use when creating a new feature folder, adding a page or view, wiring routes, building a new screen, or deciding whether to extend an existing feature vs create a new one. Also use when the user asks to build something new in the UI, even if they don't say "feature" explicitly.NVIDIA/nvcf230
- CodegenRun and manage the Orval code generation pipeline for API hooks, TypeScript models, and MSW mocks. Use when editing an OpenAPI spec, running task generate, adding or modifying MSW scenarios, troubleshooting generated code, or when generated hooks are missing or out of date.NVIDIA/nvcf230
- Documentation StyleNVCF public docs style: short, plain, ASCII Markdown with no bold, emojis, em-dash, or en-dash. Use when editing public docs, READMEs, AGENTS.md, agent skills, plans, GitHub issues, or GitHub Pull Request descriptions.NVIDIA/nvcf230
- Nvca Self Managed InstallInstall or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.NVIDIA/nvcf230
- Nvca Values CustomizationCustomize NVCA Operator Helm chart values in the native monorepo. Use when modifying vendored defaults, changing stack-derived install values, adding deployment-time overrides, or updating scripts under deploy/helm/nvca-operator.NVIDIA/nvcf230
- Nvcf Explore StackNavigate and explain the NVCF self-hosted stack inside the monorepo. Maps helmfile releases to their charts, image-source subtrees, helm hooks, namespaces, and `needs:` dependency chains. Reads deploy/stacks/self-managed/helmfile.d/*.yaml.gotmpl and deploy/stacks/nvcf-compute-plane/helmfile.d/*.yaml.gotmpl as the source of truth for ordering and versions. Use when a user or developer asks "what deploys X", "what does X depend on", "what hooks run for X", "walk me through deployment order", "whicNVIDIA/nvcf230
- Nvcf Self Managed CliInstall, operate, and tear down self-hosted NVIDIA Cloud Functions (NVCF) deployments with nvcf-cli. Use for control-plane or compute-plane install, status checks, cluster registration, function deploy/invoke, task create/list/cancel/delete, API keys, admin tokens, JWKS rotation, failed-install diagnosis, and uninstall or down workflows. Trigger keywords: nvcf, nvcf-cli, self-hosted nvcf, self-managed nvcf, NVCFBackend, NVCA, NCP, ICMS, helmfile, control plane, compute plane, LLM function, OpenANVIDIA/nvcf230
- Nvcf Self Managed InstallationInstall and operate NVCF self-hosted control-plane and separate compute-plane stacks. Covers Helmfile values and CLI profile installation flows, teardown, values overrides, pull secrets, and troubleshooting. Use for nvcf-self-managed-stack, nvcf-compute-plane-stack, split compute-plane installation, control-plane installation, CLI-generated control-plane profiles, Helmfile, self-managed, or self-hosted deployments. Do NOT use for local k3d environments; use the local k3d development workflow insNVIDIA/nvcf230
- Nvcf Self Managed PrerequisiteInstall the prerequisites the NVCA operator / compute plane needs before nvcf-nvca-install can succeed: the operator tool nvcf-cli (required by the compute-plane stack's register-cluster step), KAI Scheduler (for the KAIScheduler feature gate), and the SMB CSI driver (for the sharedStorage Samba sidecar PVCs). The two cluster components are cloud-neutral helm installs at the NVCF-validated version pins; same install on AKS, EKS, GKE, k3d, or bare metal. Use when the user mentions NVCA prereqs, nNVIDIA/nvcf230
- RunStart the nvcf-ui development server. Use when asked to run, start, or launch the app, or to verify a change works in the browser.NVIDIA/nvcf230
- TestingWriting frontend tests for the nvcf-ui app — Vitest, Testing Library, MSW, and project-specific render helpers. Use when creating test files, writing component tests, setting up MSW handlers in tests, deciding which render helper to use, or when the user is adding or modifying a UI component and hasn't mentioned tests yet (tests are required). Covers TypeScript/React only — Go backend tests follow standard Go patterns.NVIDIA/nvcf230
- Add Binding FeatureAdd or change a public NeMo Relay runtime API across Rust and affected language bindings when no more specific maintainer skill owns the domain. Do not use for middleware additions, internal refactors, binding-local fixes, or docs-only changes.NVIDIA/NeMo-Relay190
- Add MiddlewareAdd a new NeMo Relay guardrail or intercept type, registration surface, or pipeline stage. Do not use for changing an existing middleware implementation without a new middleware contract.NVIDIA/NeMo-Relay190
- Check Release DeploymentsVerify whether a tagged NeMo Relay release reached GitHub Actions, tagged Go module source, crates.io, PyPI, and npm. Use for publication status of a specific tag; not for publishing packages or creating tags.NVIDIA/NeMo-Relay190
- Contribute DocsAuthor or edit NeMo Relay documentation or examples when repository-specific MDX, public API, integration, or release-history conventions matter. Do not use for review-only requests or incidental prose edits in code.NVIDIA/NeMo-Relay190
- Contribute IntegrationAdd or change a third-party framework integration that attaches NeMo Relay to framework tool, LLM, or lifecycle boundaries. Do not use for core runtime or binding-only changes.NVIDIA/NeMo-Relay190
- Create Beta TagCreate and push a signed, annotated NeMo Relay beta tag from its release branch or validated main. Use when cutting a beta tag; not for RC or stable tags.NVIDIA/NeMo-Relay190
- Create Rc TagCreate and push a signed, annotated NeMo Relay release-candidate tag from its validated release branch. Use when cutting an RC tag; not for code freezes or stable tags.NVIDIA/NeMo-Relay190
- Create Release TagCreate and push a signed, annotated NeMo Relay stable tag, then prepare an unpublished GitHub Release draft for review. Use when cutting a stable release; not for beta or release-candidate tags.NVIDIA/NeMo-Relay190
- Draft Release NotesCompare NeMo Relay release refs and draft the current documentation release-notes page from verified repository evidence. Do not use for GitHub Release bodies or ordinary feature documentation.NVIDIA/NeMo-Relay190
- Maintain CiChange or review NeMo Relay GitHub Actions workflows where permissions, pinned actions, caching, reusable workflows, or release gates require repository-specific handling. Do not use for ordinary source changes that merely run in CI.NVIDIA/NeMo-Relay190
- Maintain Dynamic PluginsChange NeMo Relay dynamic plugin loaders, manifests, native ABI, gRPC worker protocol, or Python worker SDK. Do not use for ordinary built-in plugin configuration.NVIDIA/NeMo-Relay190
- Maintain ObservabilityChange NeMo Relay event fields, subscribers, ATIF output, or typed OpenTelemetry and OpenInference projections. Do not use for instrumentation examples that leave observability contracts unchanged.NVIDIA/NeMo-Relay190
- Maintain OptimizerChange NeMo Relay adaptive configuration, built-in adaptive components, reports, or binding helpers; also use when the task calls this surface optimizer. Do not use for generic plugin changes.NVIDIA/NeMo-Relay190
- Maintain PackagingAdd or change NeMo Relay packages, package metadata, module paths, generated artifacts, registry output, or release-facing build surfaces, including registering new unified-release surfaces with version automation. Do not use for a standalone project version bump, ordinary source builds, or tests.NVIDIA/NeMo-Relay190