- Add SourceGuide for adding a new data source to PhysicsNeMo Curator. Use when adding a remote dataset (HuggingFace, S3, etc.) or local file-based source. Covers discovery questions, file format handling, Mesh/DataArray/AtomicData construction, parallel partitioning, testing, and registration.NVIDIA/physicsnemo-curator55
- Curator ReviewerReview PRs against PhysicsNeMo Curator standards. Runs 8 review passes covering API conformance, correctness, licensing, quality gates, test coverage, performance, code quality, and style consistency. Produces a prioritized report (P0/P1/P2/NIT) and optionally posts review comments to the PR.NVIDIA/physicsnemo-curator55
- TestingRun Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.NVIDIA/physicsnemo-curator55
- Resolve IssueTriggers when you are asked to resolve a specific GitHub issue for the sphinx-llm project. Guides you through a test-driven workflow to resolve the issue, ensuring it is ready for work and following project conventions.NVIDIA/sphinx-llm44
- Check Release DeploymentsVerify whether a tagged NeMo Fabric release is deployed to crates.io, PyPI, and npm. Use when checking publication status for a specific release tag; not for publishing packages or creating tags.NVIDIA/NeMo-Fabric43
- Code ReviewReview Python changes for correctness risks and missing test coverage.NVIDIA/NeMo-Fabric43
- Contribute AdapterAdd or substantially change a first-party NVIDIA NeMo Fabric adapter, including repository packaging, discovery metadata, catalogs, CI wiring, and validation.NVIDIA/NeMo-Fabric43
- Contribute ApiContribute a new NVIDIA NeMo Fabric public API surface safely, with Rust, CLI, Python, TypeScript, schema, adapter, and documentation parity in mindNVIDIA/NeMo-Fabric43
- Contribute DocsContribute documentation or example changes that stay aligned with NeMo Fabric public behaviorNVIDIA/NeMo-Fabric43
- Create Beta TagCreate and push a signed, annotated NeMo Fabric beta tag from its release branch or from validated main. Use when cutting a beta tag; not for RC or stable release tags.NVIDIA/NeMo-Fabric43
- Create Rc TagCreate and push a signed, annotated NeMo Fabric release-candidate tag from its validated release branch. Use when cutting an RC tag; not for code freezes or stable release tags.NVIDIA/NeMo-Fabric43
- Create Release TagCreate and push a signed, annotated NeMo Fabric stable release tag, then prepare unpublished GitHub Release and team announcement drafts for review. Use when cutting a stable release tag; not for beta or release-candidate tags.NVIDIA/NeMo-Fabric43
- Draft Release NotesCompare NVIDIA NeMo Fabric release refs and draft the authoritative GitHub Release body plus any warranted documentation-site release-note update. Use when preparing a stable release, creating patch-release notes, updating docs/about-nemo-fabric/release-notes.mdx, or gathering verified release evidence.NVIDIA/NeMo-Fabric43
- Karpathy GuidelinesBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.NVIDIA/NeMo-Fabric43
- Maintain CiMaintain and review NeMo Fabric GitHub Actions workflows with minimum permissions, pinned action SHAs, deterministic caching, lockfile-backed tools, and local validationNVIDIA/NeMo-Fabric43
- Maintain PackagingMaintain NVIDIA NeMo Fabric Rust, Python, and TypeScript dependencies, package metadata, module paths, native artifacts, lockfiles, license evidence, and release-facing build surfacesNVIDIA/NeMo-Fabric43
- Nemo Fabric Build AdapterBuild, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract. Use when creating adapter or target descriptors, mapping AgentConfig into an agent harness or custom-agent runtime, implementing start/invoke/stop, declaring schemas and capabilities, packaging discovery metadata, or assessing adapter conformance. Do not use for consumer applications that only call the NVIDIA NeMo Fabric SDK.NVIDIA/NeMo-Fabric43
- Nemo Fabric IntegrateUse this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — translating the consumer's own application, job, or deployment config into an in-memory FabricConfig, choosing the single-invocation convenience API or an explicitly started runtime, validating with plan and doctor, and consuming normalized results, artifacts, and telemetry.NVIDIA/NeMo-Fabric43
- Prepare Code FreezePrepare a NeMo Fabric code freeze by creating a release branch, deciding whether frozen-line nightly alpha tags are required, bumping main to the next version, updating current-version documentation, opening the required PR, and creating RC 1. Use when starting, preparing, or automating a NeMo Fabric code freeze.NVIDIA/NeMo-Fabric43
- Prepare PrPrepare, open, create, publish, update, or edit a NeMo Fabric pull request or PR body with the right tests, docs, scope, and review handoff detailsNVIDIA/NeMo-Fabric43
- Python TestsPython tests for NeMo Fabric; use this when writing testsNVIDIA/NeMo-Fabric43
- Review Doc StyleReview NeMo Fabric documentation, examples, and docs-heavy changes for NVIDIA technical writing style, terminology, repository accuracy, and current public behavior. Use for documentation reviews and public-facing text changes.NVIDIA/NeMo-Fabric43
- Small FixMake a small, reviewable NeMo Fabric bug fix without widening scope unnecessarily. Use for narrowly scoped bug fixes or behavior corrections in NeMo Fabric.NVIDIA/NeMo-Fabric43
- Swebench DebuggingApply a focused reproduce-fix-test workflow to SWE-Bench repository tasks.NVIDIA/NeMo-Fabric43
- Update Project VersionUpdate the NVIDIA NeMo Fabric release version across Cargo, Python, and TypeScript package metadata, internal Python dependency pins, integration metadata, and lockfiles. Use when bumping, synchronizing, or auditing NeMo Fabric package versions for a release.NVIDIA/NeMo-Fabric43
- Validate ChangeChoose and run the right NeMo Fabric validation matrix for a change instead of using one fixed test listNVIDIA/NeMo-Fabric43
- Sflow Code ReviewReview sflow code changes for functional defects, modular by-purpose structure, duplicated logic that should be consolidated, adequate unit + e2e CLI test coverage, and over-engineering that should simply be deleted (ponytail pass). Use when reviewing an sflow diff, branch, PR, staged changes, or when the user asks for a code review of sflow.NVIDIA/nv-sflow41
- Sflow Error AnalysisDiagnose and troubleshoot sflow workflow errors from log output, error messages, and task failures. Covers config validation errors, expression resolution failures, backend issues (Slurm, Docker, Kubernetes/kubectl/RBAC), probe timeouts, task crashes, S3 storage/upload failures, and batch submission problems. Use when the user encounters an sflow error, pastes error output, asks to debug a failed workflow, or asks about sflow troubleshooting.NVIDIA/nv-sflow41
- Writing Sflow YamlWrite, create, and modify sflow YAML workflow configuration files. Covers schema structure, variables, task DAGs, backends (local, slurm, docker, kubernetes), operators, probes, replicas, artifacts, result parsing, storage/uploads (S3), hardware monitoring, and modular composition. Use when the user asks to create an sflow YAML, configure a workflow, set up inference serving on Slurm or Kubernetes, or asks about sflow YAML syntax.NVIDIA/nv-sflow41
- Physical Ai Defect Image GenerationUse when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect imagNVIDIA/physical-ai-data-factory38
- Physical Ai Defect Image Generation V1 1Use for NVIDIA Cosmos3-based AnomalyGen 1.1 defect image generation on OSMO; use the unversioned physical-ai-defect-image-generation skill for the original workflow. Orchestrates Day 0 USD-to-ROI, Qwen image-edit augmentation, LoRA finetuning, and generation, plus Day 1 checkpoint reuse, inference, and labeling for PCBA, metal surfaces, and glass. Trigger for AnomalyGen 1.1, Cosmos3 defects, DIG 1.1, Day 0 or Day 1 PCBA, manual ROI, real-photo alignment, setup_pcb, setup_metal, setup_glass, setuNVIDIA/physical-ai-data-factory38
- Physical Ai Video Data AugmentationUse when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augmentation, data enrichment, auto labeling, VDA demo, OSMO workflow, pseudo labeling.NVIDIA/physical-ai-data-factory38
- Docs Visual ReviewUse for docs visual audits, layout, typography, heroes, CSS, navigation, or interaction changes. Skip prose-only edits.NVIDIA/OpenShell-Research37
- Review CodeReview a code repository for concrete issues in correctness, robustness, security, maintainability, tests, and integration. Use for repository-wide or focused code review where practical engineering judgment and strict scope control matter.NVIDIA/OpenShell-Research37
- Review CommonShared evidence, scope, reporting, and scoring rules for the selected CI review task. Apply alongside one domain review skill.NVIDIA/OpenShell-Research37
- Review Research SpikeReview exploratory experiments for valid methods, defensible evidence, reproducibility, and appropriately small implementations rather than production readiness.NVIDIA/OpenShell-Research37
- Review Technical WritingReview technical documents, guides, tutorials, proposals, reports, design documents, and technical blog posts for accuracy, clarity, completeness, structure, evidence, audience fit, and practical reader utility.NVIDIA/OpenShell-Research37
- Review ToolAssess a new reusable tool or library for correctness, usability, verification, and proportionate engineering.NVIDIA/OpenShell-Research37
- Review Use Case ExampleAssess a new use case demonstration for a coherent, reproducible workflow that teaches its intended audience without unnecessary framework design.NVIDIA/OpenShell-Research37
- 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 `nre`) or for inputs without per-object masks.NVIDIA/nurec-skills35
- NcoreUse when converting any sensor dataset into NVIDIA NCore V4 format (and feeding it to NuRec or a robotics-to-sim "r2s" pipeline). Covers ingesting raw cameras, LiDARs, radars, IMUs, depth or stereo into V4 sequences; authoring a new converter from the template; adapting PAI / Waymo / PandaSet / NuScenes to V4; handling non-AV rigs (mono+depth, mono+lidar, stereo, multi-stereo, RGB-D, COLMAP / SfM, ROS2 bag); and diagnosing a broken converter against `validate.py`. Do NOT use to train reconstructNVIDIA/nurec-skills35
- NreUse to drive NVIDIA Omniverse NuRec / Neural Reconstruction Engine (NRE) via the public NGC containers nvcr.io/nvidia/nre/nre and nvcr.io/nvidia/nre/nre-tools (NGC_API_KEY required) — train 3DGUT Gaussian reconstructions from NCore clips, generate aux data, adapt an existing USDZ to an augmented target-vehicle rig (carline adaptation), render frames or LiDAR sweeps (local or warm `serve-grpc`), export PLY/depth/mesh/USDZ, edit actors, and evaluate metrics. Do NOT use for per-object asset captureNVIDIA/nurec-skills35
- Nurec FixerUse to run NVIDIA DiffusionHarmonizer (public successor to the older Fixer recipes) to enhance, harmonize, evaluate, or fine-tune novel-view frames from NRE / NuRec / 3DGS / NeRF reconstructions. Do NOT use for training the 3D reconstruction itself (use `nre`) or for sensor-to-NCore conversion (use `ncore`).NVIDIA/nurec-skills35
- Nurec IndexRouter for NVIDIA NuRec / NRE / 3DGUT / USDZ / NCore V4 / asset harvest / frame cleanup tasks — picks the right sibling (nre, ncore, asset-harvester, nurec-fixer, physical-ai-datasets). Use when the sub-skill is unclear or a multi-stage pipeline is needed; do NOT use for non-NuRec tasks or to run any pipeline itself.NVIDIA/nurec-skills35
- 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 every dataset under huggingface.co/nvidia with the `PhysicalAI-` prefix, organised by domain (AV, Robotics-Manipulation, Robotics-GR00T, Robotics-mindmap, Robotics-NuRec, Spatial Intelligence, Grasping, Healthcare, Sim-Ready, Material properties), with per-dataset size, format, gating, NVIDIA/nurec-skills35
- Benchmark IsaaclabRun Isaac Lab benchmark scripts and interpret their outputs. Covers RL training throughput, non-RL environment step FPS, camera/load/startup benchmarks, batch suites, parameter gotchas, output files, and JSON result structure. Use when the user asks to run or compare Isaac Lab benchmarks. NOT for RL convergence or policy-quality validation, profiling capture (use profiling), trace analysis (use nsys-analyze), or applying performance fixes (use perf-tuning).NVIDIA/omniperf34
- Benchmark IsaacsimRun Isaac Sim benchmark scripts and interpret benchmark outputs. Covers camera, SDG, scene-loading, robot, lidar/radar/sensor benchmark scripts, common parameters, output files, and benchmark-specific pitfalls. Use when the user asks to run or compare Isaac Sim benchmark results. NOT for initial bottleneck triage (use diagnose-perf), profiling capture (use profiling), trace analysis (use nsys-analyze), or applying performance fixes (use perf-tuning).NVIDIA/omniperf34
- Diagnose PerfFirst-responder performance triage for Isaac Sim and Isaac Lab. Identifies bottleneck category (GPU-bound, CPU-bound, VRAM, loading) using nvidia-smi and system tools without profiling. Use when a user reports slow FPS, stuttering, high latency, or wants a quick health check before profiling. NOT for applying specific fixes (use perf-tuning), capturing traces (use profiling), or analyzing traces (use nsys-analyze).NVIDIA/omniperf34
- Install IsaaclabInstall Isaac Lab for Isaac Sim-backed workflows or Isaac Lab 3.0+ kit-less/Newton workflows, then verify the setup. Use when the user asks to install, set up, or build Isaac Lab.NVIDIA/omniperf34
- Install IsaacsimInstall Isaac Sim via pip or source build. Covers Docker setup, verification, and common install issues. Use when the user asks to install, set up, or build Isaac Sim.NVIDIA/omniperf34
- 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 `tracy-capture`/`tracy-update` aliases. Use when setting up a profiling environment, when nsys/sqlite3/csvexport/capture/update tools are missing, or before running profiling, nsys-analyze, or tracy-memory.NVIDIA/omniperf34
- 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.NVIDIA/omniperf34
- 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 profiles with the profiling skill. NOT for capturing traces (use profiling), adding zones to code (use profiling-api), or applying fixes (use perf-tuning).NVIDIA/omniperf34
- 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 Nsight Systems integration. Use when CARB_PROFILING_PYTHON doesn't work (no Kit/Carbonite runtime), when profiling standalone Isaac Lab scripts, or when you need per-function Python tracing in nsys captures outside Kit.NVIDIA/omniperf34
- 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 (isaaclab_performance/balanced/quality), viewport gizmos, HydraEngine waitIdle, fsWatcher overhead, and CPU governor. Use when profiling data shows a specific bottleneck and you need the fix, when someone asks "why is it slow" and you have Tracy/nsys evidence, or NVIDIA/omniperf34
- 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 profile commands, Kit profiler args, and lightweight export handoff to nsys-analyze. Use when running profiling captures, setting up trace collection, or troubleshooting capture failures. NOT for adding profiling zones (use profiling-api), NVIDIA/omniperf34
- 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 annotations, and automatic Kit Python function capture (CARB_PROFILING_PYTHON). Use when a developer asks how to add profiling spans to Kit/Carbonite code, configure masks/channels, record custom Tracy plots, or annotate traces with event markers.NVIDIA/omniperf34
- 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 strip-test verification, Tracy Memory tab analysis, and debug symbol requirements. Use when investigating memory leaks, allocation hotspots, or VRAM growth in Isaac Sim, Isaac Lab, or Kit apps. Requires profiling capture setup plus install-profilersNVIDIA/omniperf34
- Using HolodeckUse when the user wants to provision, manage, or destroy GPU-enabled test environments via the holodeck CLI. Covers env.yaml config, create/dryrun/list/status/ssh/scp/delete/cleanup/get/os workflows, and common pitfalls.NVIDIA/holodeck30
- Ai Factory Operations Agent HeadlessUse AI Factory Operations Agent without opening the browser UI. Invoke it through the headless HTTP API, packaged CLI, or stdio MCP server, and deploy it first when no service is available.NVIDIA/AI-Factory-Operations-Agent24