NVIDIA-Omniverse

Use when setting up a fresh clone of this repo to run OVRTX Dev Variant Presenter (also called the "variant studio" in the walkthrough video and earlier releases) — no .venv yet, ovrtx/ovstage/ovstream not installed, ModuleNotFoundError on…

Use when asked to start, run, launch, restart, or bring up the OVRTX Dev Variant Presenter server, stream, or viewport in this repo — also called the "variant studio" in the walkthrough video and earlier releases — or after the stream / GPU / server was lost…

Build a browser-based, RTX-streamed app for exploring and rendering USD VARIANT PERMUTATIONS — a live ovstream/WebRTC viewport plus instant variant switching, cameras, a turntable rig, grid/batch stills, a multi-track timeline, projects, post, and…

The visual design + layout for the Dev Variant Presenter frontend — the GitHub-dark + NVIDIA-green theme, the header / viewport+timeline / right-side tabbed control panel layout, and the component styles (pill chips with swatches, segmented buttons, blocks,…

Batch-render combinatorial USD variant permutations to disk with an ovrtx renderer: one-at-a-time and full-Cartesian matrix modes, a combinatorial-explosion guard, a {set}-{variant} naming convention, optional animation-range frame sequences, progress events,…

Post-process rendered variant permutations: browse a results folder of stills/videos, burn variant-label plates onto renders (originals untouched), assemble frame sequences into MP4, and compose a labeled contact sheet ("cut sheet"). Pure PIL/OpenCV/ffmpeg,…

Persist a Variant Presenter workspace: named PROJECTS (bundle a stage with its base variant selection, display/optics, selected camera, per-camera looks/framing, and saved timeline views) and an automatic crash-recovery SESSION checkpoint that restores the…

Build a multi-track, non-linear timeline (NLE) for USD variant + camera changes over time: a pure state-resolution engine (tracks/clips, state_at(t), frame sampling, mixer/slideshow presets), a client-side JS mirror for instant scrubbing, and a render-to-MP4…

Run the direct Material Agent CLI for config-driven VLM material assignment pipelines. Use when the user wants to run material-agent commands directly, edit or execute a material-agent config YAML, resume a fixed pipeline, benchmark material predictions,…

Deploy the physics-agent-service locally using Docker Compose with the bundled OVRTX GPU rendering sidecar. Use when user wants to run physics agent with docker, docker compose, set up local deployment of the physics service, run it on a GPU box, start…

Analyze images using a Vision-Language Model through the wu CLI. Use when the user wants to describe an image, caption a picture, ask questions about visual content, inspect renders or screenshots, compare visual evidence, or produce text or JSON answers with…

Use when a long-running coding agent needs to inspect, manipulate, render, validate, optimize, restore, or export a USD asset through Content Workbench, including scene sessions, snapshots, rendering, picking, path translation, edit transactions, and workflow…

Plan and execute one or more domain tasks over finalized decomposed scene assets, with an immutable eligible work matrix, independent per-item results, agent-chosen ordering, durable decision memory, and a sealed Workflow 2 handoff. Use after scene…

Use when the user wants the public batch shortcut for a prepared agentic asset workflow, including single-asset material assignment and three-phase large-scene execution or resume through content-workflow-cli.

Use before USD-based content workflows when a source asset must be routed to OpenUSD through the agentic convert-to-usd workflow, including existing USD passthrough, CAD/mesh conversion, URDF conversion, MuJoCo/MJCF conversion, blocked reports, and handoff…

Coordinate a large OpenUSD scene through decomposition, per-asset domain processing, and original-topology collection using durable run state and deterministic handoff gates. Use when a scene is too large or repetitive to process monolithically, when…

Cloning USD subtrees to create copies at new paths. Use when user asks to clone, duplicate, copy a prim, or create instances of existing geometry.

Setting up a new CMake C/C++ project that uses ovrtx. Use when user asks to create a new C project, set up CMake with ovrtx, scaffold a C++ app, or configure build dependencies.

Reading scalar or array attributes from prims into CPU or GPU tensors. Use when user asks to read an attribute value, fetch mesh data (points, faceVertexCounts, etc.), inspect a render setting, or sample transforms.

Writing render settings to control rendering behavior. Use when user asks to change render settings, set max bounces, configure path tracing, change render quality, or modify RTX settings on a RenderProduct.

Creating and configuring an ovrtx renderer instance. Use when user asks to create a renderer, initialize ovrtx, configure renderer options, or set up ovrtx.

Upgrade skill: migrate user C/C++ application code from ovrtx 0.3.x standalone stage APIs to ovrtx 0.4.x attached to ovstage 0.1.x. Use when the user asks to "upgrade from 0.3 to 0.4 with ovstage", "ovrtx 0.4 ovstage 0.1 migration", "migrate my ovrtx app", or…

Upgrade skill to migrate an existing Python ovrtx codebase from 0.3.x to 0.4.x by moving scene population, cloning, queries, attribute reads, writes, mappings, and persistent binding workflows to ovstage while keeping rendering in ovrtx. Use when the user…

Warming up the renderer before capturing output. Use when user asks about warmup frames, image quality, texture streaming, path tracing convergence, or why renders look noisy/incomplete.

Orchestrate an end-to-end NVIDIA self-managed streaming stack across AWS or Azure. Use when planning, generating, sequencing, deploying, or validating the full path from CSP base infrastructure through NVCF self-managed control plane, NVCF auxiliary services,…

Install, 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…

Install 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,…

Deploy DDCS as a shader cache for Kit/write-render-worker on GKE. Produces Kubernetes manifests, the Helm values override for write-render-worker (drivercachewrapper + UJITSO), and optionally runs a proof-of-life test. Use when setting up DDCS for MEGA shader…

Deploy NVIDIA Omniverse Content Cache (OVCC) alongside a MEGA simulation stack. Covers evaluation, sizing (NGINX queue-depth model), configuration for GCS/S3/Azure backends, Helm install from NGC (chart ovcontentcache v4.0.4), TLS setup, in-place upgrade from…

Use for installing, debugging, or modifying NVCF GXCache across self-managed Kubernetes environments. Trigger on explicit GXCache, helm-gxcache, gxcache-init, gxcache-webhook, distributed shader cache, NVCA cache feature gates, or GXCache provider adaptation…

Generate the AWS network and IAM foundation for a KAS/NVCF EKS deployment: VPC, public/private subnets, route tables, Internet/NAT gateways, and base IAM/tagging inputs. Use as Stage 01 of aws-infra before eks-cluster.

Orchestrate the AWS KAS/NVCF EKS foundation by delegating to the component AWS infrastructure skills: aws-tf-conventions, aws-iam-vpc, eks-cluster, eks-nodes, eks-storage, ecr, eks-gpu-operator, eks-validate, and optionally ecr-mirror. Use when setting up,…

Use when adding or reviewing a storage backend plugin for ovstorage.

Use when changing or reviewing the built-in authentication and authorization Layer or its TOML policy engine.

Use when Rust changes affect the ovstorage plugin ABI header and the checked-in generated copies must be refreshed.

Use when starting ovstorage-broker locally for development or integration testing with the current Stack and listener-auth configuration.

Use when checking the Storage API wire contract that ovstorage-plugin-services-client depends on.

Use before opening or merging an ovstorage PR to run the project verification gate and inspect risky diffs.

Use when authoring or rotating the broker's built-in authorization policy.

Use when triaging a misbehaving ovstorage-broker - covers startup failures, authz denies, listener authn mismatches, streaming write aborts, reload misfires, and drain hangs.

Diff two USD stages by prim/mesh/vertex/material count, file size, and validator summary. Use for before/after optimization comparisons.

Choose and run a ready-made preset operation stack from config_presets/. Use when you want a known-good starting point for a common optimization goal rather than assembling a custom config.

Create a USD proxy mesh sibling. Use to generate decimated, bbox, or LOD stand-ins, with optional render/proxy purpose variant set.

Triage a failing Usd Optimize operation. Use when an op errors, silently no-ops, or returns unexpected output.

Collapse duplicate prim hierarchies into instanceable internal references. Use when deduplicating subtrees or folding repeated prims into prototypes.

Quick USD stage inspection — reports stage info, prim counts, mesh statistics, materials, animation, and scene scale. Use before optimizing.

Read saved validator artifacts and triage the issues that --fix could not auto-resolve, with per-rule prim lists and fix recommendations. Use after run-validators to decide what to do about remaining issues.

Scaffold a new Usd Optimize operation plugin (C++ source, premake, test, guide, optional validator). Use to add a new op or plugin.

End-to-end ovstage application lifecycle: create an instance, identify prims/attributes via the path dictionary, write attribute columns at an ordinal, advance the write floor to seal them, query/read, and release. Use when user asks how to structure an…

Clone the subtree under a source prim to one or more new target paths in a single ordinal-keyed call — including the multi-environment pattern (stamp out N copies of a prototype). Use when the user asks to clone, duplicate, or copy a prim/subtree, or to spawn…

How ovstage attribute data crosses the boundary as DLPack DLTensors — copy-in writes, copy-out reads, staging-backed map/unmap writes, CPU vs CUDA residency, cuda_sync GPU sync, and sparsity (index_map/mask). Use when user asks about DLTensor, tensor data…

Error checking patterns for the ovstage C API. Use when user asks about error handling, checking return codes, debugging ovstage failures, or troubleshooting a failed enqueue, wait, or fetch.

Setting up a Python project that uses the ovstage Python bindings. Use when user asks to create a Python ovstage app, import ovstage, configure the library path, or scaffold Python code that reads/writes stage data.

Headless load -> populate -> read -> update -> read loop with no renderer attached: open a USD scene into the ovstage runtime table, read prims back to confirm, then update the live stage two ways — write straight into the ovstage table (e.g. animate a…

Find prims with filter queries — predicates over reserved metadata built-ins (usd-path, usd-prim-type, usd-parent, usd-children, usd-schemas) and attribute presence — instead of explicit path lists, then introspect what a query matched. Use when the user asks…

Port code written against the USD API (pxr) to the ovstage data plane: map DefinePrim / CreateAttribute+Set / Get / RemovePrim / Sdf.ChangeBlock onto INSERT-mode writes, write_attribute, read_attributes, delete_attributes, and the batched write_attributes —…

Wiring connection / message / input callbacks for WebRTC, native, SHM, and CUDASHM streams. Use when user asks about receiving input events, handling messages, detecting client connect/disconnect, or sending messages back.

Writing a CUDASHM reader/consumer that attaches to an ovstream CUDASHM producer over CUDA IPC. Use when user asks about consuming GPU-resident frames, reading from a CUDA IPC ring, writing a simulation/post-processing kernel that ingests rendered output, or…

Writing a native (StreamSDK) reader/consumer that attaches to an ovstream NATIVE server over the network. Use when user asks about consuming a native stream, writing a StreamSDK client viewer, decoding frames client-side via NvStreamingMedia, or streaming…

Setting up a new CMake C/C++ project that uses ovstream. Use when user asks to create a new C project, set up CMake with ovstream, scaffold a C++ streaming app, or configure build dependencies.

Choosing between WebRTC, RTSP, the native protocol, SHM, and CUDASHM. Use when user asks which transport to use, the trade-offs, what each protocol supports, or how to view a stream.

Writing an SHM reader/consumer that attaches to an ovstream SHM producer. Use when user asks about consuming SHM frames, reading from shared memory, writing an OpenCV / Electron / custom viewer, or multi-reader patterns.

High-level overview of a typical ovstream application lifecycle. Use when user asks how to structure an ovstream program, what the main steps are, or how the pieces fit together.

CUDA buffer allocation, pitch alignment, BGRA channel order, and ctypes-bound cudart usage. Use when user asks about CUDA interop, pitched allocations, frame layout, or zero-copy GPU integration.

Stand up a USD Search deployment the user controls. Branches on local docker-compose vs. helm on Kubernetes. Local branch covers the full quickstart compose stack with GPU/VLM/storage-backend questionnaires. Helm branch covers the usdsearch chart at…

Run the locally-built Explorer UI against a REMOTE, fully-hosted USD Search instance by proxying every API call through the local gateway. No local deepsearch-api / OpenSearch / SigLIP2 / Asset Graph Service — only the Explorer + gateway run locally, so…

Deep-inspect a single 3D asset by URL. Fetches multi-view thumbnails, per-plugin indexing status, USD scene summary (prim counts, geometry, scale, up-axis, default prim), prim hierarchy, forward + inverse dependency graphs, and optionally runs VLM relevance…

Get a first-time user to a real 3D asset in seconds. Asks one question — "where do you want to search?" — with three backend lanes (NVIDIA-hosted default, your own URL, or a local deployment), then hands off to /search for the actual query. The journey is the…

Spatial and scene-graph queries inside a USD scene via the Asset Graph Service. Answers: what's near a point or prim (radius), what's inside a bounding box, what prims of a given type or property exist in this scene, what does this scene reference, where is…

Search USD Search for 3D assets. One skill, three input modes: text query, reference image, or both combined. Hits POST /search_hybrid + GET /images. Iterates on intermediate matches for visual-similarity refinement when the user wants "more like this". Use…

Discover which USD properties a USD Search deployment's corpus actually carries, and turn that into local config: hits GET /search/stats/usd_properties, then builds a ranked usd_property_catalog.yaml (the grounding source for the built-in LLM query parser)…

Create an ovphysx instance, attach an ovstage scene, step simulation, and clean up. Use when starting a new ovphysx project, testing basic integration, or learning the minimal workflow.

Clone one USD environment subtree into many runtime-only PhysX environments for RL-style batched simulation. Use when a caller needs replicated physics environments, clone API ordering, or target transform guidance.

Read ovphysx simulation output with the ovstage-native output-read API when results must retain ovstage identity or write back without rebuilding paths or repacking tensors. Covers Python `PhysX.read()` / `PhysX.read_tokens()`, C `ovphysx_query()` /…

Author USD physics content that ovphysx can load and simulate (rigid bodies, colliders, mass, physics scene). Use when creating or editing .usda or USD scenes for ovphysx, not when calling the runtime step or tensor API. Keywords USD authoring, UsdPhysics,…

Create tensor bindings to read and write physics simulation data on CPU using numpy arrays. Use when you need to exchange simulation state (poses, velocities, joint targets) with your application via tensors.

Read and write physics simulation data on GPU using CUDA device pointers and DLPack tensors. Use when you need GPU-to-GPU tensor exchange (no CPU staging) for high-throughput RL or robotics workloads.

Use when creating, modifying, inspecting, or reasoning about ovui UI from low-level atomic ovui widgets, including layout, Pixel/Percent/Fraction sizing, model-view widgets, TreeView/stage hierarchy trees, inputs, menus, windows, docking, viewport-like ovrtx…

Use this skill when the user asks to inspect, screenshot, automate, click, type into, or drive a running ovui/ovui-widgets application through the ovui-inspect FastAPI inspector. The skill provides an importable `ovuiinspect` module, an `ovui-inspect` CLI,…

Use this skill for ovui and ovui-widgets styling work: palettes, colour / float / URL constants, theme shades, ui.style.default, style dictionaries, selector grammar, widget name variants, style_type_name_override values, naming conventions, style hierarchy,…

Install and run the packaged ovui USD Viewer with ovrtx and either OpenUSD, ovstage, or both data adapters. Use when creating a clean virtual environment from published wheels, selecting the adapter configuration, or launching ovui_widgets.app against a USD…

Use this skill when a user asks to create or validate a disposable standalone ovui/ovui-widgets application from the existing widget set. The application source should live outside the repo unless the user explicitly asks to productize it. The skill gives…

Retrieves full NVCF function and deployment information for a given function ID (and optionally a function version ID) via the NVCF and NGC APIs, including status, container image, inference and health endpoints, ports, and deployment specifications. When…

Retrieves full details for a published streaming application on the Omniverse portal by locating it via app_id or NVCF function_id and function_version_id, authenticating like publish-streaming-app, and calling GET /api/apps/{app_id}. Returns portal metadata,…

Triages Omniverse Kit streaming failures on NVCF and the Web Streaming Portal by matching symptoms to issue guides, verifying portal and NVCF state via check-streaming-app and check-nvcf-function, and summarizing fixes. When the root cause stays unclear,…

Publish or update a streaming application on the Omniverse portal by collecting app metadata, authenticating against the portal's identity setup, and calling `PUT /api/apps/{app_id}`. Use when Codex needs to add, publish, register, or update a streaming…

Remove a published streaming application from the Omniverse portal by locating the app via `app_id` or via `function_id` plus `function_version_id`, authenticating against the portal's identity setup, previewing the matched app, and calling `DELETE…