Omniverse Realtime Viewer

NVIDIAOfficialCreated by NVIDIA Omniverse

Skill
Tool integration
Software development
Apache-2.0
Medium risk

From the author

Use as the top-level router for Omniverse Realtime Viewer USD apps, XR delivery, SPG GPU processing, stylized rendering, and focused viewer reference documents.

— the description by NVIDIA Omniverse

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The Omniverse Realtime Viewer skill acts as a central routing and architectural framework for developing USD-based 3D viewer applications. It provides a structured approach to composing rendering, scene state, and delivery mechanisms, ensuring that developers can integrate OVRTX rendering, OVStage scene management, and various UI or streaming adapters effectively. The skill emphasizes a modular architecture where the viewer runtime, UI/input adapters, and delivery systems are decoupled, allowing for consistent behavior across local and streamed environments.

What it does

Provides a routing architecture for USD viewer apps, XR delivery, and GPU-accelerated rendering.
Defines the separation of concerns between viewer runtime, UI adapters, and delivery systems.
Offers guidance on integrating OVRTX for high-fidelity 3D rendering.
Establishes conventions for camera interaction, scene state management, and input handling.
Supports the implementation of specialized features like stylized rendering and CAE/CFD visualization.
Provides protocols for agent-to-UI communication and scene control.

When to use it

When starting the development of a new USD-based realtime viewer application.
When integrating advanced rendering features like stylized visualization or AOV switching.
When building XR or spatial editing capabilities into an existing Omniverse application.
When you need to standardize the architecture for local and streamed viewer deployments.
When implementing chat-driven scene control or agent-based inspection of a 3D scene.

Advantages

Promotes a clean, modular architecture that separates rendering logic from UI and transport.
Ensures consistent behavior across different delivery methods, such as local windows or WebRTC streaming.
Provides clear paths for extending functionality without disrupting the core viewer runtime.
Facilitates the integration of complex simulation and visualization data into the viewer.
Standardizes conventions for scene state, selection, and camera control.

Usage examples

“How do I set up a basic USD viewer application using the Omniverse Realtime Viewer architecture?”: The agent will guide you to start with the viewer app reference, resolve dependencies, and implement the core runtime owner to manage the OVStage and OVRTX renderer.
“I need to add stylized rendering to my existing viewer. Where should I start?”: The agent will direct you to the stylized visualization references to implement the required USD/Lua/CUDA nodes within your existing runtime owner.
“How can I enable an AI agent to control the viewer scene?”: The agent will point to the A2UI Scene Copilot reference to implement an operation interface that allows the agent to send commands through the existing runtime owner.
“How do I switch between different render outputs like beauty and depth in my viewer?”: The agent will explain how to use the AOV switching reference to map RenderVars and update the RenderProduct's orderedVars through the runtime owner.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/nvidia/omniverse-realtime-viewer/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip omniverse-realtime-viewer.zip -d .agents/skills

Documentation by NVIDIA Omniverse

Omniverse Realtime Viewer

Build responsive USD viewers by composing OVRTX rendering, OVStage scene state, and the delivery/UI libraries appropriate to the app. Use this package for viewer architecture and interaction; use each selected SDK's upstream guidance for installation and exact release-specific APIs.

Start With The App

When delivery is explicit, select its recipe through references/routing.md and follow its current phase. Otherwise start with references/usd-viewer-app/README.md. For an existing app, keep its architecture and read only the references for the requested change. Broad app, conventions and UI catalogs are lookups as needed.
Resolve the selected libraries through references/dependencies/README.md. Preserve the project's manifest unless an upgrade is requested.
Build a working frame and camera interaction in the chosen shell, then add the requested capabilities. Read references/conventions.md for shared input, camera, selection, and protocol conventions.
Use references/viewer-ux-workflow/README.md for broader interface design. Loading, selection feedback, errors, and input responsiveness belong in the first working app, alongside rendering.
Validate the actual delivery path with references/validation.md. A browser screenshot does not validate a native window or a different transport.

Architecture

Owner	Responsibility
Viewer runtime	Own the live OVStage, publication clock, OVRTX renderer, scene changes, and render stepping.
UI and input adapter	Display frames and copied app state; send user intent to the runtime owner.
Storage/query/simulation workers	Perform their assigned work and return results through the selected integration boundary.
Delivery adapter	Present locally or stream through ovstream; respect frame ownership and backpressure.

Use OVRTX for USD/3D rendering. Browser apps display its WebRTC video; local apps present its output through their native shell. A missing GPU means rendering is unverified, not a reason to substitute a browser 3D renderer.

Keep viewer cameras, settings, effects, and transient edits in app-owned session or runtime state so the source USD stays intact. Serialize scene mutation and render stepping through the runtime owner. Read references/ovstage-ovrtx-integration/README.md for that loop, then the population or data-plane references when implementing scene loading or attribute writes.

Keep expensive loading and metadata work off the UI and render threads. Keep transport details behind a delivery adapter so camera, selection, properties, and loading state can be reused across local and streamed shells.

Add Capabilities As Needed

Use references/routing.md to select camera/picking, scene management, render settings, cloud assets, simulation, editor tools, deployment, or CAE/CFD visualization. Read the selected capability's implementation flow and its linked contract; the full reference catalog is not a prerequisite for a first frame.

For simulation, use the routing reference's Simulation Ecosystem section plus references/realtime-sim-integration/README.md. For UI-driven forces or control, add references/interaction-round-trip/README.md.

For example scenes, use references/usd-sample-data/README.md. When a runtime failure needs diagnosis, use references/troubleshooting/README.md and the selected SDK's matching release guidance before changing the architecture.

Solid Modeling: Upstream First

For usd-brep, exact BRep, solid modeling, kernel failures, CAD topology, or BrepArray questions, first read references/dependencies/README.md → USD BRep. Follow the owning repository's current agent guidance, skills, operation docs, and package API before selecting local integration references. Discover the upstream router rather than assuming skill names or directory layouts remain fixed. Upstream owns modeling semantics, schema rules, tuning, and diagnostics; this package owns OVRTX display, worker handoff, selection mapping, and publication timing.

GPU Processing And Stylized Viewers

For custom GPU processing, chained outputs and lens sampling, read references/spg-processing/README.md. For toon, ink, technical/X-Ray styles, geometry strokes or full wireframe, continue to references/stylized-visualization/implementation.md. Its USD/Lua/CUDA starting node and geometry/depth/composite build sequence work with the selected viewer recipe; use references/stylized-visualization/style-recipes.md for the preset math and references/stylized-visualization/README.md for supporting contracts. Implement the result inside the existing OVRTX/runtime owner and deliver the published processed output. These instructions do not require a sample checkout or a prior stylized-rendering implementation.

For an optional usd-brep geometry source, first read references/dependencies/README.md → USD BRep and the owning repository's current agent guidance, skills, and operation docs; then read references/stylized-visualization/usd-brep-source.md for the display boundary.

XR Viewers

For headsets, immersive viewers, or spatial editors, start with references/xr-viewer-recipe/README.md. Resolve SDK setup and contracts through references/dependencies/ovxr.md; the library owns OpenXR lifecycle and frame submission. For controllers, hands, navigation, or scene tools, add references/xr-spatial-input/README.md and references/ovxr-python-interactions/README.md. For projection-integrated UI, read references/ovxr-composition-ui/README.md and references/ovxr-composition-ui-validation/README.md.

Files

ATTRIBUTION.mdAdded by AutoGineer943 B
BENCHMARK.md13.4 KiB
LICENSELicence file added by AutoGineer11.2 KiB
SKILL.md6.4 KiB
evals/evals.json7.0 KiB
references/a2ui-scene-copilot/README.md10.9 KiB
references/aov-switching/README.md10.5 KiB
references/cae-cfd-visualization/README.md10.1 KiB
references/cae-cfd-visualization/cae-data-ingestion.md5.6 KiB
references/cae-cfd-visualization/coordinate-systems-and-up-axis.md11.0 KiB
references/cae-cfd-visualization/data-and-operators.md11.7 KiB
references/cae-cfd-visualization/driving-cae-viz-via-ovstage.md6.4 KiB
references/cae-cfd-visualization/emitter-and-seed-sources.md16.3 KiB
references/cae-cfd-visualization/glyphs.md7.1 KiB
references/cae-cfd-visualization/ovstage-render-and-camera.md11.0 KiB
references/cae-cfd-visualization/ovui-controls.md13.2 KiB
references/cae-cfd-visualization/rtwt-blueprint-recreation.md11.9 KiB
references/cae-cfd-visualization/streaming-cae-viewer.md25.9 KiB
references/cae-cfd-visualization/temporal-playback.md9.2 KiB
references/cae-cfd-visualization/usd-authoring-and-materials.md21.5 KiB
references/cae-cfd-visualization/volume-rendering.md2.5 KiB
references/camera-auto-select/README.md9.0 KiB
references/camera-controls/README.md20.9 KiB
references/camera-picker/README.md9.5 KiB
references/cloud-assets/README.md4.5 KiB
references/cloud-deployment/README.md19.6 KiB
references/cloud-deployment/container-image-build.md2.2 KiB
references/cloud-deployment/gpu-container-runtime.md2.8 KiB
references/cloud-deployment/nvcf-self-hosted.md8.4 KiB
references/cloud-deployment/nvcf-viewer-container-contract.md4.8 KiB
references/cloud-deployment/webrtc-network-diagnostics.md3.9 KiB
references/cloudxr-opaque-data-channel/README.md1.1 KiB
references/conventions.md7.4 KiB
references/cpp-native-viewer/README.md4.9 KiB
references/cpp-native-viewer/build-details.md5.2 KiB
references/cpp-native-viewer/interaction-features.md11.3 KiB
references/cpp-native-viewer/presentation-loop.md8.0 KiB
references/cpp-native-viewer/project-build.md3.4 KiB
references/cpp-native-viewer/renderer-session.md7.1 KiB
references/cpp-native-viewer/validation.md3.4 KiB
references/dependencies/README.md6.8 KiB
references/dependencies/electron-shm.md1.5 KiB
references/dependencies/environment-validation.md6.6 KiB
references/dependencies/frontend.md2.3 KiB
references/dependencies/local-openusd-gpu.md8.7 KiB
references/dependencies/nvidia-runtime.md14.8 KiB
references/dependencies/ovrtx.md3.1 KiB
references/dependencies/ovstream.md3.3 KiB
references/dependencies/ovxr.md2.3 KiB
references/dependencies/quick-setup.md2.6 KiB
references/dependencies/skia-yoga.md936 B
references/electron-shm-viewer/README.md2.5 KiB
references/electron-shm-viewer/architecture-project.md6.3 KiB
references/electron-shm-viewer/electron-client.md6.5 KiB
references/electron-shm-viewer/protocol-interaction-lifecycle.md7.9 KiB
references/electron-shm-viewer/python-shm-server.md5.5 KiB
references/electron-shm-viewer/validation.md2.8 KiB
references/exact-brep-in-usd/README.md2.5 KiB
references/gl-viewport-overlay/README.md8.0 KiB
references/gl-viewport-overlay/architecture.md4.1 KiB
references/gl-viewport-overlay/example-gizmo.md5.5 KiB
references/gl-viewport-overlay/interaction-pattern.md4.0 KiB
references/gl-viewport-overlay/projection-alignment.md4.3 KiB
references/headless-shm-cli/README.md12.3 KiB
references/huggingface-usd/README.md7.7 KiB
references/interaction-round-trip/README.md40.1 KiB
references/local-viewer/README.md17.8 KiB
references/native-picking-selection/README.md13.1 KiB
references/navigation-presets/README.md4.6 KiB
references/navigation-presets/preset-camera-ops.md5.1 KiB
references/newton-physics/README.md8.8 KiB
references/object-selection/README.md11.1 KiB
references/ovrtx-rendering/README.md23.0 KiB
references/ovstage-data-plane/README.md3.5 KiB
references/ovstage-live-geometry/README.md3.3 KiB
references/ovstage-ovrtx-integration/README.md5.0 KiB
references/ovstage-population/README.md3.7 KiB
references/ovstage-runtime/README.md3.1 KiB
references/ovui-library/README.md3.3 KiB
references/ovui-library/api-reference.md4.3 KiB
references/ovui-library/extending.md4.8 KiB
references/ovui-local-viewer-recipe/README.md4.7 KiB
references/ovui-local-viewer-recipe/interaction-features.md16.9 KiB
references/ovui-local-viewer-recipe/project-structure.md6.2 KiB
references/ovui-local-viewer-recipe/setup-shell-renderer.md16.4 KiB
references/ovui-local-viewer-recipe/validation-build-order.md6.1 KiB
references/ovwidgets-editor-shell/README.md5.4 KiB
references/ovxr-composition-ui-validation/README.md7.1 KiB
references/ovxr-composition-ui-validation/evidence-gates.md3.5 KiB
references/ovxr-composition-ui-validation/frustum-placement.md2.4 KiB
references/ovxr-composition-ui-validation/library-only-validation.md8.1 KiB
references/ovxr-composition-ui-validation/owned-orchestration.md5.3 KiB
references/ovxr-composition-ui-validation/viewer-evidence.md4.0 KiB
references/ovxr-composition-ui/README.md8.5 KiB
references/ovxr-composition-ui/async-raster-pipeline.md5.0 KiB
references/ovxr-composition-ui/compositor-passes-and-sync.md6.4 KiB
references/ovxr-composition-ui/depth-tools.md5.0 KiB
references/ovxr-composition-ui/editor-document-model.md4.8 KiB
references/ovxr-composition-ui/experience-quality.md8.5 KiB
references/ovxr-composition-ui/foveation-and-edge-math.md3.5 KiB
references/ovxr-composition-ui/library-only-compositor.md10.4 KiB
references/ovxr-composition-ui/native-build-and-discovery.md4.6 KiB
references/ovxr-composition-ui/performance-and-telemetry.md7.9 KiB
references/ovxr-composition-ui/primary-projection-compositor.md3.5 KiB
references/ovxr-composition-ui/primary-projection.md4.1 KiB
references/ovxr-composition-ui/projection-and-depth.md5.3 KiB
references/ovxr-composition-ui/raster-abi.md3.0 KiB
references/ovxr-composition-ui/sdk-frame-backend.md1.6 KiB
references/ovxr-composition-ui/skia-yoga.md2.8 KiB
references/ovxr-composition-ui/spatial-interaction.md5.6 KiB
references/ovxr-composition-ui/spatial-surfaces-and-interaction.md10.4 KiB
references/ovxr-composition-ui/telemetry-contract.md3.8 KiB
references/ovxr-composition-ui/validation-and-live-gates.md3.9 KiB
references/ovxr-foveation-and-display/README.md1.1 KiB
references/ovxr-frame-loop-and-readback/README.md1.2 KiB
references/ovxr-library-runtime/README.md1.1 KiB
references/ovxr-library-runtime/ar-compositing.md4.4 KiB
references/ovxr-library-runtime/frame-input-order.md2.2 KiB
references/ovxr-library-runtime/library-only.md1.1 KiB
references/ovxr-library-runtime/live-ar-controls.md4.3 KiB
references/ovxr-library-runtime/mirror-lifetime.md4.1 KiB
references/ovxr-library-runtime/settings-and-lifetime.md3.9 KiB
references/ovxr-library-runtime/viewer-assembly.md225 B
references/ovxr-openxr-runtime/README.md1012 B
references/ovxr-python-interactions/README.md1.8 KiB
references/ovxr-python-interactions/architecture.md5.5 KiB
references/ovxr-python-interactions/feature-patterns.md7.4 KiB
references/physics-simulation/README.md7.1 KiB
references/prim-info-display/README.md10.9 KiB
references/prim-pick-effects/README.md7.3 KiB
references/prim-transform-safety/README.md8.6 KiB
references/realtime-sim-integration/README.md7.0 KiB
references/render-settings/README.md12.6 KiB
references/routing.md37.7 KiB
references/section-views/README.md5.8 KiB
references/seg-outline-highlight/README.md1.5 KiB
references/selection-animation/README.md5.0 KiB
references/selection-feedback/README.md7.5 KiB
references/smlib-brep-pitfalls/README.md2.5 KiB
references/spg-processing/README.md8.0 KiB
references/stage-attribute-reads/README.md6.2 KiB
references/stage-hierarchy/README.md20.3 KiB
references/stage-hierarchy/fallback-worker-protocol.md7.4 KiB
references/stage-loading/README.md7.1 KiB
references/stage-management/README.md6.6 KiB
references/stage-queries/README.md6.1 KiB
references/streaming-client/README.md25.6 KiB
references/streaming-lifecycle/README.md4.6 KiB
references/streaming-messages/README.md19.5 KiB
references/streaming-messages/server-handler-map.md3.1 KiB
references/streaming-server/README.md17.7 KiB
references/streaming-server/frame-loop-and-continuity.md3.8 KiB
references/streaming-viewer-recipe/README.md1.9 KiB
references/streaming-viewer-recipe/client-protocol.md14.2 KiB
references/streaming-viewer-recipe/interaction-features.md13.8 KiB
references/streaming-viewer-recipe/project-structure.md7.3 KiB
references/streaming-viewer-recipe/server-runtime.md20.2 KiB
references/streaming-viewer-recipe/validation-build-order.md8.5 KiB
references/streaming-vs-local/README.md9.4 KiB
references/stylized-visualization/README.md8.7 KiB
references/stylized-visualization/aov-guide-contracts.md8.1 KiB
references/stylized-visualization/implementation.md11.4 KiB
references/stylized-visualization/line-compositor-delivery.md7.7 KiB
references/stylized-visualization/mesh-xray.md10.1 KiB
references/stylized-visualization/reproduction-validation.md10.2 KiB
references/stylized-visualization/style-composition-contract.md5.4 KiB
references/stylized-visualization/style-recipes.md14.7 KiB
references/stylized-visualization/usd-brep-source.md4.9 KiB
references/subprocess-geometry-bridge/README.md3.5 KiB
references/tauri-local-viewer/README.md6.7 KiB
references/tauri-shm-transform-gizmo/README.md12.3 KiB
references/transform-manipulator/README.md17.1 KiB
references/troubleshooting/README.md11.2 KiB
references/troubleshooting/scenario-playbooks.md24.7 KiB
references/usd-sample-data/README.md12.0 KiB
references/usd-viewer-app/README.md5.0 KiB
references/validation.md6.3 KiB
references/viewer-backend-interface/README.md20.1 KiB
references/viewer-control-patterns/README.md4.8 KiB
references/viewer-data-view-patterns/README.md5.6 KiB
references/viewer-feedback-status/README.md5.0 KiB
references/viewer-input-routing/README.md11.9 KiB
references/viewer-layout-patterns/README.md4.7 KiB
references/viewer-ux-workflow/README.md5.2 KiB
references/viewport-overlays/README.md9.9 KiB
references/viewport-overlays/cuda-compositing.md6.6 KiB
references/viewport-resize/README.md4.0 KiB
references/vulkan-compositing/README.md6.1 KiB
references/vulkan-compositing/depth-overlays.md15.7 KiB
references/vulkan-compositing/interop-and-lifecycle.md6.6 KiB
references/webgl-shm-transport/README.md14.5 KiB
references/windows-native-setup/README.md11.6 KiB
references/xr-client-connection/README.md1.1 KiB
references/xr-client-message-contract/README.md8.5 KiB
references/xr-desktop-mirror/README.md13.8 KiB
references/xr-session-modes-and-passthrough/README.md930 B
references/xr-spatial-input/README.md2.3 KiB
references/xr-spatial-input/advanced-tools.md5.2 KiB
references/xr-spatial-input/controllers.md16.3 KiB
references/xr-spatial-input/feature-validation.md4.9 KiB
references/xr-spatial-input/gesture-arbitration.md4.9 KiB
references/xr-spatial-input/gesture-filtering.md5.5 KiB
references/xr-spatial-input/hand-recognizers.md4.0 KiB
references/xr-spatial-input/hands.md10.3 KiB
references/xr-spatial-input/navigation.md13.5 KiB
references/xr-spatial-input/physics-interaction.md23.2 KiB
references/xr-spatial-input/simulation-lifecycle.md5.9 KiB
references/xr-spatial-input/stage-composition.md4.9 KiB
references/xr-spatial-input/teleport-acceptance.md5.2 KiB
references/xr-spatial-input/webxr-client.md3.9 KiB
references/xr-tracking-anchor-and-scale/README.md950 B
references/xr-viewer-recipe/README.md10.5 KiB
skill-card.md7.7 KiB
skill.oms.sig58.2 KiB

BENCHMARK.md

Skill Benchmark: omniverse-realtime-viewer

✅ Overall verdict: PASS — Recommended for publication

Publication Recommendation

Recommended for publication based on the completed evaluation evidence in this report.

Evaluation Metadata

Skill: omniverse-realtime-viewer
Validation status: passed
Evaluation date: 2026-11-06
Evaluator version: 1.6.9
Agents: Claude Code (aws/anthropic/bedrock-claude-opus-5-5), Codex (openai/openai/gpt-6.1-sol)
Tasks: 8 evaluation tasks (7 positive, 1 negative)
Dataset digest: sha256:b6a6c8ae48e6631377089dd22912257405540a3a1fecd6db54bdcce1e550ee79 (skill-evaluator-dataset-snapshot/1)
Attempts per task: 1
Environment: k8s-sandbox
Tier 2 evidence: required for publication
Tier 3 evidence: required for publication

Each task attempt ran in its own isolated sandbox pod.

Tier 1 LLM Provenance

SkillSpector provider, model, analyzer revision, and determinism evidence retained for this scan.

Skill	Provider	Adapter	Analyzer	Model	Revision	Determinism
omniverse-realtime-viewer	nv_inference	openai	mcp_tool_poisoning	`aws/anthropic/bedrock-claude-opus-5-5`	`2.13.4`	nondeterministic / provider_defaults
omniverse-realtime-viewer	nv_inference	openai	semantic_developer_intent	`aws/anthropic/bedrock-claude-opus-5-5`	`2.13.4`	nondeterministic / provider_defaults
omniverse-realtime-viewer	nv_inference	openai	semantic_quality_policy	`aws/anthropic/bedrock-claude-opus-5-5`	`2.13.4`	nondeterministic / provider_defaults
omniverse-realtime-viewer	nv_inference	openai	semantic_security_discovery	`aws/anthropic/bedrock-claude-opus-5-5`	`2.13.4`	nondeterministic / provider_defaults
omniverse-realtime-viewer	nv_inference	openai	meta_analyzer	`aws/anthropic/bedrock-claude-opus-5-5`	`2.13.4`	nondeterministic / provider_defaults

Controls for omniverse-realtime-viewer: temperature=not set (source=provider_default, forwarded=no); seed=not set (source=unset, forwarded=no); reasoning_effort=not set (source=provider_default, forwarded=no)

What This Report Answers

The three-tier evaluation checks whether the skill:

is safe to use;
produces correct answers;
is discovered and activated when needed;
helps the agent complete the user's goal and expected workflow; and
avoids wasted skill and tool usage.

Results at a Glance

Measure	Claude Code (Baseline → Skill Uplift)	Codex (Baseline → Skill Uplift)
Overall	93.9% — baseline ran, but no comparable score was available; uplift unavailable	88.0% — baseline ran, but no comparable score was available; uplift unavailable
Security	100.0% → 100.0% (±0.0 points)	100.0% → 93.8% (-6.2 points)
Correctness	42.5% → 100.0% (+57.5 points)	80.0% → 100.0% (+20.0 points)
Discoverability	93.6% — baseline ran, but no comparable score was available; uplift unavailable	91.4% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness	54.2% → 89.1% (+34.9 points)	66.7% → 82.3% (+15.6 points)
Efficiency	86.9% — baseline ran, but no comparable score was available; uplift unavailable	72.4% — baseline ran, but no comparable score was available; uplift unavailable

How to read this table: baseline is the same task attempted without the target skill. Scores are rounded to one decimal; threshold-adjacent values use additional precision so their displayed band matches the verdict. Uplift is derived from those displayed scores and shown in percentage points.

Example: 47.0% → 92.0% (+45.0 points) means the skill-assisted run scored 92.0%, 45.0 percentage points above its 47.0% no-skill baseline.

A partial dimension was calculated from only the available configured signals; review the detailed report before relying on it.

Comparison details

Shared-source comparisons use the same signals and weights on both conditions. They do not replace the full dimension scores above or change the publication verdict.

Agent	Dimension	Basis	Baseline → With skill (uplift)	Explanation
claude-code	Discoverability	Dimension comparison	N/A	Discoverability is not applicable to the no-skill baseline; there is no installed skill to discover.
claude-code	Efficiency	Token-only comparison	92.3% → 86.0% (-6.3 points)	Only Token Efficiency is comparable; the full dimension scores use different evaluator sources.
codex	Discoverability	Dimension comparison	N/A	Discoverability is not applicable to the no-skill baseline; there is no installed skill to discover.
codex	Efficiency	Token-only comparison	84.7% → 81.8% (-2.9 points)	Only Token Efficiency is comparable; the full dimension scores use different evaluator sources.

Token Usage

Actual Tier 3 execution usage is reported for every observed agent/case pair and both conditions.

Agent	Dataset case	With skill	Without skill	Delta	Change	Coverage
claude-code	All cases	2,843,994	735,099	+2,108,895	+286.89%	skill 8/8; base 8/8
claude-code	unrelated-python-median	35,302	35,140	+162	+0.46%	skill 1/1; base 1/1
claude-code	viewer-browser-plan	496,313	75,284	+421,029	+559.25%	skill 1/1; base 1/1
claude-code	viewer-native-plan	758,174	74,747	+683,427	+914.32%	skill 1/1; base 1/1
claude-code	viewer-no-gpu	282,641	109,197	+173,444	+158.84%	skill 1/1; base 1/1
claude-code	viewer-nvcf-cleanup-plan	358,536	109,072	+249,464	+228.71%	skill 1/1; base 1/1
claude-code	viewer-pick-and-normal-review	332,760	109,120	+223,640	+204.95%	skill 1/1; base 1/1
claude-code	viewer-scene-replacement	361,339	112,163	+249,176	+222.16%	skill 1/1; base 1/1
claude-code	viewer-source-metadata	218,929	110,376	+108,553	+98.35%	skill 1/1; base 1/1
codex	All cases	1,388,192	488,082	+900,110	+184.42%	skill 8/8; base 8/8
codex	unrelated-python-median	13,317	13,253	+64	+0.48%	skill 1/1; base 1/1
codex	viewer-browser-plan	143,609	49,170	+94,439	+192.07%	skill 1/1; base 1/1
codex	viewer-native-plan	99,695	58,871	+40,824	+69.34%	skill 1/1; base 1/1
codex	viewer-no-gpu	75,062	58,192	+16,870	+28.99%	skill 1/1; base 1/1
codex	viewer-nvcf-cleanup-plan	656,841	110,393	+546,448	+495.00%	skill 1/1; base 1/1
codex	viewer-pick-and-normal-review	188,428	98,380	+90,048	+91.53%	skill 1/1; base 1/1
codex	viewer-scene-replacement	125,034	41,679	+83,355	+199.99%	skill 1/1; base 1/1
codex	viewer-source-metadata	86,206	58,144	+28,062	+48.26%	skill 1/1; base 1/1
ALL AGENTS	Dataset aggregate	4,232,186	1,223,181	+3,009,005	+246.00%	skill 16/16; base 16/16

Prompt tokens include cached reads, so total tokens are prompt + completion (cached is not added twice). The Efficiency score uses (prompt - cached) + completion. Change is 100 * (with - without) / without; negative means fewer tokens. N/A comparisons include their reason in the coverage column; coverage is never estimated.

Tier Status

Tier	Purpose	Status	Evidence
Tier 1	Static validation	PASSED WITH OBSERVATIONS	11 validator(s); 70 finding(s)
Tier 2	Semantic deduplication	PASSED WITH OBSERVATIONS	2 validator(s); 54 finding(s)
Tier 3	Live agent evaluation	PASS	2 agent(s); 8 task(s)

Findings and Observations

<details> <summary>Show detailed findings and successful checks</summary>

HIGH DUPLICATE/duplicate: Duplicate content found across references/aov-switching/README.md and references/ovrtx-rendering/README.md and references/usd-viewer-app/README.md: "## Processed GPU outputs" in references/aov-switching/README.md (lines 206-213) vs "## Processed GPU outputs" in references/ovrtx-rendering/README.md (lines 433-440) vs "## Processed GPU outputs" in references/usd-viewer-app/README.md (lines 91-98) (references/aov-switching/README.md:206)
HIGH DUPLICATE/duplicate: Duplicate content found across SKILL.md and references/dependencies/README.md and references/routing.md: "## Solid Modeling: Upstream First" in SKILL.md (lines 67-76) vs "## USD BRep: Public Solid Modeling Dependency" in references/dependencies/README.md (lines 77-108) vs "## Solid Modeling: Upstream First" in references/routing.md (lines 349-362) (SKILL.md:67)
HIGH DUPLICATE/duplicate: Duplicate content found across references/cpp-native-viewer/interaction-features.md and references/native-picking-selection/README.md and references/object-selection/README.md: "## Native Picking" in references/cpp-native-viewer/interaction-features.md (lines 92-93) vs "## Native Picking" in references/cpp-native-viewer/interaction-features.md (lines 173-191) vs "## Decode Pick Results" in references/native-picking-selection/README.md (lines 144-183) vs "## Decode Pick Hits" in references/object-selection/README.md (lines 150-187) (references/cpp-native-viewer/interaction-features.md:92)
HIGH DUPLICATE/duplicate: Duplicate content found across references/dependencies/environment-validation.md and references/dependencies/ovrtx.md and references/ovrtx-rendering/README.md and references/ovui-local-viewer-recipe/setup-shell-renderer.md and references/streaming-viewer-recipe/server-runtime.md and references/troubleshooting/README.md: "## Environment Variable Summary" in references/dependencies/environment-validation.md (lines 3-43) vs "## ovrtx" in references/dependencies/ovrtx.md (lines 32-37) vs "## ovrtx" in references/dependencies/ovrtx.md (lines 43-51) vs "## Environment" in references/ovrtx-rendering/README.md (lines 338-347) vs "## Common Errors" in references/ovrtx-rendering/README.md (lines 408-432) vs "## 2. Install Dependencies And Configure The Environment" in references/ovui-local-viewer-recipe/setup-shell-renderer.md (lines 29-33) vs "## 2. Install Dependencies And Configure The Environment" in references/streaming-viewer-recipe/server-runtime.md (lines 43-49) vs "## Common Error Map" in references/troubleshooting/README.md (lines 63-101) (references/dependencies/environment-validation.md:3)
HIGH DUPLICATE/duplicate: Duplicate content found across references/ovui-local-viewer-recipe/interaction-features.md and references/render-settings/README.md and references/streaming-viewer-recipe/interaction-features.md: "## 11. Add Render Settings And Lighting Controls" in references/ovui-local-viewer-recipe/interaction-features.md (lines 190-196) vs "## Capability-Driven Settings" in references/render-settings/README.md (lines 22-54) vs "## 13. Add Render Settings And Lighting Controls" in references/streaming-viewer-recipe/interaction-features.md (lines 172-178) (references/ovui-local-viewer-recipe/interaction-features.md:190)
119 additional finding(s) are available in the full evaluation artifacts.

</details>

Scoring Methodology

<details> <summary>Show dimension definitions, source signals, and thresholds</summary>

Dimension	Question	Scored signals
Security	Is it safe to use?	`security` (100%)
Correctness	Is the answer correct?	`accuracy` (100%)
Discoverability	Was the right skill loaded when needed?	`skill_execution` (100%)
Effectiveness	Did the skill help complete the task?	`goal_accuracy` (50%) + `behavior_check` (50%)
Efficiency	Did it avoid wasted tool calls and token usage?	`skill_efficiency` (50%) + `token_efficiency` (50%)

Dimension bands: PASS at 50% or above; NEUTRAL from 40% to below 50%; FAIL below 40%.
Overall Tier 3 lift: PASS at +5 points or more; FAIL at -10 points or less; values between those bands are NEUTRAL.
Overall verdict: PASS only when every configured dimension passes for at least one supported agent. Lift is reported as diagnostic evidence and does not override this gate.
The 50% attempt pass threshold is a separate per-task gate; it is not the dimension pass threshold.
Effectiveness is the equal-weight mean of goal completion (goal_accuracy) and expected workflow adherence (behavior_check).
Efficiency is 50% tool-call productivity (the backward-compatible skill_efficiency wire id) and 50% token_efficiency. Positive-case skill routing is scored under Discoverability, not Efficiency; a negative case without a routing target is N/A. N/A sources are omitted, remaining weights are renormalized, and the dimension is marked partial.

Signals present in this run:

security (Security): unsafe operations, secret leakage, and unauthorized access.
skill_execution (Skill Execution): whether the expected skill was selected, decoys were avoided, and the workflow executed.
skill_efficiency (Tool Productivity): tool-call productivity (legacy wire id; routing is scored under Discoverability).
accuracy (Accuracy): final-answer correctness against the reference answer.
goal_accuracy (Goal Accuracy): whether the user's goal was achieved.
behavior_check (Behavior Check): whether the expected workflow behavior was followed.
token_efficiency (Token Efficiency): actual uncached prompt plus completion usage (50% of Efficiency).

</details>

Freshness

Regenerate this benchmark when the skill, evaluation dataset, target agent/model, evaluator version, environment, or scoring policy changes.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python, Needs Node.js

The author says: Orchestrator skill. Downstream focused references may require NVIDIA GPUs, ovrtx, ovstream, ovui, OpenUSD, Python, Node/React, Tauri, Electron, C++, or cloud GPU deployment access depending on the selected viewer path.

Security

What our scanner noticed· Medium risk

Large base64-encoded blobs
Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

NVIDIA Omniverse

Publisher

NVIDIA (Official)

Source

NVIDIA/skills · skills/omniverse-realtime-viewer · commit fce3cca

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE-APACHE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by NVIDIA Omniverse or NVIDIA.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download omniverse-realtime-viewer.zip

From the author

AutoGineer summary

What it does

When to use it

Advantages

Usage examples

Install

Documentation by NVIDIA Omniverse

Omniverse Realtime Viewer

Start With The App

Architecture

Add Capabilities As Needed

Solid Modeling: Upstream First

GPU Processing And Stylized Viewers

XR Viewers

Files

BENCHMARK.md

Skill Benchmark: omniverse-realtime-viewer

Publication Recommendation

Evaluation Metadata

Tier 1 LLM Provenance

What This Report Answers

Results at a Glance

Comparison details

Token Usage

Tier Status

Findings and Observations

Scoring Methodology

Freshness

Requirements and compatibility

Security

Attribution and licence

Related skills

Setup TS Deep Modules

To Spec

Improve Codebase Architecture

Domain Modeling

Codebase Design

Prototype

Download ZIP