AutoGineer
Generated banner for Omniverse Usd Performance Tuning
Generated logo for Omniverse Usd Performance Tuning

Omniverse Usd Performance Tuning

OpenAIOfficialCreated by NVIDIA OmniverseDistributed by OpenAI

  • Skill
  • Workflow
  • Software development
  • Apache-2.0
  • Medium risk
  • Has scripts
Download ZIP

From the author

Top-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates auth/runtime setup to Phase 0 owners.
— the description by NVIDIA Omniverse

AutoGineer summary

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

The omniverse-usd-performance-tuning skill provides a structured, end-to-end procedure for addressing performance bottlenecks in USD assets. It manages the lifecycle of performance tuning, from initial runtime context setup and baseline profiling to composition auditing, validation, and targeted scene optimization. The skill enforces a rigorous milestone-based approach, ensuring that all destructive operations are planned and approved, and that performance improvements are verified through comparative profiling and standardized reporting.

What it does

  • Orchestrates the end-to-end USD performance tuning lifecycle.
  • Validates runtime environments and handles authentication for remote assets.
  • Conducts composition audits and structural assessments of USD stages.
  • Executes validated optimization operations using Scene Optimizer.
  • Generates structured optimization reports comparing baseline and post-optimization metrics.
  • Enforces safety gates for destructive operations and mutation.

When to use it

  • When a USD scene exhibits slow loading times or low frame rates.
  • When memory usage is excessively high or GPU crashes occur.
  • When you need to optimize a scene for better interactivity or performance.
  • When you need to diagnose CAD conversion quality issues.
  • When you need to validate a scene before and after applying optimizations.

Advantages

  • Ensures consistent performance diagnosis through a standardized workflow.
  • Prevents accidental data loss by requiring approval for destructive operations.
  • Provides clear, evidence-based reporting on performance improvements.
  • Integrates seamlessly with existing Omniverse validation and optimization tools.
  • Maintains strict separation between diagnosis, planning, and execution phases.

Usage examples

“This USD scene loads very slowly; please triage what I should check first.”
The agent will initiate the runtime context gate, perform a composition audit, and provide a structured plan to identify the source of the slow load time.
“Optimize my CAD scene for better performance.”
The agent will verify the runtime, assess the CAD conversion quality, and propose a milestone-based optimization plan including validation and profiling.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/openai/omniverse-usd-performance-tuning/download

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

    mkdir -p .agents/skills && unzip omniverse-usd-performance-tuning.zip -d .agents/skills

Documentation by NVIDIA Omniverse

Omniverse USD Performance Tuning

<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->

<!-- SPDX-License-Identifier: Apache-2.0 -->

When to Use

Use this workflow for broad performance asks such as slow loading, high memory, low FPS, GPU crashes, conversion-quality triage, or generic requests to optimize a USD scene.

Instructions

  1. Start from the mandatory runtime context gate before producing tuning output, unless the prompt is only asking for a static classification test.

  2. Classify broad optimization requests as ready_to_plan; reserve approval_required for prompts that explicitly name a destructive operation to execute before planning.

  3. Plan the full canonical chain through optimization-report, preserving the structured milestone order and the profile-stage:baseline / profile-stage:after labels when listing milestones.

  4. Invoke downstream skill bodies only when their phase is reached, and keep raw runtime artifacts on disk while reading compact summaries.

Frontmatter keeps version and tools at top level for agentskills.io runtime compatibility. NVCARPS discoverability fields live under metadata.

Output Format

Return a plan or status summary that names the selected entry skill, uses ready_to_plan for generic optimization requests, includes the full milestone chain through optimization-report, and labels profile phases as profile-stage:baseline and profile-stage:after. For structured outputs, the broad-optimization milestone subsequence is omniverse-usd-performance-tuning -> profile-stage:baseline -> usd-structure-assessment -> usd-validation-runner -> restructure-decision -> apply-restructure -> so-run-validators -> so-interpret-validators -> so-run-operations -> profile-stage:after -> compare-profiles -> optimization-report. End-to-end execution should produce an optimized stage when mutation runs and a report conforming to the optimization-report reference's schema (scripts/optimization-report.schema.json within that reference).

Use this workflow for broad performance asks such as slow loading, low FPS, high memory, GPU crashes, conversion quality, or "optimize my scene."

Entry skill rule

This skill is the named entry point for broad performance work whenever the agent has any verified way to do that work. Runtime probing details live in setup-usd-performance-tuning; this rule only decides which skill owns the user-facing performance request.

  • If the setup probe shows any verified runtime path - Kit, standalone, or even a partial stack such as Asset Validator only - enter here. If the user's requested tool is missing, return the specific blocked_code (blocked_missing_scene_optimizer, blocked_missing_so_operation, etc.) instead of substituting another workflow.

  • Enter at setup-usd-performance-tuning only when no runtime path is verified and runtime choice/setup is the first unresolved problem.

  • For omniverse:// assets, enter at omniverse-authentication first. Authentication precedes setup and triage for remote assets.

The decision is about ownership, not order. Setup, authentication, and triage all run in their normal phase order; this rule only fixes which skill the agent names as the entry skill in its response.

Runtime context — session-start gate (mandatory)

Before any other tuning output, follow the mandatory session-start gate in skills/omniverse-usd-performance-tuning/references/setup-usd-performance-tuning/references/runtime-context-header.md. That reference owns output_path, the canonical setup-preflight.json location, Format A/Format B, and the "do not improvise a silent probe" anti-pattern.

Required outcomes:

  • Missing or unreadable preflight: invoke setup-usd-performance-tuning.

  • Present preflight: print Format A and wait for the user to choose Continue, Change Kit, Switch to standalone, or Re-run probe.

  • Confirmed runtime in the same session: use compact Format B for follow-up status.

[Kit: {runtime_context.kit.application} {runtime_context.kit.version}  |  SO: {runtime_context.sceneOptimizer.version}  |  AV: {runtime_context.assetValidator.version}]

Runtime artifact token budget

Before reading Kit logs, Asset Validator CSVs, Scene Optimizer logs, Tracy CSVs, or other runtime output, follow references/runtime-artifact-token-budget.md. Keep raw artifacts on disk, read summary JSON first, and use bounded log snapshots instead of full dumps or live streams.

Plan-time vs execution-time approval

approval_required at planning time is reserved for requests that explicitly name a destructive operation. Use the following rule when deciding between ready_to_plan and approval_required:

  • approval_required at planning time — the user's request itself names a destructive operation: "flatten this stage", "decimate the meshes", "merge prototypes", "delete unused prims", or any specific named mutation that cannot be undone within the same workflow. In this case the agent's first response must be an approval prompt that names the operation, before the agent commits to a plan that executes it.

  • ready_to_plan at planning time — the user's request is general: "optimize this scene", "make it load faster", "reduce GPU memory", "improve interactivity". The agent lays out the full plan, including any destructive operations the plan would invoke (for example so-run-operations with mergeMaterials), without withholding the plan itself. Approval for each destructive operation is requested alongside plan approval.

The distinction is between authorising a plan and authorising a destructive action. A general optimisation request authorises planning; it does not authorise execution of specific destructive operations.

For structured runtime-test responses and similar planning summaries:

  • A future restructure-decision prompt is a planned user-decision gate, not a reason to set the top-level response decision to approval_required for a generic optimization request.

  • For a generic optimization request, set decision: "ready_to_plan" and include the full intended chain in both committed_milestones and planned_phases, through optimization-report.

  • It is valid for gates_observed to include asks_user_for_restructure_decision while the top-level decision remains ready_to_plan.

  • Whenever a chain names profile phases, use the exact labels profile-stage:baseline and profile-stage:after; do not emit the ambiguous bare profile-stage token.

  • Start structured milestone lists with omniverse-usd-performance-tuning as the owning entry skill. Include setup-usd-performance-tuning only as additional Phase 0 context, not as a replacement for the entry skill milestone.

  • For broad optimization requests, preserve the milestone subsequence from Output Format above exactly, with optional extra analysis steps inserted only where they do not reorder it.

  • Do not list so-run-validators or so-interpret-validators before restructure-decision in broad optimization milestone summaries. Phase-aware validator routing still happens through usd-validation-runner; the SO validator executor/interpreter milestones appear after the restructure decision path in the structured plan contract.

Output expectation

End-to-end optimization work should produce both an optimized USD stage, when mutation is executed, and a structured optimization report conforming to the optimization-report reference's scripts/optimization-report.schema.json. The HTML report must be rendered from references/report-templates/optimization-report.html.template via render_preview.py — never hand-write HTML. Diagnosis-only work should still end with a report or summary that states no optimized stage was written.

Purpose

Route digital twin USD performance requests into the right diagnostic and optimization workflow while preserving evidence before mutation.

Prerequisites

  • Stage path or enough context to identify the target asset.

  • User goal: diagnosis only, validation, profiling, or processor execution.

  • Runtime availability status from setup-usd-performance-tuning when not already known.

  • Permission status for in-place mutation vs writing a separate optimized output.

Examples

  • "This USD loads slowly; triage what to check first."

  • "Route a low-FPS CAD scene through the performance workflow."

Triage order

  1. Runtime gate. Follow the mandatory session-start gate above before validation, profiling, or optimization. Do not scan, probe, install, or pick Kit/standalone runtimes directly in this skill; setup-usd-performance-tuning owns probe/chooser/install dispatch and writes the preflight consumed here.

  2. Identify the target problem:

    • Load time.

    • FPS or interactivity.

    • GPU or system memory.

    • Crash or device lost.

    • CAD conversion quality.

    • Validation failure.

  3. Gather minimum context:

    • Stage path and size.

    • Whether the stage is local, mounted, or omniverse:// remote. For remote assets, route through omniverse-authentication before first open.

    • Kit or USD runtime.

    • Whether the workload is CAD, VFI, AIF, Isaac, or generic OpenUSD.

    • Whether in-place mutation is allowed.

    • Whether the user wants diagnosis only or processor execution.

  4. Route:

    • USD composition questions: usd-structure-assessment (composition is now part of the SA umbrella; deeper detail in skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/composition-audit.md).

    • Validation and content issues: usd-validation-runner (master router; routes to validate-* family or so-run-validators based on intent).

    • Edit/output decisions: usd-edit-target-planner (also owns variant/payload gates).

    • Repeated copied hierarchy or high mesh count with no instancing: usd-hierarchy-dedupe-candidates.

    • Restructure decision (monolithic stage, asset boundary materialization): restructure-decision.

    • CAD converter settings: read references/cad-conversion/README.md (niche pre-USD concern; see reference for details).

    • Scene Optimizer: so-run-validators, so-interpret-validators, so-run-operations.

Optimization ordering

Follow the canonical ordering in workflow.md § Operation ordering invariants. The high-level rule: prototypes first → per-asset validation → stage-level operations last. The workflow reference owns the full invariant list (meshCleanup before decimateMeshes, deduplication before decimation, never merge if instanced, etc.) and the analysis-only ops catalogue.

Rules

  • Always run composition audit before mutation.

  • Always validate before and after processor execution.

  • Optimize prototypes before per-asset validation.

  • Do not run whole-stage mesh deduplication on very large CAD scenes before checking for hierarchy-level reuse.

  • Do not recommend a fixed optimization stack without bottleneck evidence.

  • Do not invent numeric thresholds or expected percentage wins.

  • Prefer canonical SO ops over specialty / documentary ones. The op curation in references/operations/_curation.json classifies every op as canonical, specialty, analysis, documentary, or deprecated. When more than one op could resolve the same finding, recommend the canonical one first and only reach for a specialty op when the user explicitly asks or the rationale warrants it. Specifically:

    • For vertex welding, prefer canonical meshCleanup with explicit flags over the standalone mergeVertices op. The standalone op is a legacy/specialty surface; use upstream usd-optimize for the operation mechanics and local approval policy before mutating.

    • For hierarchy dedupe, recommend usd-hierarchy-dedupe-candidates + apply-restructure (the USD-authored rewrite path).

    • For per-mesh dedupe, recommend deduplicateGeometry (canonical) over findCoincidingGeometry (analysis — produces a report, not a change).

    • Do not recommend documentary-status ops (e.g., boxClip, deletePrims, removeAttributes, removeUntypedPrims, merge outside its narrow non-instanced case) without an explicit user request. Documentary ops survive in the per-op references/operations/<key>.md routing stubs for completeness but are excluded from agent-initiated recommendations.

    • Specialty ≠ documentary. Ops classified as specialty in _curation.json either (a) have validator-finding evidence that wires them into the so-interpret-validators chain (e.g. sparseMeshes, optimizePrimvars), or (b) are load-bearing escape hatches needed for specific downstream contexts (e.g. primitivesToMeshes when output must be UsdGeomMesh, utilityFunction for instancing toggles and material rebinding, pythonScript for so-create-proxy recipes). Recommend specialty ops when their validator fires OR when their downstream context applies — the suppression above only targets documentary ops.

Limitations

  • Does not replace downstream reference instructions; load each required reference before executing it.

  • Does not install runtimes directly; follow setup or install references when requirements are missing.

  • Does not authorize mutation when the user has not allowed writes.

Troubleshooting

  • If runtime status is unclear, run setup-usd-performance-tuning before profiling or validation.

  • If the reported problem is vague, gather stage path, workload type, and whether diagnosis or execution is requested.

  • If the workflow suggests mutation before evidence, return to baseline profiling and composition audit first.

References

Before routing, read:

  • skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/optimization-tradeoffs.md — identify which pipeline phase the scene is in (extraction, structuring, or optimization). The right action depends on the phase.

  • skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/factory-level-structuring.md — understand the three pillars (assets, aggregation, animation) and the seven-step structuring pattern.

If you have network access, prefer the live URLs (noted in each reference file) for the most current version.

Required execution flow

Read references/workflow.md for the canonical Phase 0-7 flow, including Kit/standalone branches, validator-stack routing, operation ordering, termination conditions, duration hints, and the optional iteration pattern. The compact root map at references/skill-map.md only routes agents into this workflow.

Do not treat downstream phase names as plain checklist labels. Before executing each step, load that phase's nested README.md reference and follow its instructions. Claude Code only exposes the public catalog skill; it does not recursively inject profile-stage, usd-structure-assessment, or other nested references.

The final deliverable must come from optimization-report: save both the structured JSON report and the generated Markdown summary. Do not substitute an ad hoc SUMMARY.md or chat-only recap for the optimization report.

For deeper subtopic guidance, consult the references:

  • skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/composition-audit.md, skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/layer-health.md - subtopic detail for SA's Phase 1 checklist.

  • skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/instancing-readiness/references/instancing-tradeoffs.md - merge safety, decision tree for instancing choices.

  • skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/usd-edit-target-planner/references/variants-payloads.md - deeper variant/payload trade-offs (gates are inline in usd-edit-target-planner).

  • references/cad-conversion/README.md - CAD converter settings.

  • references/upstreams/usd-optimize.md - upstream SO mechanics and prebuilt package resolution.

  • skills/omniverse-usd-performance-tuning/references/usd-validation-runner/references/so-run-validators/references/infrastructure.md - local handoff for SO validator infrastructure.

  • skills/omniverse-usd-performance-tuning/references/usd-validation-runner/references/validation-scoping.md - tier 1/2/3 plan + scene-aware adjustment.

  • skills/omniverse-usd-performance-tuning/references/optimization-report/references/optimization-report-template.md - the data contract every phase populates.

For full Kit runtime profiling (FPS, frame time, Hydra/RTX metrics), refer to the external profiling skills at NVIDIA/omniperf.

Files

references/setup-usd-performance-tuning/references/runtime-context-header.md

<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->

<!-- SPDX-License-Identifier: Apache-2.0 -->

Runtime context header

Audience: every agent that prompts the user inside the USD Performance Tuning workflow. Rule: print one of the two formats below before asking the user anything that depends on the active Kit / Scene Optimizer / Asset Validator runtime — runtime choice at Phase 0, restructure decision at Phase 2e, destructive-op approval in so-run-operations, verdict in compare-profiles, and the runtime block in optimization-report. The user must always be able to see which Kit application and which package versions are about to act on their asset.

Why this exists

Three concrete pains have repeatedly surfaced when the runtime isn't visible:

  • A user authorizes a destructive operation without knowing which Kit version is about to mutate their stage — when something goes sideways later, reproduction is guesswork.

  • The agent recommends an SO operation that the user's installed runtime doesn't ship. The user only finds out when the op silently no-ops mid-chain.

  • Two team members run the same workflow against the same asset and get different validator counts because they're on different Kit / AV versions, and neither tracked which.

Always-showing the runtime context puts that information where the decision happens.

Where artifacts live (the output_path workspace)

Every DTP run that writes anything (probe results, profiles, reports, optimized USDs, generated scripts) writes into a single output_path provided by the user. The output_path is the run's workspace; nothing DTP-generated should live anywhere else.

Required layout under output_path:

<output_path>/
├── setup-preflight.json         ← session-scoped runtime config (probe output)
├── scripts/                     ← agent-generated Python scripts
│   ├── probe_setup.py
│   ├── profile_quick.py
│   ├── sa_assess.py
│   └── ...
├── profiles/                    ← profile-stage captures
├── <asset_stem>.optimized.usdc  ← optimized USD outputs
├── baseline_profile.json
├── sa_report.json
├── dedupe_candidates.json
└── *.log                        ← per-skill logs alongside the scripts

Anti-patterns:

  • Do not create a _work/ directory inside the skill repo or the working directory. Every artifact lives under output_path.

  • Do not write setup-preflight.json under any other name (e.g., probe_result.json) or any other location. Downstream skills read this exact filename at this exact location.

  • Do not run agent-generated Python scripts inline only to discard the source. Write them to <output_path>/scripts/ so the run is reproducible / auditable.

When output_path is unknown: if the user's first request does not name an output_path and the request will write any artifact, the agent asks the user for one before continuing. Do not pick a default.

Mandatory session-start gate

Before any other user-facing output, the entry skill of every DTP session MUST run the session-start gate exactly once. The entry skill is whichever workflow skill the agent invokes first for the user's request — typically omniverse-usd-performance-tuning, but can be so-run-operations, so-run-validators, or usd-validation-runner when the user invokes one of those directly. Downstream skills (apply-restructure, so-interpret-validators, compare-profiles, optimization-report, etc.) inherit the gate's result via the preflight JSON and do not re-run it.

The gate's steps:

  1. Determine output_path. Read it from the user's request, or prompt the user if they did not name one. The path must be writable and outside the skill repo (otherwise the repo gets polluted with run artifacts).

  2. Check <output_path>/setup-preflight.json.

    • Missing or unreadable → invoke setup-usd-performance-tuning to run the full Step 1 flow (which will fire Step 1b's "provide path / scan / standalone / install" prompt when there's nothing to auto-detect). The setup skill writes its output to <output_path>/setup-preflight.json (canonical filename, canonical location). Do not improvise a probe, a different filename, or a different directory; the setup skill owns that flow.

    • Present and parseable → continue to step 3 below.

  3. Print Format A and ask the user to confirm.

    ─── Runtime context ───────────────────────────────────────────────────────
Kit application:    {kit.chosen.application} {kit.chosen.version}
  path:             {kit.chosen.path}
  build:            {kit.chosen.build}
Scene Optimizer:    {sceneOptimizer.extension} {sceneOptimizer.version}
Asset Validator:    {assetValidator.package} {assetValidator.version} via {assetValidator.source}
───────────────────────────────────────────────────────────────────────────

This runtime will be used for the work that follows. Continue, or change it?

  > 1. Continue with this runtime
    2. Change Kit installation (re-runs setup-usd-performance-tuning Step 1)
    3. Switch to standalone (pip-installed libraries, no Kit)
    4. Re-run the runtime probe (refresh versions, re-detect)

  4. Route the answer.

    • Option 1 → proceed to the actual work; subsequent messages in the same session may use Format B and skip the prompt.

    • Option 2 / 3 / 4 → invoke setup-usd-performance-tuning and overwrite the preflight before continuing.

The gate fires once per session. Subsequent skill invocations within the same conversation reuse the preflight (and the user's "continue" answer) without re-prompting; they use Format B for routine status.

Anti-pattern — do not skip the gate just because preflight exists. A user who's coming back to a directory days later has no way to know which Kit was chosen earlier or whether the previous probe is still correct. Surfacing Format A + confirmation at session start is the only way to make that visible.

Anti-pattern — do not improvise a silent probe. If the agent finds itself running python.bat directly, scanning LOCALAPPDATA, or Test-Path-checking kit.exe outside of setup-usd-performance-tuning, the session-start gate has been skipped and the agent must back out and run the gate instead.

Source of truth

Both formats below read from <output_path>/setup-preflight.json (canonical filename + location; see Where artifacts live above). The fields the header consumes are:

  • kit.chosen.application — friendly name (e.g. USD Composer, Isaac Sim, Kit SDK)

  • kit.chosen.version — release version (e.g. 110.1.0)

  • kit.chosen.path — absolute install path

  • kit.chosen.build — full build identifier when present (e.g. 110.1.0+main.10181.f4b28ef2.gl.windows-x86_64.release)

  • sceneOptimizer.extension — extension name (e.g. omni.scene.optimizer.core)

  • sceneOptimizer.version — extension version

  • assetValidator.package — package or extension name

  • assetValidator.version — version

  • assetValidator.source — kit-extension or pip (informs the user whether AV runs through Kit or as a standalone Python install)

If <output_path>/setup-preflight.json is unavailable when an agent reaches a prompt that requires the header, it must invoke setup-usd-performance-tuning first. The header must never be skipped or partially filled.

Format A — full block

Use at every decision point where the user is authorizing something that mutates state or sets the workflow direction. Required at:

  • setup-usd-performance-tuning runtime-choice prompt

  • restructure-decision Phase 2e prompt

  • so-run-operations destructive-op confirmation

  • The first user-facing message in any session that starts mid-workflow

─── Runtime context ───────────────────────────────────────────────────────
Kit application:    {kit.chosen.application} {kit.chosen.version}
  path:             {kit.chosen.path}
  build:            {kit.chosen.build}
Scene Optimizer:    {sceneOptimizer.extension} {sceneOptimizer.version}
Asset Validator:    {assetValidator.package} {assetValidator.version} via {assetValidator.source}
───────────────────────────────────────────────────────────────────────────

If the user has more than one Kit installed and the workflow has not yet committed to one, also append the choice prompt described in setup-usd-performance-tuning Step 1.5 below the block.

Format B — compact one-liner

Use for routine status messages, ack messages, and follow-up prompts in the same session where the user has already seen Format A.

[Kit: {kit.chosen.application} {kit.chosen.version}  |  SO: {sceneOptimizer.version}  |  AV: {assetValidator.version}]

Required at:

  • omniverse-usd-performance-tuning initial acknowledgement

  • compare-profiles verdict header

  • Per-prototype progress lines in so-run-operations batch mode (Phase 4b)

When to refresh the block

The runtime can change mid-session if the user installs a new Kit or switches Python environments. The agent must re-print Format A whenever:

  • setup-usd-performance-tuning is re-invoked

  • An install reference (install-kit, install-so-via-kit, install-so-standalone, install-asset-validator-standalone) reports a successful install

  • The agent explicitly requests a runtime switch from the user

Otherwise the cached preflight is fresh enough for the duration of the workflow.

Examples

A — fresh session, single Kit install detected
─── Runtime context ───────────────────────────────────────────────────────
Kit application:    USD Composer 110.1.0
  path:             D:\build\chk\usd_composer-fat\110.1.0+main.10181.f4b28ef2.gl.windows-x86_64.release\kit
  build:            110.1.0+main.10181.f4b28ef2.gl.windows-x86_64.release
Scene Optimizer:    omni.scene.optimizer.core 110.0.4
Asset Validator:    omniverse-asset-validator 1.x.y via kit-extension
───────────────────────────────────────────────────────────────────────────

I will run usd-structure-assessment on /path/to/asset.usd. OK?
A with a multi-Kit choice prompt
─── Runtime context ───────────────────────────────────────────────────────
Kit application:    (not yet chosen — see Kit candidates below)
Scene Optimizer:    (version determined by Kit choice)
Asset Validator:    (version determined by Kit choice)
───────────────────────────────────────────────────────────────────────────

Multiple Kit installations were found. The newest one is pre-selected.
Press Enter to accept, or type the number of a different one.

  > 1. USD Composer 110.1.0    D:\build\chk\usd_composer-fat\110.1.0+main.…\kit         (newest, pre-selected)
    2. USD Composer 109.0.4    %LOCALAPPDATA%\ov\pkg\usd-composer-2025.1.0\kit
    3. Isaac Sim 5.1.0         %LOCALAPPDATA%\ov\pkg\isaac-sim-2025.1\kit
    4. Use standalone libraries instead (no Kit application)
B — compact, mid-session
[Kit: USD Composer 110.1.0  |  SO: 110.0.4  |  AV: 1.x.y]

profile-stage: starting BASELINE capture in quick mode...

Anti-patterns

  • Do not print Format A more than once in the same session unless the runtime actually changed; users will start skimming it. Use Format B for everything after the first prompt.

  • Do not print just the version without the path. The path is what lets the user reproduce the run on another machine or check whether they're pointed at a build they don't expect.

  • Do not paraphrase the version. Print exactly what <output_path>/setup-preflight.json records. Paraphrasing creates ambiguity when someone later asks "which build?"

  • Do not skip the block in so-run-operations destructive-op confirmation. The user authorizing a destructive op must see the runtime explicitly at the moment of authorization, not earlier in the session.

Cross-references

  • setup-usd-performance-tuning README.md — the source of the version probe and the multi-Kit selection prompt.

  • optimization-report README.md — the report's runtime_context field mirrors these fields verbatim so post-hoc audits can reconstruct the run's runtime.

  • The optimization-report reference's scripts/optimization-report.schema.json — the schema definition for the runtime_context object.

Requirements and compatibility

Written for: OpenAI Codex

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

The author says: Orchestrator skill. Downstream phases may require Kit, Scene Optimizer, Asset Validator, USD Python, writable output paths, and omniverse:// authentication selected by setup-usd-performance-tuning.

Security

What our scanner noticed· Medium risk

  • Large base64-encoded blobs
  • Instructions that use the network
  • Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

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
OpenAI (Official)
Distributed by
OpenAI
Source
openai/plugins · plugins/nvidia/skills/omniverse-usd-performance-tuning · commit d420d13
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (written by AutoGineer)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

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

Download ZIP

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