Omniverse Cad To Simready

OpenAIOfficialCreated by OmniverseDistributed by OpenAI

Skill
Workflow
Software development
Apache-2.0
Medium risk
Has scripts

From the author

Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.

— the description by Omniverse

From the skill’s files

Taken from the skill’s own files (its description, section headings and stated usage). Not an AutoGineer summary, and not written by the author as one.

Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references. Use this workflow skill when the user wants an end-to-end pipeline from a source asset to a SimReady asset or package. This skill coordinates existing conversion, authoring, validation, conformance, rendering, and packaging references directly. Do not replace the workflow with a single monolithic runner command.

What it does

When to Use
Prerequisites
Minimum Viable Scope
First Action
Instructions
Output Format

When to use it

Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and…
Use this workflow skill when the user wants an end-to-end pipeline from a source asset to a SimReady asset or package.
This skill coordinates existing conversion, authoring, validation, conformance, rendering, and packaging references directly.
This skill is documentation-driven and does not ship scripts/run.py.
It should not depend on a repository checkout.
When a stage needs deterministic execution, run the portable script from that stage reference's installed directory.

Advantages

The skill’s files do not state this.

Usage examples

The skill’s files do not state this.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/openai/omniverse-cad-to-simready/download

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

mkdir -p .agents/skills && unzip omniverse-cad-to-simready.zip -d .agents/skills

Documentation by Omniverse

CAD to SimReady

When to Use

Use this workflow skill when the user wants an end-to-end pipeline from a source asset to a SimReady asset or package. This skill coordinates existing conversion, authoring, validation, conformance, rendering, and packaging references directly. Do not replace the workflow with a single monolithic runner command.

This skill is documentation-driven and does not ship scripts/run.py. It should not depend on a repository checkout. When a stage needs deterministic execution, run the portable script from that stage reference's installed directory. Shell is declared because this workflow invokes installed stage reference scripts directly; it still must not grow a monolithic runner.

Prerequisites

Prefer running the preflight reference first for deterministic setup. It installs or verifies local upstream checkouts, writes a cad-to-simready-preflight.json manifest, and exports PHYSICAL_AI_PREFLIGHT_MANIFEST plus PHYSICAL_AI_REQUIRE_PREFLIGHT=1 for downstream references.
Python 3.12 and uv (per repo README.md).
NVIDIA_API_KEY from https://build.nvidia.com when local Content Agents deployment will run. Already-running endpoints may instead use explicit endpoint variables plus usage tokens such as NGC_API_KEY, NVCF_API_KEY, or CONTENT_AGENTS_*_TOKEN.
Docker, NVIDIA Container Toolkit, and an NVIDIA GPU for Content Agents and OVRTX stages.
Local upstream checkouts under ${PHYSICAL_AI_SKILL_HUB_UPSTREAM_ROOT:-$HOME/.physical-ai-skill-hub/upstreams} when a downstream stage needs upstream scripts or specs.

Minimum Viable Scope

Conversion-only is a valid workflow request. When the user asks only to convert or smoke-test source asset conversion, set property_assignment_intent=skip, do not deploy Content Agents, run convert-to-usd, then run validate-usd-minimum on the generated USD if conversion succeeds.

Do not imply that uv sync installs every source converter runtime. URDF, MuJoCo/MJCF, and the repo Python dependencies are handled by the project environment, but NVIDIA-backed source conversion requires an installed and validated NVIDIA-Omniverse/usd-convert-cad checkout. If that runtime is missing or does not support the source, preserve the blocked conversion report and its install_hint instead of attempting an unrequested local build or substituting another converter.

First Action

For any broad CAD/source-asset to SimReady request, assume property_assignment_intent=run unless the user explicitly asks for conversion-only, validation-only, or no material/physics assignment.

Before invoking converter, validation, Content Agents, OVRTX, packaging, or FET helper scripts, run the preflight reference or verify an existing PHYSICAL_AI_PREFLIGHT_MANIFEST. Treat preflight as the mandatory dependency bootstrap step, not as workflow routing. If the user explicitly asks not to deploy services or asks for conversion-only/validation-only, use --skip-content-agents. When PHYSICAL_AI_REQUIRE_PREFLIGHT=1 is set and a required component is not ready in the manifest, downstream references must block with the preflight guardrail instead of rediscovering upstreams or services directly.

When property_assignment_intent=run, the first operational action after confirming the source path and resolving intent is to verify or deploy Content Agents services. Do this before asset-context inspection, converter dependency checks, conversion, validation, conformance, rendering, packaging, or upstream source builds.

Use healthy existing endpoints when available. If OVRTX, Material, or Physics endpoints are missing or unhealthy, run deploy-content-agents first and do not continue until the shared standalone OVRTX renderer plus independent Material and Physics service containers are healthy and exported through CONTENT_AGENTS_*_BASE_URL. Deploy the Texture Agent too when texture generation is requested.

If required deployment authentication is missing, ask the user for NVIDIA_API_KEY and wait. If a provided endpoint requires usage auth, ask for the appropriate usage token instead. If deployment cannot produce healthy services, report Content Agents readiness as blocked instead of proceeding to conversion.

Instructions

Confirm the source asset path exists, resolve output_root, and classify the request as end-to-end, conversion-only, validation-only, or packaging.
Resolve property_assignment_intent before running any asset inspection, converter probe, conversion, validation, conformance, rendering, or packaging step.
Run preflight for the selected workflow targets, unless a ready PHYSICAL_AI_PREFLIGHT_MANIFEST is already configured. Source the generated env file before running downstream scripts. Treat preflight as dependency setup only: it may use a provided --source-asset, --source-format, or --conversion-tools value to scope dependency checks, but convert-to-usd and the upstream converter references still decide actual conversion support.
Verify or deploy Content Agents services first when property_assignment_intent=run; block on missing authentication or unhealthy services instead of continuing.
Read references/workflow.md and references/commands.md, then run only the stage references needed for the current request.
Run identify-asset-context on the original source asset when web search is available or property assignment will run.
Route the source through convert-to-usd, or skip conversion for existing USD input and treat the source path as the current USD path.
Run validate-usd-minimum before expensive downstream work. Treat this as a viability gate only: record unit/profile issues such as metersPerUnit != 1.0, but do not run simready-conform-profile, FET001, or any other FET repair before Content Agents assignment when property assignment will run.
Run Content Agents material, physics, and optional texture assignment on the converted/minimum-valid USD when requested or required.
Run simready-conform-profile on the latest simulation USD path after property assignment and preserve every selected FET repair report.
Run validation gates in order: omni-asset-validate, omni-asset-validate-geometry, omni-asset-validate-physics, and simready-validate.
Rerun simready-conform-profile when simready-validate reports a repairable requirement, then rerun profile validation on the newest authored USD.
Run ovrtx-render-service when preview, thumbnail, or inspection images are requested. When package outputs are requested, run assemble-package-source next to create the clean deliverable/ package source from the final USD and thumbnail, then run nv-core-package-sample and nv-core-package-sample-validation on that deliverable folder only.
Emit the consolidated workflow report with the final USD path, all stage reports, validation findings, rerun reasons, and next work.

Use the simready-conform-profile reference only after property assignment when property_assignment_intent=run. It routes feature repair to upstream SimReady Foundation FET skills such as simready-foundation-conform-fet-000-core, simready-foundation-conform-fet-001-minimal, simready-foundation-conform-fet-004-simulate-multi-body-physics, and simready-foundation-conform-fet-005-simulate-grasp-physics from branch main.

If simready-validate reports a repairable requirement after the first conformance pass, feed the structured requirement IDs back into the simready-conform-profile reference before writing the final result. In particular, GSP.001 is owned by upstream simready-foundation-conform-fet-005-simulate-grasp-physics; run that skill when a vision-capable agent can inspect visual evidence or explicit grasp points were provided, otherwise record the FET005 step as blocked by missing vision/points instead of treating it as an optional preview task. For RB.MB.001, route the failure to upstream simready-foundation-conform-fet-004-simulate-multi-body-physics. Do not assume multiple visual prims are multiple rigid bodies; inspect UsdPhysics.RigidBodyAPI applications. When the Physics Agent report shows composed topology optimization or the USD has existing component colliders/part roots and the profile validator reports FET004/RB.MB.001, FET004 should promote those existing components into rigid bodies without creating geometry. Do not mark the gate not applicable until after confirming there are fewer than two reusable body candidates.

Output Format

Emit a consolidated workflow report in Markdown, and include JSON when the workflow writes structured artifacts. The report must include:

Overall status: passed, blocked, failed, or needs_rerun.
Request summary: source asset path, detected source format, output root, selected SimReady profile/version, and property assignment intent.
Ordered stage results: stage reference, input artifact, output USD or USDZ path, report path, status, blocker reason, and rerun reason when applicable.
Content Agents readiness and property assignment results with service URLs, tokens, and credentials redacted.
Conformance and validation findings grouped by gate, requirement ID, selected FET repair reference, repair-loop attempt, and final disposition.
Final artifacts: final reported USD path, render preview path when requested, package root and package validation report when packaging ran, Markdown report path, JSON report path when present, and recommended next work.

Detailed References

Read only the references needed for the current request:

references/preflight/README.md: deterministic local setup, manifest/env contract, Linux and Windows wrappers, Content Agents deployment opt-out, and guardrail behavior.
references/workflow.md: inputs, source routing, detailed workflow, validation policy, output report fields, approval points, and next steps.
references/commands.md: concrete portable script command patterns for each stage.
references/assemble-package-source/README.md: two-zone package source assembly, canonical root USD naming, thumbnail placement, and self-contained deliverable checks.

Publishing Layout Notes

Use skills/omniverse-cad-to-simready/ as the source of truth for this product repo's skill. The .agents/skills symlink is a compatibility alias for local agentskills.io-style discovery, and .codex/skills and .claude/skills are agent-specific compatibility aliases.

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

The nested references/ tree is intentional. It keeps one public catalog skill while retaining script-bearing atomic stage references, upstream handoff notes, and router documentation under the workflow. Do not flatten those references or promote nested README references to sibling SKILL.md files unless the repo's publishing model changes.

Limitations

This workflow coordinates existing conversion, property assignment, conformance, validation, rendering, and packaging skills; it does not replace them with a single monolithic runner command.
Stop at the first failing deployment, conversion, property-assignment, or conformance authoring gate unless the user explicitly asks for best-effort continuation.
Upstream simready-foundation-conform-fet-005-simulate-grasp-physics needs visual review or explicit grasp points before it can author a meaningful grasp vector.

Troubleshooting

Symptom	Cause	Fix
Downstream reference reports that cad-to-simready preflight has not prepared a component	`PHYSICAL_AI_REQUIRE_PREFLIGHT=1` is set, but the manifest is missing or the required runtime/service is not `ready`	Run `preflight/scripts/preflight.py`, source the generated env file, or explicitly disable service deployment with `--skip-content-agents` only when Content Agents are out of scope.
Workflow stops on `GSP.001` and reports the failure as unclassified	Visual evidence or explicit grasp points were not provided to FET005	Run upstream `simready-foundation-conform-fet-005-simulate-grasp-physics` only after a vision-capable agent has reviewed the asset, or pass explicit grasp points. Otherwise report the FET005 step as `blocked`, not failed.
Validation fails after a meaningful USD artifact already exists	Workflow stopped at the first validation finding	Continue remaining diagnostic gates and mark the result `needs_rerun`. Do not stop at validation findings once a USD artifact has been produced.
Property-assignment stage fails with a missing service endpoint	Content Agents service was not deployed before conversion	Run `deploy-content-agents` first. Do not start asset inspection, conversion, validation, conformance, rendering, or packaging before Content Agents readiness when property assignment will run.
Material Agent reports that rendering produced `0 images` after unit or profile repair	A FET repair, commonly FET001 unit normalization, was applied before Material Agent and changed the USD layering/scene state consumed by the service	Rerun assignment from the converted/minimum-valid USD: Material Agent first, then Physics Agent, then run `simready-conform-profile` and FET repairs on the latest service-authored USD.
Material or Physics Agent local optimized path reports `Permission denied: '/app/.build-resources/scene_optimizer_core/python'`	Local Docker Scene Optimizer bundle permissions prevent the non-root service user from reading the packaged SO runtime	Repair the relevant local container with `docker exec --user root content-material-agent-service chmod -R a+rX /app/.build-resources/scene_optimizer_core` or `docker exec --user root content-physics-agent-service chmod -R a+rX /app/.build-resources/scene_optimizer_core`, then rerun the same optimized agent command. Do not treat the no-optimizer fallback as the root cause for instanced/prototype assets.
`RB.MB.001` fails even though the asset has many prims	The profile counts `UsdPhysics.RigidBodyAPI` prims, not visual or collider prims; Physics Agent may author one root rigid body	Route to upstream `simready-foundation-conform-fet-004-simulate-multi-body-physics`. First ensure Physics Agent used composed-topology optimization when applicable, then promote existing component colliders/part roots when the active profile reports FET004/RB.MB.001 and no geometry must be invented.

Hard Rules

Prefer the preflight manifest for local upstream roots, converter executables, SimReady validation runtime, OVRTX endpoint, and Content Agents service URLs. When PHYSICAL_AI_REQUIRE_PREFLIGHT=1 is set, do not bypass the manifest with direct upstream discovery.
Do not run asset inspection, converter probes, local upstream builds, conversion, validation, conformance, rendering, or packaging before Content Agents readiness when property assignment will run.
Use stage-specific installed reference scripts directly. Do not add or call a single omniverse-cad-to-simready runner command.
For source conversion, delegate to the convert-to-usd reference; do not substitute another converter for CAD or mesh formats.
For property assignment, use Content Agents references as separate atomic steps: material first, then physics, then texture only when requested.
When property assignment will run, do not run simready-conform-profile or any FET helper before Content Agents. Validate minimum USD first, then run Content Agents on that converted/minimum-valid USD, then apply FET repairs to the latest service-authored USD.
When property assignment will run, do not run simready-validate or any SimReady profile validation before Content Agents. The only validation gate allowed before service calls is validate-usd-minimum, which is a basic USD viability check.
Stop at the first failing deployment, conversion, property-assignment, or conformance authoring gate unless the user explicitly asks for best-effort continuation.
Do not stop at validation findings after a meaningful USD artifact exists. Continue remaining diagnostic gates and mark the result needs_rerun.
Do not leave a GSP.001 profile failure as an unclassified final finding. Route it to upstream simready-foundation-conform-fet-005-simulate-grasp-physics; if the current agent cannot inspect renders or no explicit grasp points are available, report a blocked FET005 repair with the visual evidence path or missing input reason.
Preserve every stage report and pass the concrete output USD path from each report into the next stage.

Files

references/content-agents/README.md

Content Agents

When to Use

Use this router reference after USD conversion and minimum USD validation when an asset needs NVIDIA Omniverse Content Agents service calls. Select the right nested call reference, preserve each service report, and hand the newest USD or USDZ artifact to the next workflow stage.

This is not the deployment workflow and not a replacement for the service-specific call references. If an endpoint is missing, hand off to deploy-content-agents for the required target, then return to this router and run the selected service call.

This installed router reference ships a narrow scripts/run.py control-plane wrapper for deterministic service sequencing and report generation. It still delegates service calls to the portable scripts/run.py from each selected service reference; it does not reimplement Material, Physics, or Texture Agent behavior.

Prerequisites

Python 3.12 and uv (per repo README.md).
Prefer a ready PHYSICAL_AI_PREFLIGHT_MANIFEST from the preflight reference. The client wrappers consume prepared CONTENT_AGENTS_*_BASE_URL endpoints from that manifest before falling back to direct environment variables. When PHYSICAL_AI_REQUIRE_PREFLIGHT=1 is set, missing or unhealthy services block at the preflight guardrail.
A required .usd, .usda, .usdc, or .usdz input asset.
Reachable Material, Physics, Texture, or OVRTX endpoints through CONTENT_AGENTS_*_BASE_URL, unless this router hands off to deployment first.
Bearer auth through explicit usage token environment variables when a provided endpoint requires auth: CONTENT_AGENTS_TOKEN, NGC_API_KEY, NVCF_API_KEY, or selected service-specific variables such as CONTENT_AGENTS_MATERIAL_AGENT_TOKEN, MATERIAL_AGENT_TOKEN, CONTENT_AGENTS_PHYSICS_AGENT_TOKEN, PHYSICS_AGENT_TOKEN, CONTENT_AGENTS_TEXTURE_AGENT_TOKEN, or TEXTURE_AGENT_TOKEN.

Routing

Choose the smallest route that satisfies the user request and selected workflow profile:

Request or evidence	Route
Visual appearance, material prediction, or material bindings	`material-agent-client`
Rigid bodies, colliders, mass, density, friction, restitution, or simulation physics properties	`physics-agent-client`
Textured output, texture artifacts, or textured USDZ generation	`texture-agent-client`
Broad Content Agents enrichment for SimReady or simulation use	`material-agent-client` then `physics-agent-client`; add `texture-agent-client` only when textured output is requested
Missing Material, Physics, Texture, or OVRTX service endpoint	`deploy-content-agents` for the missing target, then rerun the selected call reference
Deployment-only request	`deploy-content-agents`; do not treat this router as the deployment workflow

Prefer explicit user intent over default ordering. For simulation-readiness, run visual material assignment before physics assignment so the Physics Agent can use the materialized USD when available. Run texture generation after material assignment, and do not replace the physics-authored USD path for simulation validation unless the user explicitly wants to validate the textured USDZ.

Run the local router when more than one Content Agents call is selected so path handoff is deterministic:

python3 /path/to/skills/omniverse-cad-to-simready/references/content-agents/scripts/run.py \
  /path/to/material_input.usd \
  --output-dir /path/to/output/content-agents \
  --call material \
  --call physics \
  --report /path/to/output/content-agents/content-agents.json

Add --call texture only when textured output or textured packaging is requested. The consolidated output_usd_path remains the latest simulation USD when physics ran; textured_usdz_path is reported separately.

Inputs

Collect:

Input	Requirement
`asset_path`	Required `.usd`, `.usda`, `.usdc`, or `.usdz` input.
`output_root`	Required directory for service reports and downloaded artifacts.
`material_intent`	Whether to run, skip, or require visual material assignment.
`physics_intent`	Whether to run, skip, or require physics property assignment.
`texture_intent`	Whether to run, skip, or require texture generation.
`asset_context_report`	Optional context report from `identify-asset-context`; use its `material_physics_prompt` when present.
`service_endpoints`	Optional Material, Physics, Texture, and OVRTX URLs from env or user input. Check `CONTENT_AGENTS_MATERIAL_AGENT_BASE_URL`, `CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL`, and `CONTENT_AGENTS_TEXTURE_AGENT_BASE_URL`.
`NVIDIA_API_KEY` availability	Required only before local deployment when service endpoints are missing. Do not use it as the default bearer token for already-running endpoints.

Instructions

Confirm the asset exists and is USD-family.
Determine the requested Content Agents calls from user intent, workflow defaults, and selected SimReady profile.
Resolve required service endpoints from explicit inputs or CONTENT_AGENTS_*_BASE_URL.
For each missing required endpoint, use deploy-content-agents with the matching target. Require a healthy service before returning to this router.
Do not run simready-conform-profile, FET001 unit normalization, or other FET repairs before the first Content Agents call. If minimum USD validation found metersPerUnit != 1.0 or another repairable SimReady issue, record it for the post-assignment conformance pass and continue with the converted/minimum-valid USD as the service input.
Use the material-agent-client reference first when material assignment is requested or needed. Its wrapper stages USD-layer uploads without MDL shader sourceAsset references when those references point at missing converter sidecars such as gltf/pbr.mdl; preserve the material_upload_info field from its report.
Use the physics-agent-client reference on the latest materialized USD path when physics assignment is requested or needed. Its wrapper automatically inspects USD topology and enables --optimize-usd --enable-deinstance --enable-split for composed CAD assets with GeomSubset, instance, or prototype component structure. It also stages Physics Agent uploads without MDL shader sourceAsset references and unresolved service-internal USDZ subasset paths from Material Agent outputs when those references would only affect visual material source files and can break main optimizer packaging. If the optimized Physics service path fails because Scene Optimizer is unavailable, the wrapper retries once without the optimizer flags and records both attempts. Preserve the usd_topology, physics_optimizer, physics_upload_info, and attempts fields from its report.
Use the texture-agent-client reference only when texture generation or textured packaging is requested.
Preserve each JSON report and report HTML or prediction artifact when available.
Summarize the selected route, service readiness decisions, generated artifacts, latest USD-family output, and next handoff.

When an existing service endpoint requires bearer auth, export an explicit usage token environment variable before running the command. Use CONTENT_AGENTS_TOKEN for a shared Content Agents token, service-specific CONTENT_AGENTS_*_TOKEN / *_AGENT_TOKEN variables for one service, or NGC_API_KEY / NVCF_API_KEY for provided NVCF endpoints. Do not use NVIDIA_API_KEY as the default client token; it is deployment auth. Do not pass secrets as command-line arguments in normal workflows because process listings can expose argv. In normal agent workflows, omit --token entirely, including empty strings or placeholders, and let the wrapper read the credential from env or a *_FILE variable. The wrapper still accepts --token for constrained automation, but that path should be treated as a fallback.

For detached or shared-host runs, prefer file-backed secrets such as CONTENT_AGENTS_TOKEN_FILE, NGC_API_KEY_FILE, MATERIAL_AGENT_TOKEN_FILE, PHYSICS_AGENT_TOKEN_FILE, or TEXTURE_AGENT_TOKEN_FILE. The wrappers read the token from those files when the corresponding environment variable is unset, which avoids exposing token values through shell expansion or process argv.

The service wrappers poll /pipeline/<session>/status until the service reaches a terminal state or the wrapper timeout expires. Transient polling failures such as SSL or connection timeouts, HTTP 408, HTTP 429, or HTTP 5xx responses are retried and recorded as warnings when the service later completes.

Multi-File USD Uploads

The service API accepts a single uploaded USD-family file. When the input USD uses external layers or asset dependencies, the wrappers inspect dependencies with OpenUSD and package the asset as USDZ for upload with UsdUtils.CreateNewUsdzPackage. The report records this in upload_info and upload_packaging. Prefer this packaging path over flattening because it keeps the authored layer structure and referenced assets together for the service. If OpenUSD cannot inspect or package dependencies, the wrapper reports the unresolved paths instead of silently flattening or dropping references.

Rate Limits

Wrapper retries cover transient status polling and delayed artifact download failures, including HTTP 429 responses visible to the wrapper. They do not retry per-prim VLM prediction failures that the Material Agent records inside a completed service session. If predictions are partially rate-limited, preserve the service report, rerun later or with a smaller asset/workload when possible, and use a higher-quota service key for large assemblies.

Command Patterns

Material assignment:

python3 /path/to/skills/omniverse-cad-to-simready/references/content-agents/references/material-agent-client/scripts/run.py asset.usda output_dir/content-agents/materials \
  --prompt "$ASSET_CONTEXT_PROMPT" \
  --report output_dir/content-agents/material-agent-client.json

For any existing endpoint that requires a different bearer token, set MATERIAL_AGENT_TOKEN, PHYSICS_AGENT_TOKEN, or TEXTURE_AGENT_TOKEN in the environment for the selected service instead of changing wrapper defaults. Use the matching *_FILE variable when the run is long-lived or process listings are visible to other users.

If the Material Agent optimized path was intended but local service logs show Scene Optimizer failed — continuing pipeline without optimization together with Permission denied: '/app/.build-resources/scene_optimizer_core/python', repair the running local Material Agent container permissions and rerun the same Material Agent command. This is a local Scene Optimizer bundle permission issue, not an asset-level reason to disable optimize_usd.

Physics assignment:

python3 /path/to/skills/omniverse-cad-to-simready/references/content-agents/references/physics-agent-client/scripts/run.py output_dir/content-agents/materials/output_material.usd output_dir/content-agents/physics \
  --render-backend remote \
  --convert-output-to-usd \
  --prompt "$ASSET_CONTEXT_PROMPT" \
  --report output_dir/content-agents/physics-agent-client.json

The Physics Agent wrapper auto-enables --optimize-usd --enable-deinstance --enable-split when USD inspection detects composed component topology, and it falls back to a no-optimizer retry when the service reports an optimizer setup failure. If the optimized attempt fails immediately at optimize_usd with no completed service steps, inspect the Physics Agent service logs before treating the no-optimizer retry as meaningful. On local Docker deployments, a known Scene Optimizer bundle permission issue can appear as Permission denied: '/app/.build-resources/scene_optimizer_core/python'; repair the running service container permissions and rerun the optimized command instead of disabling deinstance/split for instanced topology. Do not wrap the call in a shorter external timeout or terminate the wrapper while the service remains non-terminal and its current step or progress is advancing. Remote-rendered Physics stages such as identify_asset, build_dataset_usd, predict, restore_usd, and apply_physics can take many minutes on CAD or instanced assets; wait for the wrapper to return its JSON report unless the service reaches a terminal failure state or the wrapper's own timeout expires.

If the physics-authored USD still has one rigid body and the selected profile reports RB.MB.001, keep the service output and route that validation failure through simready-conform-profile / upstream simready-foundation-conform-fet-004-simulate-multi-body-physics only when the USD has at least two reusable component candidates. For a single mesh component or single GeomSubset component, simready-validate treats RB.MB.001 as non-blocking and records it under ignored_issues; do not retry the same Physics Agent call blindly.

If system python3 cannot import pxr, the Material and Physics wrappers try uv run --python 3.12 for OpenUSD topology inspection. The wrappers use the same fallback when preparing upload copies that strip missing MDL shader sources or clear unresolved service-internal USDZ subasset paths before packaging.

Texture generation:

python3 /path/to/skills/omniverse-cad-to-simready/references/content-agents/references/texture-agent-client/scripts/run.py output_dir/content-agents/materials/output_material.usd output_dir/content-agents/textures \
  --report output_dir/content-agents/texture-agent-client.json

Use the concrete output_usd_path, output_usdz_path, or downloaded artifact paths from each report. Do not assume placeholder filenames from examples.

Output Format

The router summary should include:

Field	Meaning
`input_asset_path`	Original USD-family input path.
`selected_calls`	Ordered Content Agents call references selected by this router.
`deployment_handoffs`	Any `deploy-content-agents` targets needed before calls.
`reports`	JSON report paths for each call reference.
`materialized_usd_path`	USD path after visual material assignment, when available.
`physics_usd_path`	USD path after physics assignment, when available.
`textured_usdz_path`	USDZ path after texture generation, when available.
`output_usd_path`	Latest USD-family artifact for downstream validation or conformance.
`next_step`	Usually `simready-conform-profile` or validation.

Limitations

This router is not the deployment workflow and not a replacement for the service-specific call references.
Run texture generation only when texture generation or textured packaging is requested.
Do not replace the physics-authored USD path for simulation validation with a textured USDZ unless the user explicitly requests that validation target.

Troubleshooting

Symptom	Cause	Fix
Service call fails because endpoint requires bearer auth and the wrapper's default token is wrong	Endpoint-specific credentials are not the wrapper's default environment token	Export the selected service token environment variable before running the command. Avoid `--token` except when environment injection is impossible.
Required service endpoint missing	`CONTENT_AGENTS_*_BASE_URL` is unset	Hand off to `deploy-content-agents` for the missing target, then return to this router and rerun.
Material Agent renders `0 images` after a pre-assignment FET repair	The input USD was normalized or otherwise rewritten before Material Agent, which can change layer composition or scene traversal behavior seen by the service	Restart Content Agents from the converted/minimum-valid USD, then run `simready-conform-profile` and FET fixes on the latest service-authored USD.
Material Agent local logs show `Scene Optimizer failed — continuing pipeline without optimization` and `Permission denied: '/app/.build-resources/scene_optimizer_core/python'`	Local Docker Scene Optimizer bundle parent directory is not traversable by the non-root `material-agent` user; tracked upstream in `NVIDIA-dev/world-understanding#303`	For the running local container, run `docker exec --user root content-material-agent-service chmod -R a+rX /app/.build-resources/scene_optimizer_core`, then rerun the same optimized Material Agent command. If the service is remote or cannot be repaired, include the optimizer-bypass evidence in the handoff.
Physics Agent fails immediately in `optimize_usd` with no completed steps, and local service logs show `Permission denied: '/app/.build-resources/scene_optimizer_core/python'`	Local Docker Scene Optimizer bundle parent directory is not traversable by the non-root `physics-agent` user; tracked upstream in `NVIDIA-dev/world-understanding#303`	For the running local container, run `docker exec --user root content-physics-agent-service chmod -R a+rX /app/.build-resources/scene_optimizer_core`, then rerun the same optimized Physics Agent command. If the service is remote or cannot be repaired, report the optimized attempt as blocked.
Selected Content Agents call fails or times out	Service-level failure	Inspect the specific call's JSON report and retry that service reference after fixing the service or input issue. Do not hand-author substitute material/physics bindings.
Physics Agent appears slow during `identify_asset`, `build_dataset_usd`, `predict`, `restore_usd`, or `apply_physics`	Remote rendering, VLM inference, or CAD/instanced topology can make valid service steps take many minutes	Keep waiting while the wrapper polls and the service remains non-terminal with changing status/progress. Do not terminate the wrapper and write a substitute report.

Pass/Fail Policy

Block when a required service endpoint is missing and deploy-content-agents cannot deploy or verify the service.

Fail when a selected Content Agents call fails, times out, or cannot download its required output artifact.

Skip when the user explicitly disables a call, the selected profile does not need that enrichment, or texture generation is not requested.

Warn when optional prediction files, report HTML, or texture artifacts are unavailable but the required USD-family handoff exists.

Next Steps

Use this handoff:

Result	Next step
Material and physics assignment completed	Run `simready-conform-profile` on the latest physics-authored USD.
Texture generation completed for visual packaging	Use the textured artifact for packaging or preview; keep the physics USD for simulation validation unless requested otherwise.
Service deployment blocked	Resolve the deployment blocker or configure the missing service base URL and usage token, then rerun this router.
Selected call failed	Inspect the specific call report and retry that service reference after fixing the service or input issue.

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 an API key, Needs Python

The author says: Orchestrator skill. Managed Content Agents deployment requires NVIDIA_API_KEY (build.nvidia.com), Docker + NVIDIA Container Toolkit + GPU, Python 3.12, and an upstream checkout of nvidia-omniverse/content-agents on branch main. Reused/provided endpoints may instead use explicit endpoint and usage-token environment variables. Linux/macOS only.

Security

What our scanner noticed· Medium risk

Large base64-encoded blobs
Instructions that use the network
Downloads piped into a shell
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

Omniverse

Publisher

OpenAI (Official)

Distributed by

OpenAI

Source

openai/plugins · plugins/nvidia/skills/omniverse-cad-to-simready · commit d420d13

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (written by AutoGineer)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

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

Download ZIP

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

From the author

From the skill’s files

What it does

When to use it

Advantages

Usage examples

Install

Documentation by Omniverse

CAD to SimReady

When to Use

Prerequisites

Minimum Viable Scope

First Action

Instructions

Output Format

Detailed References

Publishing Layout Notes

Limitations

Troubleshooting

Hard Rules

Files

references/content-agents/README.md

Content Agents

When to Use

Prerequisites

Routing

Inputs

Instructions

Multi-File USD Uploads

Rate Limits

Command Patterns

Output Format

Limitations

Troubleshooting

Pass/Fail Policy

Next Steps

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