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://mp-staging.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/references/physics-agent-client/README.md

Assign Physics Properties

When to Use

Use this reference after visual material assignment when an asset needs simulation physics. It is normally selected through the content-agents router and calls this reference's scripts/run.py, which talks to the Content Agents Physics Agent service API and downloads the physics-authored USD output.

This reference should be the main bridge between Content Agents property prediction and static SimReady validation. It is expected to author or return USD with physics schemas when the service succeeds.

Upstream Reference

Use the upstream NVIDIA Omniverse Content Agents Physics Agent client skill as the authoritative reference for service API behavior, endpoint semantics, request fields, and client-side troubleshooting:

Upstream skill: https://github.com/nvidia-omniverse/content-agents/blob/main/.codex/skills/physics-agent-client/SKILL.md
Upstream repository: https://github.com/nvidia-omniverse/content-agents on branch main
Upstream service client: https://github.com/nvidia-omniverse/content-agents/blob/main/apps/physics_agent_service/client/client.py

Access note: Browser or raw-file fetches of the upstream skill URL can fail. If that happens, use the normalized local clone of https://github.com/nvidia-omniverse/content-agents checked out to main and read .codex/skills/physics-agent-client/SKILL.md from that checkout. Resolve that clone from CONTENT_AGENTS_UPSTREAM_ROOT, then $PHYSICAL_AI_SKILL_HUB_UPSTREAM_ROOT/content-agents, then $HOME/.physical-ai-skill-hub/upstreams/content-agents.

Do not copy or reinterpret upstream Physics Agent API behavior here. Keep this reference limited to this reference's wrapper contract, required environment, report shape, and downstream handoff.

Dependency Check

Require:

this reference's portable scripts/run.py and scripts/check_dependencies.py
a reachable Physics Agent service URL through --base-url or CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL
CONTENT_AGENTS_PHYSICS_AGENT_TOKEN, PHYSICS_AGENT_TOKEN, CONTENT_AGENTS_TOKEN, NGC_API_KEY, or NVCF_API_KEY when the service requires bearer auth.

If no Physics Agent base URL is configured, do not immediately stop at assignment. Use deploy-content-agents with target physics; that reference points to the upstream deployment skill and owns deployment details. After deployment health checks pass, export the resulting host/client URL as CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL and rerun physics-agent-client.

First-time users must not run assignment before service readiness is settled. Check for a reachable endpoint, then check for NVIDIA_API_KEY; if the key is missing, ask the user to create/provide one and wait. When deployment succeeds and the service is healthy, run this command.

If deployment is unavailable or fails because the upstream checkout, Docker/GPU prerequisites, renderer wiring, or required credentials are missing, preserve those deployment findings and then report the physics assignment as blocked. Do not hand-author substitute rigid bodies, colliders, mass, or friction data when this reference was selected.

Do not commit API keys, put them in reports, or pass them as command-line arguments in normal workflows because process listings can expose argv. The portable wrapper redacts tokens from its report command, but prefer CONTENT_AGENTS_PHYSICS_AGENT_TOKEN, PHYSICS_AGENT_TOKEN, CONTENT_AGENTS_TOKEN, NGC_API_KEY, NVCF_API_KEY, or matching *_FILE variables from the environment. NVIDIA_API_KEY is deployment auth and is not used as the default client bearer token. The --token option remains available only for constrained automation that cannot inject environment variables.

Inputs

Collect:

Input	Requirement
`asset_path`	Required `.usd`, `.usda`, `.usdc`, or `.usdz` asset, preferably after material assignment.
`output_directory`	Required directory for downloaded service artifacts.
`base_url`	Optional Physics Agent service endpoint; overrides env-based base URL resolution.
`token`	Optional bearer token; defaults to env.
`prompt`	Optional property assignment guidance; prefer the `material_physics_prompt` from `identify-asset-context` when available.
`render_backend`	Optional `warp`, `ovrtx`, or `remote`.
`optimize_usd`	Optional Physics Agent USD optimizer preprocessing path.
`enable_deinstance`	Optional optimizer setting; enabled by default for Physics Agent parity with upstream.
`enable_split`	Optional optimizer setting that splits combined meshes into separate components.
`auto_optimize_composed_usd`	Enabled by default. The wrapper inspects USD topology and automatically enables `optimize_usd`, `enable_deinstance`, and `enable_split` when it detects `GeomSubset`, instance, or prototype component topology. If system `python3` cannot import `pxr`, the wrapper tries `uv run --python 3.12` for this inspection before falling back to a skipped inspection. Use `--no-auto-optimize-composed-usd` to disable this behavior.
`convert_output_to_usd`	Optional local wrapper workaround. When requested with `--convert-output-to-usd`, ensure the downloaded Physics Agent USD-family artifact is crate-backed `.usd` and report that `.usd` as `output_usd_path`.

Optimizer Flags for Composed CAD Assets

The wrapper automatically inspects the input USD before the Physics Agent request. When it detects instances, prototypes, or a single mesh partitioned by GeomSubset children, it runs Physics Agent with all three optimizer controls:

--optimize-usd --enable-deinstance --enable-split

Use this combination after Material Agent output when the goal is component-level physics authoring. --optimize-usd enables the service preprocessing path, --enable-deinstance makes instance/prototype geometry writable when present, and --enable-split lets the optimizer split combined meshes into separate component prims before rendering, prediction, and physics schema application.

Before uploading USD-layer inputs to Physics Agent, the wrapper stages a physics-only copy when it finds MDL shader sourceAsset attributes such as pbr.mdl. Those MDL source files are not needed for physics authoring, and the main optimizer can otherwise produce output that still points at missing MDL sidecars during packaging. The report records this as physics_upload_info.staged=true with stripped_mdl_source_assets.

The same upload-prep step clears unresolved service-internal USDZ subasset paths from Material Agent outputs, for example /var/material-agent/sessions/.../scene.usdz[textures/name.png]. Those paths refer to files inside the Material Agent service container and are not available to the local wrapper when it packages the materialized USD for Physics Agent. The report records this as physics_upload_info.cleared_unresolved_service_asset_paths.

For the GZIO connector test asset, the materialized USD has one combined mesh with six GeomSubset partitions. Running Physics Agent with these flags produced six split mesh parts and six corresponding rigid bodies instead of one rigid body on the combined mesh.

This optimizer path is a preprocessing hint, not a guarantee that the Physics Agent will author one rigid body per component. If the returned USD still fails RB.MB.001, hand the latest Physics Agent output to simready-conform-profile and route the failure to upstream simready-foundation-conform-fet-004-simulate-multi-body-physics when the asset has at least two reusable component candidates. FET004 may promote existing component colliders or part roots into separate rigid bodies when the profile requires multibody physics and no new geometry is needed. For a single mesh component or single GeomSubset component, simready-validate treats RB.MB.001 as non-blocking and preserves it under ignored_issues.

Local Scene Optimizer Permission Workaround

For local Docker deployments, a known upstream issue can make the optimized Physics Agent path fail immediately in optimize_usd with a service log like: Permission denied: '/app/.build-resources/scene_optimizer_core/python'. This is a Scene Optimizer bundle permission problem in the service container, not a signal to disable --optimize-usd, --enable-deinstance, or --enable-split for instanced/prototype topology.

When the report shows current_step.name=optimize_usd and the service failed with no completed steps, inspect the Physics Agent service logs. If they show the permission error above on a local container named content-physics-agent-service, repair the running deployment and rerun the same optimized Physics Agent command:

docker exec --user root content-physics-agent-service chmod -R a+rX /app/.build-resources/scene_optimizer_core

If the container name differs, use the active Physics Agent service container. If the endpoint is managed or remote and you cannot inspect or repair the container, report the optimizer failure as blocked and include the optimized attempt details. Track the upstream issue at https://github.com/NVIDIA-dev/world-understanding/issues/303.

Instructions

Confirm the asset exists and is a USD-family file.
Resolve the Physics Agent endpoint from --base-url or CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL.
If no endpoint is available, check NVIDIA_API_KEY; if missing, ask the user to provide one and wait.
Use deploy-content-agents with target physics; when deployment succeeds and the service is healthy, set CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL and return to this workflow.
If an asset context report exists, use its likely identity, evidence, physics hints, and confidence to craft --prompt.
Run this reference's portable scripts/run.py.
Preserve the JSON report, physics-authored USD output, predictions JSONL, dataset JSONL, and HTML report when available. The upstream /output-usd artifact extension follows the input asset or the service response filename; do not assume it is .usda.
When ASCII USDA output or universal .usd output would block downstream validators that expect crate-backed USD, add --convert-output-to-usd so the wrapper exports the downloaded artifact to crate-backed .usd. Already crate-backed .usd output is accepted as-is.
If the optimized path fails at optimize_usd, inspect service logs before accepting a no-optimizer retry as diagnostic. For the local Scene Optimizer permission failure above, repair the container permissions and rerun the optimized command.
Use output_usd_path from the report as the input to simready-conform-profile.

CLI Pattern

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

Add --base-url "$CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL" only when overriding the URL resolved from the environment.

The wrapper auto-enables --optimize-usd --enable-deinstance --enable-split for composed CAD topology. Pass those flags explicitly when the caller already knows component-level processing is required, or pass --no-auto-optimize-composed-usd for hand-authored USD where topology changes are not desired.

Use --convert-output-to-usd only as a local post-processing workaround. It does not change the upstream Physics Agent service response; it opens the downloaded USD-family artifact with OpenUSD when conversion is needed, exports the root layer to .usd, and verifies the result is crate-backed. If the downloaded artifact is already crate-backed .usd, the wrapper reports that path directly.

Output Format

The report includes:

asset_path
skill
agent
tool
passed
status
base_url
session_id
output_directory
output_usd_path; with --convert-output-to-usd, this points to the converted crate-backed .usd
artifacts
service_status
service_results
usd_topology and physics_optimizer for Physics Agent topology inspection and effective optimizer decisions
physics_upload_info when the wrapper stages a physics-safe upload copy
checks
warnings
errors
next_step

Pass/Fail Policy

Fail or block when:

the input asset is missing or not USD-family
the service URL is missing and deploy-content-agents cannot deploy a healthy Physics Agent service
the service session fails or times out
the required physics-authored USD artifact cannot be downloaded
--convert-output-to-usd is requested and the local OpenUSD conversion to crate-backed .usd fails

Warn when optional prediction, dataset, or HTML report artifacts are unavailable.

Next Steps

Use this handoff:

Result	Next step
Physics-authored USD downloaded	Run `simready-conform-profile` on `output_usd_path`.
Service endpoint missing	Check `NVIDIA_API_KEY`, use `deploy-content-agents` target `physics`, export `CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL`, then rerun.
Service deployment blocked	Resolve the deployment blocker, or configure a Physics Agent base URL and usage token, then rerun.
Service failed	Inspect `service_status`, `service_results`, predictions, and report artifacts.

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

2026-11-08

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/references/physics-agent-client/README.md

Assign Physics Properties

When to Use

Upstream Reference

Dependency Check

Inputs

Optimizer Flags for Composed CAD Assets

Local Scene Optimizer Permission Workaround

Instructions

CLI Pattern

Output Format

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