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/workflow.md

CAD to SimReady Workflow Reference

Inputs

Collect these inputs before running:

Input	Requirement
`source_asset`	Required path to a source asset or existing USD asset.
`output_root`	Required or inferred directory for generated USD, reports, and intermediate outputs.
`simready_profile`	Optional formal SimReady Foundation profile. Prefer `Robot-Body-Runnable` for URDF/MJCF robots and `Prop-Robotics-Neutral` for generic CAD or mesh props unless the user names another profile.
`profile_version`	Optional SimReady profile version. Default to `1.0.0` unless the user names another version.
Asset context intent	Whether to run web-backed asset identification before conversion and property assignment. Default to run when web search is available.
Property assignment intent	Whether to run, skip, or block on Content Agents material and physics assignment. Default to `run` for end-to-end SimReady requests; skip only when the user explicitly requests conversion-only, validation-only, or no property assignment.
Content Agents endpoints	Optional service URLs for Material, Physics, and Texture agents. Use `CONTENT_AGENTS_*_BASE_URL` env vars for both self-deployed and provided endpoints.
Service auth availability	`NVIDIA_API_KEY` is required only before local Content Agents deployment when service endpoints are missing. Existing endpoints should use explicit usage token env vars such as `CONTENT_AGENTS_TOKEN`, service-specific `CONTENT_AGENTS_*_TOKEN`, `NGC_API_KEY`, or `NVCF_API_KEY`; omit `--token` in normal workflows.
Conformance inputs	Optional metadata values, grasp target prim, or explicit grasp points for `simready-conform-profile`.
Preview intent	Optional visual preview request for `ovrtx-render-service` after conversion, conformance, or successful validation. When the user asks to render final results, this is a required output artifact, not a best-effort diagnostic.
Package inputs	Optional package name, version, license, asset name, thumbnail, and backend for `assemble-package-source` plus `nv-core-package-sample`.
Package roots	Optional URDF package mappings when mesh references use `package://`.
Preflight manifest	Optional existing `PHYSICAL_AI_PREFLIGHT_MANIFEST`. If absent, run the `preflight` reference for the selected workflow targets before downstream stages.

If a required sidecar path is missing, stop and report the blocked dependency. Do not move or rewrite source assets unless the user explicitly asks.

Source Routing

Input	Conversion route
`.urdf`	`urdf-usd-converter` through `convert-to-usd`
MuJoCo XML (MJCF) `.xml`	`mujoco-usd-converter` through `convert-to-usd`
Mesh/scene `.fbx`, `.obj`, `.gltf`, `.glb`, `.dae`, or `.stl`	`usd-convert-cad` through `convert-to-usd` when upstream `usd-convert-cad` reports support; otherwise unsupported
Gaussian splat `.ply` or `.spz`	`usd-convert-gsplat` through `convert-to-usd`
Existing `.usd`, `.usda`, `.usdc`, or `.usdz`	Skip conversion and validate directly

NVIDIA-backed source formats route through the usd-convert-cad reference and must delegate to upstream usd-convert-cad only, including the suffixes listed by upstream src/usd_convert_cad/formats.py. If the upstream checkout, setup, Python 3.12 runtime, omniverse-kit, required converter extension, platform support, licensing, or conversion support is unavailable, mark conversion blocked rather than substituting another converter.

Workflow

Confirm the source asset path exists. Do not inspect, convert, validate, build converter dependencies, or open the asset yet when property assignment will run.
Resolve property_assignment_intent before running any stage. Default to run for broad CAD/source-asset to SimReady requests. Set it to skip only when the user explicitly asks for conversion-only, validation-only, or no material/physics assignment.
Run the preflight reference for the selected targets, or verify an existing PHYSICAL_AI_PREFLIGHT_MANIFEST. For conversion-only or validation-only requests, include --skip-content-agents. Source the generated env file so downstream references use the prepared local roots, runtime executables, and service endpoints. If PHYSICAL_AI_REQUIRE_PREFLIGHT=1 is set and the manifest is missing or a component is not ready, stop at the preflight guardrail.
If property_assignment_intent=run, make Content Agents readiness the first operational gate. Verify healthy existing OVRTX, Material, and Physics endpoints before any asset inspection or conversion work. If endpoints are missing or unhealthy, check the required deployment or service API key; if missing, ask the user to provide one and wait.
Use deploy-content-agents to deploy missing Material/Physics services before continuing. Require the shared OVRTX plus individual service-container topology and healthy CONTENT_AGENTS_*_BASE_URL exports. Do not run converter probes, source builds, validation, or conformance while this deployment gate is unsettled.
Run identify-asset-context on the original source asset when web search is available or when material/physics assignment will run. Preserve local inspection and research reports.
Detect the input format and choose the concrete conversion route through convert-to-usd.
Run convert-to-usd when needed and capture the generated USD path from its report. For existing USD input, skip conversion and use the source path as the USD path.
Run validate-usd-minimum on the converted or existing USD before expensive downstream work. Use this only as a viability gate before service calls. If the report or USD metadata shows metersPerUnit != 1.0 or another repairable profile issue, record it for the post-assignment conformance pass instead of running FET001 or any other FET helper now.
Run content-agents when material, physics, or texture assignment is requested or required. Use the context report's material and physics prompt when available. The Physics Agent wrapper inspects USD topology and automatically enables --optimize-usd --enable-deinstance --enable-split when it detects composed CAD component structure such as GeomSubset, instances, or prototypes.
Use each assignment report's concrete output_usd_path or output_usdz_path as the next handoff path. Keep the physics-authored USD path for simulation validation unless the user explicitly wants to validate the textured USDZ.
Run simready-conform-profile on the latest simulation USD path. Preserve each selected FET repair report and use the newest authored USD path for the next stage. Always inspect the latest service-authored USD's metersPerUnit before final profile validation; if it is not 1.0, route through upstream simready-foundation-conform-fet-001-minimal in this post-assignment conformance pass so UN.007 is repaired before later profile gates. For prop profiles, do not defer a detected or expected GSP.001 failure by default: route it through upstream simready-foundation-conform-fet-005-simulate-grasp-physics and either author a vision-selected grasp line or record an explicit FET005 blocked report when visual evidence or a vision-capable agent is unavailable.
Run validation gates on the conformed USD: omni-asset-validate, omni-asset-validate-geometry, omni-asset-validate-physics, and simready-validate.
If simready-validate reports a repairable SimReady requirement, rerun the relevant upstream conformance skill and then rerun the profile validation on the newest authored USD. For GSP.001, use upstream simready-foundation-conform-fet-005-simulate-grasp-physics: generate or collect visual evidence, choose explicit grasp points only when a vision-capable agent can inspect that evidence, and call the upstream author_grasp_line.py after the point decision. If the current agent is terminal-only or the points are not supplied, record the FET005 step as blocked with the render/evidence paths and do not author a bounds-only placeholder line. For RB.MB.001, use upstream simready-foundation-conform-fet-004-simulate-multi-body-physics: inspect the actual UsdPhysics.RigidBodyAPI prims, not just visual prim count. If the latest Physics Agent output has existing component colliders or part roots that represent source parts, FET004 should move or add rigid-body schemas to those existing candidates and rerun validation. If the asset has fewer than two reusable physical body candidates, rely on the simready-validate single-component policy to treat RB.MB.001 as non-blocking when the USD has only one mesh component or one GeomSubset component; otherwise report FET004 as blocked or not applicable instead of inventing geometry.
Run ovrtx-render-service on the latest USD path when the user requests a visual preview, thumbnail, inspection image, or final renders. Final renders must come from the ovrtx-render-service reference output for the final USD being reported. Do not substitute Material Agent or Physics Agent HTML report images, generated service thumbnails, screenshots, or earlier conversion thumbnails as final render artifacts. For final report renders, use the render reference's default no-authored-light mode so the renderer keeps a clean black background; only pass --default-lights when explicitly debugging lighting. If ovrtx-render-service returns a blank/uniform image, no PNG, or an image of the wrong asset, record render status as failed/blocked and troubleshoot or rerun the OVRTX render reference instead of silently falling back. Treat render failure as diagnostic unless a render artifact is explicitly required.
If package inputs are available, run assemble-package-source before packaging. Use the latest conformed USD as final_usd, the final ovrtx-render-service PNG as --thumbnail, and the workflow output_root as the two-zone root. This stage creates {output_root}/deliverable/simready_usd/sm_{asset_name}_01.usd, places the thumbnail under .thumbs/256x256/, localizes referenced files, rewrites authored asset paths where OpenUSD exposes them, and verifies the assembled USD dependencies resolve within deliverable/.
Run nv-core-package-sample against {output_root}/deliverable, never the full workflow output root. Pass --root-usd simready_usd/sm_{asset_name}_01.usd, write package reports under {output_root}/pipeline/07_package/, and then run nv-core-package-sample-validation even when earlier validation gates produced findings.
Write omniverse-cad-to-simready-report.md under output_root unless the user requests a different path. Include asset identity evidence, stage status, selected profile, key output USD paths, structure counts when useful, grouped validation failures, warnings, render preview paths, and recommended next work.

Validation Policy

The workflow is blocked only by failures that prevent later stages from using a meaningful USD artifact or required services: failed Content Agents readiness, unsupported source formats, missing converter dependencies, missing sidecar assets, invalid minimum USD, property assignment failures, and conformance authoring failures.

When property assignment will run, deterministic SimReady conformance repairs are post-assignment work. Do not normalize units, author FET000 metadata, create grasp lines, or apply FET004 rigid-body fixes before Material/Physics/Texture Agent calls. This keeps Content Agents operating on the converter-produced USD shape and avoids service rendering failures caused by pre-assignment root-layer/unit edits.

Validation failures from Asset Validator, geometry, physics, SimReady profile, or package validation are not terminal workflow blockers. They mean the asset is not SimReady-clean yet, but the workflow should continue through remaining diagnostic gates and put the asset in the rerun/remediation queue. If a validation command exits non-zero after writing a structured report, parse the report, record the findings, and continue the workflow.

Packaging can be skipped without failing the asset workflow when the user did not provide package inputs. If the user asked for a finished package, missing package inputs are blocked requirements.

Output Report Fields

The JSON report should include:

Field	Meaning
`source_asset_path`	Original source asset path.
`source_format`	Detected format.
`asset_context_report_path`	Asset identity/context report path when context research ran.
`asset_identity`	Likely identity and confidence from the context report.
`output_root`	Directory holding stage reports and generated USD output.
`output_usd_path`	Generated or existing USD path, when available.
`conformed_usd_path`	Latest USD path after `simready-conform-profile`, when available.
`simready_profile`	Selected profile, feature, or capability target.
`property_assignment_status`	`passed`, `failed`, `skipped`, or `blocked`.
`materialized_usd_path`	USD path after Material Agent, when available.
`physics_usd_path`	USD path after Physics Agent, when available.
`textured_usdz_path`	USDZ path after Texture Agent, when requested and available.
`render_preview_path`	PNG path produced by `ovrtx-render-service` for the final reported USD, when requested and available. Do not populate this with Material Agent/Physics Agent report images or thumbnails from earlier stages.
`deliverable_root`	Clean package source prepared by `assemble-package-source`, normally `{output_root}/deliverable`.
`assembled_root_usd_path`	Canonical root USD prepared for packaging, normally `deliverable/simready_usd/sm_{asset_name}_01.usd`.
`assembly_report_path`	Assembly report path, normally `{output_root}/pipeline/assembly-report.json`.
`package_root`	Package root when packaging ran or was prepared; use the deliverable root, not the pipeline workspace.
`package_definition_path`	Package definition path when packaging ran.
`markdown_report_path`	Final Markdown report path.
`passed`	Overall workflow pass/fail result.
`needs_rerun`	Whether the asset completed the workflow but has validation findings, transient service failures, or other remediation items.
`rerun_reasons`	Validation findings, transient service errors, or blocked diagnostics that require later retry/remediation.
`steps`	Ordered conversion, assignment, conformance, validation, and packaging step results.

Human Approval Points

Ask for explicit approval before destructive or ambiguous operations such as overwriting source files, modifying vendored assets, applying repairs, stamping guessed metadata, choosing a package license, or selecting between multiple equally plausible source assets. Writing into a user-provided output directory is allowed.

Next Steps

If profile validation fails, use simready-validate details to identify the first missing SimReady requirement.
If profile validation reports GSP.001, rerun simready-conform-profile through upstream simready-foundation-conform-fet-005-simulate-grasp-physics. Complete the repair automatically when the agent can inspect visual evidence and select a useful grasp region, or with user-provided explicit grasp points. Otherwise mark the FET005 handoff blocked so the final report explains why the grasp repair did not author USD.
If packaging is skipped, collect package name, version, license, asset name, final thumbnail, and final USD path, then run assemble-package-source before nv-core-package-sample.

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