Omniverse Cad To Simready
OpenAIOfficialCreated by OmniverseDistributed by OpenAI
- Skill
- Workflow
- Software development
- Apache-2.0
- Medium risk
- Has scripts
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/downloadUnzip 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
preflightreference first for deterministic setup. It installs or verifies local upstream checkouts, writes acad-to-simready-preflight.jsonmanifest, and exportsPHYSICAL_AI_PREFLIGHT_MANIFESTplusPHYSICAL_AI_REQUIRE_PREFLIGHT=1for downstream references.Python 3.12 and
uv(per repoREADME.md).NVIDIA_API_KEY from
https://build.nvidia.comwhen local Content Agents deployment will run. Already-running endpoints may instead use explicit endpoint variables plus usage tokens such asNGC_API_KEY,NVCF_API_KEY, orCONTENT_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_intentbefore running any asset inspection, converter probe, conversion, validation, conformance, rendering, or packaging step.Run
preflightfor the selected workflow targets, unless a readyPHYSICAL_AI_PREFLIGHT_MANIFESTis 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-toolsvalue to scope dependency checks, butconvert-to-usdand 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.mdandreferences/commands.md, then run only the stage references needed for the current request.Run
identify-asset-contexton 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-minimumbefore expensive downstream work. Treat this as a viability gate only: record unit/profile issues such asmetersPerUnit != 1.0, but do not runsimready-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-profileon 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, andsimready-validate.Rerun
simready-conform-profilewhensimready-validatereports a repairable requirement, then rerun profile validation on the newest authored USD.Run
ovrtx-render-servicewhen preview, thumbnail, or inspection images are requested. When package outputs are requested, runassemble-package-sourcenext to create the cleandeliverable/package source from the final USD and thumbnail, then runnv-core-package-sampleandnv-core-package-sample-validationon 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, orneeds_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-physicsneeds 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=1is 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-simreadyrunner command.For source conversion, delegate to the
convert-to-usdreference; 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-profileor 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-validateor any SimReady profile validation before Content Agents. The only validation gate allowed before service calls isvalidate-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.001profile failure as an unclassified final finding. Route it to upstreamsimready-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
- ATTRIBUTION.mdAdded by AutoGineer1.0 KiB
- BENCHMARK.md7.2 KiB
- LICENSEAdded by AutoGineer10.0 KiB
- SKILL.md17.5 KiB
- agents/openai.yaml427 B
- evals/evals.json4.0 KiB
- evals/files/minimal_mesh.stl157 B
- references/assemble-package-source/README.md3.5 KiB
- references/assemble-package-source/scripts/check_dependencies.pyScript1.1 KiB
- references/assemble-package-source/scripts/report_schema.json1.2 KiB
- references/assemble-package-source/scripts/run.pyScript17.6 KiB
- references/commands.md5.3 KiB
- references/content-agents/README.md18.6 KiB
- references/content-agents/references/material-agent-client/README.md12.1 KiB
- references/content-agents/references/material-agent-client/scripts/check_dependencies.pyScript417 B
- references/content-agents/references/material-agent-client/scripts/report_schema.json722 B
- references/content-agents/references/material-agent-client/scripts/run.pyScript405 B
- references/content-agents/references/physics-agent-client/README.md13.1 KiB
- references/content-agents/references/physics-agent-client/scripts/check_dependencies.pyScript417 B
- references/content-agents/references/physics-agent-client/scripts/report_schema.json722 B
- references/content-agents/references/physics-agent-client/scripts/run.pyScript405 B
- references/content-agents/references/texture-agent-client/README.md6.2 KiB
- references/content-agents/references/texture-agent-client/scripts/check_dependencies.pyScript417 B
- references/content-agents/references/texture-agent-client/scripts/report_schema.json722 B
- references/content-agents/references/texture-agent-client/scripts/run.pyScript405 B
- references/content-agents/scripts/check_dependencies.pyScript1.3 KiB
- references/content-agents/scripts/content_agent_check_dependencies.pyScript4.6 KiB
- references/content-agents/scripts/content_agent_client.pyScript71.2 KiB
- references/content-agents/scripts/content_agent_material_cleanup.pyScript10.7 KiB
- references/content-agents/scripts/content_agent_report_schema.json722 B
- references/content-agents/scripts/report_schema.json961 B
- references/content-agents/scripts/run.pyScript9.6 KiB
- references/convert-to-usd/README.md10.7 KiB
- references/convert-to-usd/references/mujoco-usd-converter/README.md4.0 KiB
- references/convert-to-usd/references/mujoco-usd-converter/scripts/check_dependencies.pyScript1.5 KiB
- references/convert-to-usd/references/mujoco-usd-converter/scripts/report_schema.json405 B
- references/convert-to-usd/references/mujoco-usd-converter/scripts/run.pyScript9.3 KiB
- references/convert-to-usd/references/openusd-exchange-sdk-usdex/README.md4.7 KiB
- references/convert-to-usd/references/urdf-usd-converter/README.md3.8 KiB
- references/convert-to-usd/references/urdf-usd-converter/scripts/check_dependencies.pyScript1.5 KiB
- references/convert-to-usd/references/urdf-usd-converter/scripts/report_schema.json403 B
- references/convert-to-usd/references/urdf-usd-converter/scripts/run.pyScript9.4 KiB
- references/convert-to-usd/references/usd-convert-cad/README.md11.7 KiB
- references/convert-to-usd/references/usd-convert-cad/scripts/check_dependencies.pyScript8.3 KiB
- references/convert-to-usd/references/usd-convert-cad/scripts/kit_app_template_cad.pyScript27.2 KiB
- references/convert-to-usd/references/usd-convert-cad/scripts/report_schema.json476 B
- references/convert-to-usd/references/usd-convert-cad/scripts/run.pyScript25.4 KiB
- references/convert-to-usd/references/usd-convert-gsplat/README.md4.2 KiB
- references/convert-to-usd/references/usd-convert-gsplat/scripts/check_dependencies.pyScript2.1 KiB
- references/convert-to-usd/references/usd-convert-gsplat/scripts/report_schema.json413 B
- references/convert-to-usd/references/usd-convert-gsplat/scripts/run.pyScript13.6 KiB
- references/convert-to-usd/scripts/check_dependencies.pyScript1.7 KiB
- references/convert-to-usd/scripts/report_schema.json1.4 KiB
- references/convert-to-usd/scripts/run.pyScript22.6 KiB
- references/deploy-content-agents/README.md7.9 KiB
- references/deploy-content-agents/references/deploy-material-agent-docker.md413 B
- references/deploy-content-agents/references/deploy-ovrtx-docker.md395 B
- references/deploy-content-agents/references/deploy-physics-agent-docker.md411 B
- references/deploy-content-agents/references/deploy-texture-agent-docker.md411 B
- references/identify-asset-context/README.md4.7 KiB
- references/identify-asset-context/scripts/check_dependencies.pyScript1.5 KiB
- references/identify-asset-context/scripts/report_schema.json751 B
- references/identify-asset-context/scripts/run.pyScript11.1 KiB
- references/nv-core-package-sample-validation/README.md5.2 KiB
- references/nv-core-package-sample-validation/scripts/check_dependencies.pyScript419 B
- references/nv-core-package-sample-validation/scripts/report_schema.json702 B
- references/nv-core-package-sample-validation/scripts/run.pyScript400 B
- references/nv-core-package-sample/README.md6.2 KiB
- references/nv-core-package-sample/scripts/check_dependencies.pyScript419 B
- references/nv-core-package-sample/scripts/report_schema.json702 B
- references/nv-core-package-sample/scripts/run.pyScript400 B
- references/omni-asset-validate-geometry/README.md3.5 KiB
- references/omni-asset-validate-geometry/scripts/check_dependencies.pyScript1.5 KiB
- references/omni-asset-validate-geometry/scripts/report_schema.json363 B
- references/omni-asset-validate-geometry/scripts/run.pyScript2.0 KiB
- references/omni-asset-validate-physics/README.md3.4 KiB
- references/omni-asset-validate-physics/scripts/check_dependencies.pyScript1.5 KiB
- references/omni-asset-validate-physics/scripts/report_schema.json362 B
- references/omni-asset-validate-physics/scripts/run.pyScript2.0 KiB
- references/omni-asset-validate/README.md3.5 KiB
- references/omni-asset-validate/scripts/check_dependencies.pyScript2.0 KiB
- references/omni-asset-validate/scripts/report_schema.json359 B
- references/omni-asset-validate/scripts/run.pyScript13.0 KiB
- references/ovrtx-render-service/README.md13.5 KiB
- references/ovrtx-render-service/scripts/check_dependencies.pyScript3.0 KiB
- references/ovrtx-render-service/scripts/report_schema.json674 B
- references/ovrtx-render-service/scripts/run.pyScript23.5 KiB
- references/ovrtx-render-service/scripts/stage_prep.pyScript18.5 KiB
- references/ovrtx-render-service/scripts/turntable.pyScript10.8 KiB
- references/preflight/README.md9.9 KiB
- references/preflight/scripts/preflight.ps1Script460 B
- references/preflight/scripts/preflight.pyScript68.8 KiB
- references/preflight/scripts/preflight.shScript278 B
- references/simready-conform-profile/README.md13.7 KiB
- references/simready-conform-profile/references/FET_000_CORE/README.md1.3 KiB
- references/simready-conform-profile/references/FET_000_CORE/scripts/check_dependencies.pyScript1.4 KiB
- references/simready-conform-profile/references/FET_000_CORE/scripts/report_schema.json418 B
- references/simready-conform-profile/references/FET_000_CORE/scripts/run.pyScript11.6 KiB
- references/simready-conform-profile/references/FET_001_MINIMAL/README.md1.5 KiB
- references/simready-conform-profile/references/FET_001_MINIMAL/scripts/check_dependencies.pyScript1.9 KiB
- references/simready-conform-profile/references/FET_001_MINIMAL/scripts/report_schema.json668 B
- references/simready-conform-profile/references/FET_001_MINIMAL/scripts/run.py16.3 KiB
- references/simready-conform-profile/references/FET_004_SIMULATE_MULTI_BODY_PHYSICS/README.md1.4 KiB
- references/simready-conform-profile/references/FET_004_SIMULATE_MULTI_BODY_PHYSICS/scripts/check_dependencies.py1.6 KiB
- references/simready-conform-profile/references/FET_004_SIMULATE_MULTI_BODY_PHYSICS/scripts/report_schema.json1.0 KiB
- references/simready-conform-profile/references/FET_004_SIMULATE_MULTI_BODY_PHYSICS/scripts/run.py13.3 KiB
- references/simready-conform-profile/references/FET_005_SIMULATE_GRASP_PHYSICS/README.md1.8 KiB
- references/simready-conform-profile/references/FET_005_SIMULATE_GRASP_PHYSICS/scripts/author_grasp_line.py11.2 KiB
- references/simready-conform-profile/scripts/check_dependencies.py1.9 KiB
- references/simready-conform-profile/scripts/report_schema.json466 B
- references/simready-conform-profile/scripts/run.py19.8 KiB
- references/simready-validate/README.md9.5 KiB
- references/simready-validate/scripts/check_dependencies.py4.2 KiB
- references/simready-validate/scripts/report_schema.json480 B
- references/simready-validate/scripts/run.py27.9 KiB
- references/validate-usd-minimum/README.md2.5 KiB
- references/validate-usd-minimum/scripts/check_dependencies.py1.7 KiB
- references/validate-usd-minimum/scripts/report_schema.json1.3 KiB
- references/validate-usd-minimum/scripts/run.py11.5 KiB
- references/workflow.md15.7 KiB
- shared/preflight_manifest.py6.0 KiB
- shared/script_utils.py11.7 KiB
- shared/simready_package.py33.6 KiB
- shared/simready_package_check_dependencies.py1.7 KiB
- shared/simready_package_report_schema.json702 B
- shared/usd_convert_cad_diagnostics.py3.2 KiB
- skill-card.md2.9 KiB
- skill.oms.sig38.3 KiB
references/deploy-content-agents/README.md
Deploy Content Agents
When to Use
Use this reference when the user asks to deploy, start, configure, or troubleshoot NVIDIA Omniverse Content Agents services. This repo does not ship a deployment runner or duplicate service runbooks; it selects the target, resolves the upstream checkout, enforces repo-local readiness policy, and hands off to the upstream deployment skills.
This reference is documentation-driven, does not ship scripts/run.py, and should not depend on this repository checkout.
Prerequisites
NVIDIA_API_KEY from
https://build.nvidia.comfor provider-backed services.Docker, Docker Compose v2, NVIDIA Container Toolkit, an NVIDIA driver, and an NVIDIA GPU on the deployment host.
A normalized upstream checkout of
https://github.com/nvidia-omniverse/content-agentson branchmain.
Upstream Reference
Use the NVIDIA Omniverse Content Agents main deployment skills as the source of truth:
| Target | Upstream skill |
|---|---|
| Material Agent | https://github.com/nvidia-omniverse/content-agents/blob/main/.codex/skills/deploy-material-agent-docker/SKILL.md |
| Physics Agent | https://github.com/nvidia-omniverse/content-agents/blob/main/.codex/skills/deploy-physics-agent-docker/SKILL.md |
| Texture Agent | https://github.com/nvidia-omniverse/content-agents/blob/main/.codex/skills/deploy-texture-agent-docker/SKILL.md |
| OVRTX renderer | https://github.com/nvidia-omniverse/content-agents/blob/main/.codex/skills/deploy-ovrtx-docker/SKILL.md |
Repository: https://github.com/nvidia-omniverse/content-agents, branch main
If browser or raw-file fetches are blocked, use a local clone checked out to main and read .codex/skills/<skill-name>/SKILL.md from that checkout. Resolve it 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 scan broad developer workspaces.
Do not duplicate full upstream deployment runbooks here.
Inputs
Collect:
| Input | Requirement |
|---|---|
target_service | material, physics, texture, or ovrtx. |
content_agents_root | Optional explicit upstream checkout path. |
deployment_mode | Local container deployment or reuse of healthy existing services. |
render_endpoint | Required for render-dependent agent services. |
env_keys | Provider/API keys required by the upstream skill. Never print or commit secrets. |
Instructions
Resolve the upstream checkout from the normalized root policy.
Read the matching upstream deployment skill before issuing service-specific commands.
Confirm required secrets are available from local shell state or a private
.env; if missing, ask the user and wait.For
material,physics, ortexture, deploy or reuse OVRTX first when the selected upstream skill requires rendering.Prefer a shared standalone OVRTX renderer plus independently deployed agent services for this workflow. Use bundled agent-specific renderer stacks only when the user asks for isolation or the upstream skill requires it.
Preserve upstream secret handling, build steps, image names, health checks, and service-specific environment details.
Verify the renderer and selected agent health endpoints before exporting
CONTENT_AGENTS_*_BASE_URLorRENDER_ENDPOINT.Return to the caller only after the requested service is healthy, or report the missing prerequisite as blocked.
Headless / Nested Host Notes
Use this section only as deployment-readiness guidance for nested or headless
hosts. The upstream content-agents skills still own the actual Docker
Compose files, commands, image names, ports inside containers, and
service-specific environment variables.
Single GPU + Cloud VLM
For local evaluation, prefer one shared standalone OVRTX renderer on the local
GPU plus independent Material, Physics, and Texture Agent service containers
that use NVIDIA_API_KEY from https://build.nvidia.com for provider-backed
VLM calls. This topology does not require a separate local VLM GPU. Verify the
OVRTX host endpoint first, then verify each agent service reports configured API
keys before exporting CONTENT_AGENTS_*_BASE_URL.
Confirm Docker Compose v2 is installed before following the upstream deployment skills; the legacy
docker-composebinary is not sufficient when upstream expectsdocker compose.In nested Docker environments, overlay storage can fail with
invalid argument. If Docker cannot start containers, check whether the host needs avfsstorage-driver fallback before retrying the upstream deployment.Avoid changing Docker daemon settings in a shared or user-provided SSH session until the user approves that risk; prefer a fresh disposable session for deployment experiments.
Treat the Xvfb display number as a configurable deployment input. If OVRTX exits during startup and the logs show a display conflict, choose an unused display such as
:100instead of assuming the default display is free.Prefer distinct host endpoints for the shared renderer and each independently deployed agent service. A proven local layout is OVRTX on
8001, Material Agent on8100, Physics Agent on8200, and Texture Agent on8300when texture generation is needed; export the corresponding host URLs only after those endpoints respond healthy.A container-internal OVRTX healthcheck can be a false negative when the externally mapped host
/healthendpoint is healthy. Record both the container health result and the host endpoint result before declaring the renderer blocked.
Handoff Map
| Target | After deployment |
|---|---|
| Material Agent | Set CONTENT_AGENTS_MATERIAL_AGENT_BASE_URL, then use material-agent-client. |
| Physics Agent | Set CONTENT_AGENTS_PHYSICS_AGENT_BASE_URL, then use physics-agent-client. |
| Texture Agent | Set CONTENT_AGENTS_TEXTURE_AGENT_BASE_URL, then use texture-agent-client. |
| OVRTX | Set RENDER_ENDPOINT or OVRTX_RENDER_ENDPOINT for render clients. |
Limitations
This reference selects targets and readiness gates; upstream deployment skills own commands and service internals.
It does not call already-running services for asset enrichment.
It does not publish Docker Compose,
docker run, port, image-name, or in-container environment recipes. Read those from upstream.
Troubleshooting
| Symptom | Action |
|---|---|
| Upstream skill URL cannot be fetched | Use the local content-agents clone checked out to main. |
| Required API key is missing | Ask the user for NVIDIA_API_KEY for deployment and wait. Usage tokens for already-running endpoints belong to the client references, not this deployment reference. |
| Service health is not ready | Follow the selected upstream deployment skill's health-check section. |
| Renderer-dependent agent cannot reach OVRTX | Use the upstream renderer and agent deployment skills together; do not patch this repo with local Docker recipes. |
| Nested host cannot start Docker containers | Check Docker Compose v2, GPU visibility, NVIDIA Container Toolkit, and whether the host requires the vfs storage-driver fallback. |
| OVRTX exits in a headless session | Check Xvfb logs and retry the upstream deployment with an unused display value instead of assuming :99 is available. |
| Container health is unhealthy but the mapped host endpoint responds | Treat this as a healthcheck mismatch until the upstream deployment skill confirms the container-internal and host-mapped ports. Use the host endpoint only after /health reports renderer readiness. |
Pass/Fail Policy
Report blocked rather than guessing when:
the upstream checkout is inaccessible
Docker/GPU/container prerequisites fail
required credentials are missing
the selected upstream deployment skill does not support the requested mode
health checks do not pass
Next Steps
After a service is healthy, return to content-agents or the selected service wrapper reference for the asset workflow.
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
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