physics-agent-cli

Classify USD asset physics properties and author UsdPhysics schemas via CLI.

179|21|Updated Apr 28, 2026

Search Tags:#cli #physics #classification #datasets #usd #vlm

Ready to run

npx skills add https://github.com/NVIDIA-Omniverse/content-agents --skill physics-agent-cli

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: physics-agent-cli
Source: https://github.com/NVIDIA-Omniverse/content-agents/tree/main/.agents/skills/physics-agent-cli
Command: npx skills add https://github.com/NVIDIA-Omniverse/content-agents --skill physics-agent-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates physics property classification and USD physics schema authoring via the Physics Agent CLI, reducing manual analysis, scripting, and error-prone workflows in 3D asset pipelines.

Core Features & Use Cases

Run the Physics Agent CLI to classify component parts of USD assets using VLM-based predictions.
Identify asset type, predict material properties, physics characteristics, and write simulation-ready UsdPhysics schemas.
Build per-asset datasets from USD files and integrate CLI workflows into automation pipelines.

Quick Start

Activate your Python environment and run the CLI with a config file, for example physics-agent run apps/physics_agent/configs/lightbulb.yaml --dry-run.

Frequently Asked Questions about physics-agent-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate physics property classification for USD assets?▼

Automate physics property classification for USD assets by running the Physics Agent CLI to apply VLM-based predictions for component classification and material physics characteristics. This reduces manual scripting and error-prone workflows in 3D asset pipelines.

Can I generate simulation-ready UsdPhysics schemas from existing USD files?▼

Yes, you can generate simulation-ready UsdPhysics schemas from existing USD files. The CLI predicts physics characteristics and writes schemas directly into the assets, preparing them for downstream simulation pipelines.

What do I need to run the Physics Agent CLI with a VLM backend?▼

To run the Physics Agent CLI with a VLM backend, you need an activated Python environment, the physics-agent CLI installed, and valid credentials and endpoints for your chosen VLM backend and render/optimizer services.

What is the best way to build per-asset datasets from USD files?▼

The best way to build per-asset datasets from USD files is using the Physics Agent CLI, which classifies component parts, identifies asset types, and predicts material properties to generate structured datasets for automation pipelines.

How does VLM-based physics prediction work for 3D asset typing?▼

VLM-based physics prediction for 3D asset typing works by applying vision-language models to USD assets, analyzing component geometries to identify asset types and predict physics characteristics without manual inspection.