validation-agent-cli

Automates validation of 3D content via the Validation Agent CLI.

179|21|Updated Apr 28, 2026
One-click install
npx skills add https://github.com/NVIDIA-Omniverse/content-agents --skill validation-agent-cli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: validation-agent-cli
Source: https://github.com/NVIDIA-Omniverse/content-agents/tree/main/.agents/skills/validation-agent-cli
Command: npx skills add https://github.com/NVIDIA-Omniverse/content-agents --skill validation-agent-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Validates generated 3D content by running the Validation Agent via a CLI, reducing manual review time and increasing consistency across assets.

Core Features & Use Cases

  • CLI-first interface that supports config-driven and prompt-driven validation.
  • Generates structured artifacts such as validation_request.json, validation_plan.json, and validation_result.json for traceability.
  • Supports templates like render_valid, look_right, physics_sane, and physical_behavior for end-to-end checks.

Quick Start

Install the repo package, activate the virtual environment, and run validation-agent with a sample config to validate an asset.

Frequently Asked Questions about validation-agent-cli

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

FAQPage Schema
How do I automate validation for generated USD assets?

You can automate USD asset validation by running the Validation Agent CLI, which supports config-driven and prompt-driven tasks to reduce manual review time and increase consistency across assets.

What is config-driven validation for 3D content?

Config-driven validation is a CLI-first process that checks 3D content using predefined settings, generating structured artifacts like validation_request.json and validation_result.json for traceability.

Can I use validation-agent in CI pipelines to check 3D renders?

Yes, you can use the Validation Agent CLI across CI pipelines to validate 3D renders and evidence artifacts, applying templates like render_valid and look_right for end-to-end checks.

Do I need a Python environment to run validation-agent?

Yes, you need a repo Python environment with the validation-agent package installed, along with access to local inputs such as configuration files, assets, and evidence for CLI-based validation.

What templates are available for USD asset validation?

Available validation templates include render_valid, look_right, physics_sane, and physical_behavior, which apply end-to-end checks to generated 3D content and evidence artifacts.