xb-context

Extract semantic trees and visible-object states from XR scenes.

455|91|Updated Sep 25, 2025
One-click install
npx skills add https://github.com/google/xrblocks --skill xb-context
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: xb-context
Source: https://github.com/google/xrblocks/tree/main/skills/xb-context
Command: npx skills add https://github.com/google/xrblocks --skill xb-context

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill allows for efficient scene context extraction from XR environments, providing agents with semantic trees, visible-object state, and Set-of-Mark labels, simplifying object selection and interaction.

Core Features & Use Cases

  • Scene Context Extraction: Offers detailed scene context, including semantic trees and object visibility, for better XR interaction.
  • Use Case: When developing an XR application that requires object selection and manipulation, this Skill provides the necessary context to make informed decisions without delving into complex Three.js objects.

Quick Start

Use the xb-context skill to retrieve the semantic tree from the current XR scene.

Frequently Asked Questions about xb-context

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

FAQPage Schema
How do I extract scene context from an XR environment for object interaction?

To extract scene context from an XR environment, retrieve semantic trees and visible-object states to enable object selection. This process provides agents with Set-of-Mark labels, simplifying interaction decisions without delving into complex Three.js objects.

What is an XR semantic tree and how does it help with object selection?

An XR semantic tree is a structured representation of scene context that details object visibility and states. It helps with object selection by providing agents with Set-of-Mark labels, enabling informed interaction decisions without parsing complex Three.js objects.

Does scene context retrieval work in desktop simulators or only in XR environments?

Scene context retrieval works in both XR environments and desktop simulators. It consistently provides semantic trees, visible-object state, and Set-of-Mark labels to support scene detection and context extraction across different platforms.

How do I get visible-object states for agent interaction in XR applications?

You get visible-object states for agent interaction in XR applications by using scene context extraction. This provides detailed semantic trees and Set-of-Mark labels, allowing agents to make informed selection decisions without handling complex Three.js objects.

Why use scene context extraction instead of parsing Three.js objects directly for XR development?

Use scene context extraction instead of parsing Three.js objects directly because it efficiently provides semantic trees and visible-object states. This simplifies object selection and manipulation by delivering agent-facing context and Set-of-Mark labels without complex object handling.