Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Initial release
What This Skill Does
Generates 3D models from text descriptions or reference images using the each::sense AI API. Outputs files in GLB, GLTF, OBJ, FBX, and USDZ formats with PBR textures. Supports characters, vehicles, architecture, furniture, environments, and game assets.
Skips manual modeling by generating production-ready assets with PBR textures directly from text or images, covering formats used across Unity, Unreal, web, and Apple AR.
When to use it
- Prototyping a game asset pack from text descriptions
- Converting a product photo into a 3D model for AR try-on
- Generating furniture models for interior design visualization
- Creating character models in T-pose for animation pipelines
- Building architectural 3D mockups from written descriptions
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create a low-poly treasure chest game asset with gold trim and iron locks
- 1Set mode to 'eco' for a game asset prototype
- 2POST to https://sense.eachlabs.run/chat with the description and mode
- 3Stream the response via text/event-stream
- 4Receive GLB or OBJ file URL in the output
- 5Download and import into the game engine
A low-poly GLB file of a treasure chest with PBR textures, ready to import into Unity or Unreal
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.