meshy-3d-generation

Automate 3D asset creation via the Meshy API with text, image, and animation workflows.

Updated Dec 8, 2025
One-click install
npx skills add https://github.com/MarcMercury/Everloop.live --skill meshy-3d-generation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meshy-3d-generation
Source: https://github.com/MarcMercury/Everloop.live/tree/main/.agents/skills/meshy-3d-generation
Command: npx skills add https://github.com/MarcMercury/Everloop.live --skill meshy-3d-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates end-to-end 3D asset creation by orchestrating Meshy API tasks, handling environment setup and credentials, and delivering ready-to-use outputs.

Core Features & Use Cases

  • End-to-end workflows: text-to-3D (preview + refine), image-to-3D, multi-image-to-3D, retexture, remesh, auto-rigging, and animation.
  • Multi-format outputs with textures and PBR maps, thumbnails, and activity history for iterative pipelines.
  • Use cases include game character assets, AR-ready models, product visuals, and rapid iteration of textured, rigged assets.

Quick Start

Provide a descriptive prompt and select the desired pipeline (text-to-3D with optional textures, rigging, and export formats) to generate a ready-to-use 3D asset.

Frequently Asked Questions about meshy-3d-generation

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

FAQPage Schema
How do I generate a 3D model from text prompts?

To generate a 3D model from text, you provide a descriptive prompt and select the text-to-3D pipeline. The workflow runs a preview phase followed by a refinement step to produce a ready-to-use 3D asset with textures.

Can I convert an existing image into a 3D model?

Yes, you can convert an image into a 3D model using the image-to-3D workflow. The process also supports multi-image-to-3D inputs, allowing you to generate textured 3D assets from multiple reference pictures.

Does the 3D generation process include auto-rigging and animation?

Yes, the 3D generation process includes auto-rigging and animation workflows. After generating or retopologizing your model, you can apply rigging to prepare the asset for animation pipelines.

What do I need to set up before automating 3D asset creation?

Before automating 3D asset creation, you need a Python environment with the requests package installed. You must also configure your Meshy API key securely to allow the scripts to handle task creation and polling.

What file formats and texture maps are supported by the 3D generation workflow?

The 3D generation workflow supports multi-format outputs, including standard 3D model files and PBR texture maps. It also generates thumbnails and maintains an activity history for iterative design pipelines.

Why does my text-to-3D generation task stop working during polling?

Text-to-3D generation tasks may stop working during polling due to network interruptions or invalid API credentials. The scripts include robust error handling and progress reporting to help identify and resolve these processing failures.