3Dviz Pro Max by Viet Tran — workflow skill for 3D scenes

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page. From a terminal: curl -fsSL https://varg.ai/install | sh installs the vargai CLI (https://varg.ai/how-to/cli.md): vargai search and vargai install <slug> with no key, every varg model after vargai login.

Idea to explorable three.js or Blender scene: 223 recipes, runnable kits and a capture helper to check real frames.

What it does

A standalone skill for creative 3D visualization: a ten-step workflow (intent, object reasoning, representation, construction routing, quality targets, first view, behavior, run and inspect, refine, honest report), a searchable catalog of 223 recipes and 440 knowledge records across 24 directions (villages and worlds, anatomy, molecules, linear algebra, orbits, robotics and more), a Vite + three.js scaffold with camera, light and post rigs, 22 proved kit blueprints, and capture.py, which drives the built scene in headless Chromium so the agent looks at real frames instead of describing them. Blender 4.2+ is optional for baked hero assets. The repo publishes 21 GPU showcase frames and 37 runnable example studies.

Use when

Not for

Install

Example output

https://raw.githubusercontent.com/viettranx/3dviz-pro-max/main/site/public/media/clips/village.mp4 — The village example study, recorded for the project's landing page: a stylized island village built with the skill, 4 s orbit (credit: Viet Tran (3dviz-pro-max), https://github.com/viettranx/3dviz-pro-max/blob/main/docs/site.md)

More 3D scenes skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.