Wasteland Builder by Anders Bjarby — 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.

Any town on Earth becomes a Mad Max battle-car browser game: OpenStreetMap to a Blender city to a three.js game.

What it does

A template repo whose agent skills turn a named place into a Mad Max battle-car game. The pipeline searches the place on OpenStreetMap, downloads buildings, streets, water, trees and street furniture plus terrain, extrudes an editable Blender city (storeys, facades, roofs, churches with towers), exports streamed 60 m tiles and a street graph, and themes a three.js game with the town's name, landmarks, narrator and radio. Refinement rounds fix buildings from Street View, satellite views and your photos, logged per round; it comes from Kalmar Wasteland, refined over 140 rounds. Without an agent, python3 wasteland.py doctor then make "<place>" does the same. Beta, with OpenStreetMap attribution required.

Use when

Not for

Install

Example output

https://raw.githubusercontent.com/fltman/wasteland-builder/main/docs/images/visby-street.jpg — Visby straight from the generator (about a minute): OSM footprints extruded into a Blender city, rendered in the game (credit: Anders Bjarby (wasteland-builder); map data © OpenStreetMap contributors, https://github.com/fltman/wasteland-builder#refinement-rounds-from-generated-to-real)

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.