y3-gen-terrain-from-image

Generate Y3 Editor terrain and texture grids from a 2D map image.

Updated Apr 4, 2026
One-click install
npx skills add https://github.com/WindXRan/y3td --skill y3-gen-terrain-from-image-windxran
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: y3-gen-terrain-from-image
Source: https://github.com/WindXRan/y3td/tree/main/.claude/skills/y3-gen-terrain-from-image
Command: npx skills add https://github.com/WindXRan/y3td --skill y3-gen-terrain-from-image-windxran

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires opencv-python, numpy, requests, scipy, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill converts a 2D map image into Y3 Editor terrain data, removing the need to manually recreate terrain layouts and textures cell-by-cell.

Core Features & Use Cases

  • Two-round vision + generation pipeline: clusters image colors, detects water and continents, then identifies decoration intent (trees/bridges/land motifs) through structured JSON outputs.
  • Deterministic CV-driven geometry: uses CV clustering and continent splitting to generate grid-aligned CSV inputs, ensuring terrain layout comes from the image rather than guessing.
  • MCP-driven terrain and decoration writing: writes terrain layers and textures via Y3 Editor MCP tools, then places decoration entities from generated results.

Quick Start

Provide the map image file path, then run the Skill to generate terrain_grid.csv and texture_grid.csv and write the result into your loaded Y3 map through MCP (including decoration placement).

Frequently Asked Questions about y3-gen-terrain-from-image

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

FAQPage Schema
How do I generate Y3 Editor terrain from a 2D map image?

To generate Y3 Editor terrain from a 2D map image, provide the image file path so the CV+AI pipeline can cluster colors, detect water and continents, and write terrain grids via MCP tools.

How does computer vision clustering detect water and continents for terrain generation?

Computer vision clustering detects water and continents by analyzing the 2D map image's colors, splitting continents to generate grid-aligned CSV inputs, ensuring terrain layout comes from the image rather than guessing.

Do I need MCP tools connected to write terrain and texture grids into Y3 Editor?

Yes, you need an active MCP connection because the Skill writes terrain layers and texture grids directly into your loaded Y3 map through MCP tools, featuring failure-safe MCP connection handling during the process.

Can I use hand-drawn planning sketches to place environment decorations in Y3 Editor?

Yes, you can use hand-drawn planning sketches to place environment decorations in Y3 Editor, as the pipeline identifies decoration intent like trees, bridges, and land motifs from the image before writing via MCP.

What are the limitations of using image processing to generate terrain grids for Y3?

Limitations include strict validation rules: you must run get_map_info for dimensions first, perform CV clustering before CSV generation, and use a fixed working output directory for the generated terrain_grid.csv and texture_grid.csv files.