Landscape Auto Material logo

Landscape Auto Material

Community
kevinpbuckley
landscape-auto-material

Create production-quality landscape materials with the master-material + material-function + material-instance paradigm, RVT, and auto-layering. Use when the user asks for an auto/procedural landscape material, slope/altitude/distance-based layer blending, Runtime Virtual Textures, biome configuration via instances, or layer material functions. For basic layer-blend materials load landscape-materials.

Overview

Publisherkevinpbuckley
RepositoryVibeUE
Skill namelandscape-auto-material
Stars
735
Forks
161
Bundled files
7
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by kevinpbuckley on GitHub. Read the source before you install it.

Installation

Install the Landscape Auto Material AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/landscape-auto-material
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git /tmp/VibeUE
mkdir -p .claude/skills
cp -r /tmp/VibeUE/Content/Skills/landscape-auto-material .claude/skills/landscape-auto-material
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Landscape Auto Material in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Landscape Auto Material on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Landscape Auto Material is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Landscape Auto-Material System Skill

When to Use This Skill

Use this skill when you need production-quality landscape materials with:

  • A master material → material instance workflow (artists change parameters, not graphs)
  • Automatic layer blending by slope, altitude, or distance
  • Material functions for reusable logic (layer sampling, color correction, etc.)
  • Runtime Virtual Textures for scalable landscape rendering
  • Biome configuration through material instances (swap textures/thresholds, same master)

For simple prototyping with 2-5 painted layers, load the landscape-materials skill instead (the engine's AgentSkillToolset GetSkills exposes it).

Architecture Overview

The Master Material Paradigm

Master Material (M_Landscape_Master)
 ├── Material Functions (reusable logic blocks)
 │   ├── MF_AutoLayer     ── auto-selects layers by altitude/slope
 │   ├── MF_Slope_Blend   ── slope mask (0=flat, 1=steep)
 │   ├── MF_Altitude_Blend ── height mask (0=below, 1=above)
 │   ├── MF_Layer_Grass    ── per-layer texture sampling
 │   ├── MF_Layer_Rock     ── per-layer texture sampling
 │   ├── MF_RVT            ── Runtime Virtual Texture output
 │   └── MF_Distance_Blend ── LOD transitions
 ├── Exposed Parameters (50+ scalar/vector/texture/switch)
 └── Material Outputs (BaseColor, Normal, Roughness, WPO, RVT)

Material Instance (MI_Landscape_Biome_01)
 ├── Inherits master material graph
 ├── Overrides parameters only (no graph editing)
 └── Different biomes = different instances of same master

Why this is better than manual graph building:

  • Reusability: Material functions used across multiple masters
  • Artist-friendly: Biome artists edit parameters in instances, never touch the graph
  • Performance: Compiled once in master, instances are cheap
  • Maintainability: Fix a function → all materials using it update

Critical Rules

🚨 Inspect Before Modifying Existing Materials or Functions

Before modifying an existing master material or material function, MUST export and review its current state:

python
import unreal, json

# For materials:
graph = json.loads(unreal.MaterialNodeService.export_material_graph("/Game/Materials/M_Landscape_Master"))
print(f"Expressions: {len(graph['expressions'])}, Connections: {len(graph['connections'])}")
for expr in graph['expressions']:
    name = expr.get('parameter_name') or expr.get('function_path') or expr.get('class')
    print(f"  [{expr['id']}] {expr['class']} - {name}")

# For material functions:
func_info = unreal.MaterialNodeService.get_function_info("/Game/Functions/MF_AutoLayer")
func_graph = json.loads(unreal.MaterialNodeService.export_function_graph("/Game/Functions/MF_AutoLayer"))

Why: Auto-material master graphs can have 50+ expressions and complex function call chains. Adding nodes without reviewing first creates duplicates, broken connections, and compilation failures. Always export → review → plan → modify.

Four Services Work Together

ServiceRole
MaterialNodeServiceMaterial function creation/introspection, expression graphs
MaterialServiceMaterial/instance creation, properties, bulk parameters
LandscapeMaterialServiceCreateAutoMaterial, FindLandscapeTextures, layer infos
RuntimeVirtualTextureServiceRVT assets, volumes, landscape assignment

⚠️ compile_material Is Slow — Use Separate Code Blocks

Master materials with many function calls are very slow to compile. NEVER create + compile in the same block.

Split into steps:

  1. Block 1: Create material, add functions, connect graph, save
  2. Block 2: compile_material() alone (may take minutes)
  3. Block 3: Create instances, set parameters, assign to landscape

⚠️ Enable Virtual Texturing on Material

If using RVT, you MUST set bUsedWithVirtualTexturing = true on the master material:

python
unreal.MaterialService.set_property(mat_path, "bUsedWithVirtualTexturing", "true")

⚠️ Material Functions Must Be Saved Before Use

After creating a material function and adding inputs/outputs, save it before calling it from a material:

python
unreal.EditorAssetLibrary.save_asset(func_path)

⚠️ Function Inputs/Outputs Need Sort Priority

Set SortPriority to control pin ordering. Lower values appear first:

python
unreal.MaterialNodeService.add_function_input(func_path, "BaseColor", "Vector3", 0)
unreal.MaterialNodeService.add_function_input(func_path, "Normal", "Vector3", 1)
unreal.MaterialNodeService.add_function_input(func_path, "Roughness", "Scalar", 2)

Sub-docs available

Read these sibling files directly (the engine AgentSkillToolset GetSkills is the loader; this SKILL.md is the index, the deeper docs live alongside it):

Sub-docWhat's inside
reference-example.mdConcrete reference architecture: full master material function chain, biome instances, texture naming convention
workflows.mdStep-by-step recipes: auto-material creation, biome instances, building/inspecting material functions, RVT setup
material-functions.mdPatterns for common material functions (Slope_Blend, Altitude_Blend, Layer_*, RVT) + EFunctionInputType reference table
architecture-details.mdDeep dive on the auto-layer function chain, mask combination math, slope/altitude function creation, extension points
biomes-and-templates.mdBiome comparison table, static-switch feature toggles, naming conventions, standard layer function template (inputs/outputs/catalog)
parameter-reference.mdFull parameter catalog: layer textures, auto-blend, distance/LOD, color correction, feature toggles, displacement, RVT, FindLandscapeTextures suffix matching
rvt-setup.mdRVT material types, sizing guidelines, inspection code, common RVT issues with causes/fixes

Common Mistakes

1. Forgetting bUsedWithVirtualTexturing

Material has RVT output node but rendering fails → set the property before compiling.

2. No RVT Volume Actor

Material outputs to RVT but nothing reads it → create RuntimeVirtualTextureVolume covering the landscape.

3. RVT MaterialType Mismatch

Volume expects BaseColor_Normal_Roughness but material only outputs BaseColor → types must match.

4. Not Saving Functions Before Referencing

Create function → immediately create function call → fails because function not saved. Always save_asset() the function first.

5. Missing bExposeToLibrary

Material function created but doesn't appear in the material editor's function library → set bExposeToLibrary=True.

6. Compiling in Same Block as Creation

Master materials with many function calls take minutes to compile. Putting create + compile in one code block causes timeout.

7. Wrong Bulk Parameter Types

set_instance_parameters_bulk requires exact type strings: "Scalar", "Vector", "Texture", "StaticSwitch". Typos silently skip parameters.

8. Static Switch Parameters Need UpdateStaticPermutation

Static switches are compile-time. After setting via bulk set, the instance needs a static permutation update (handled internally by set_instance_parameters_bulk).

9. Auto Layer Has Zero Weights

Landscape looks unpainted or auto-blend never appears when all layer weights are 0. Verify with get_weights_in_region and fill/paint the base auto layer at least once.

10. Layer Info/Material Family Mismatch

If a landscape is switched to a different master/instance family, existing Layer Info assets may not match expected layer names/workflow. Recreate layer infos from the active material's layer list and reassign them.

11. RVT Volume Missing or Mis-sized

RVT asset assignment alone is not enough. Ensure each landscape has an RVT volume covering its bounds; recreate volume per landscape after major transform/scale changes.


Related Skills

TaskSkills to Load
Sculpt terrain onlylandscape
Simple painted material (2-5 layers)landscape + landscape-materials
Auto-blending material (production)landscape + landscape-auto-material
Material instances/biome configurationlandscape-auto-material
Material functions (non-landscape)materials
Full pipeline (terrain + auto-material + RVT)landscape + landscape-auto-material

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Landscape Auto Material AI skill do?

Create production-quality landscape materials with the master-material + material-function + material-instance paradigm, RVT, and auto-layering. Use when the user asks for an auto/procedural landscape material, slope/altitude/distance-based layer blending, Runtime Virtual Textures, biome configuration via instances, or layer material functions. For basic layer-blend materials load landscape-materials.

Why use Landscape Auto Material on TypingMind?

Because you install it once and use it with any model. Landscape Auto Material is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Landscape Auto Material in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/landscape-auto-material. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Landscape Auto Material?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Landscape Auto Material?

As many as you like. As long as a model supports skills, you can use Landscape Auto Material with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Landscape Auto Material AI skill free?

Yes. It is published on GitHub by kevinpbuckley under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇