Kiln Compose Scene logo

Kiln Compose Scene

Organization
instruktlabs
kiln-compose-scene

Compose existing assets into an exported scene or interactive proving environment. Use Kiln welding to fit assets into a game's own geometry batches, materials, collision and interaction systems.

Overview

Publisherinstruktlabs
Repositorykiln
Skill namekiln-compose-scene
Stars
292
Forks
24
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Kiln Compose Scene 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/instruktlabs/kiln/tree/main/skills/kiln-compose-scene
  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/instruktlabs/kiln.git /tmp/kiln
mkdir -p .claude/skills
cp -r /tmp/kiln/skills/kiln-compose-scene .claude/skills/kiln-compose-scene
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kiln Compose Scene 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 Kiln Compose Scene 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 Kiln Compose Scene 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.

Compose and weld a scene from existing assets

Use this optional workflow when the task concerns several assets. Keep placement separate from individual source authoring so moving an object does not regenerate its geometry.

A scene or environment can be a standalone deliverable. A Kiln project is optional organization for a shared brief, inventory and design profile; composing several assets does not by itself require one. When composing a project's proving scene, use its selected saved inventory revisions and preserve the individual editable assets.

Read the composition API notes when using the library. These are host/project APIs, not tools automatically added to the Kiln MCP surface.

For Kiln welding, where authored pieces become part of an existing game's structures and rendering, read the welding workflow. It covers placement, surface-role mapping, geometry batches and preserving moving parts, collision and interaction anchors. Welding is a consumer workflow, not a new Kiln tool or a requirement to fuse every vertex.

Choose the deliverable before composing. A single scene GLB and an interactive application have different requirements; exporting a monolithic GLB is optional. For terrain, animated environments, traversal or measured optimization, read runtime scene guidance. Keep those systems in the consuming scene rather than adding them to every asset-authoring task. To reduce draw calls, count them per render pass first. Then merge by material within each animation and interaction anchor, and give shadow and reflection passes their own stand-ins. Do not flatten an asset into one mesh.

Inspect each GLB with inspectGlbIntegration(bytes) and confirm it returned a usable manifest. Use units, axes, bounds, and ground information to place the object deliberately. Give instances stable names and explicit transforms.

Start with the layout's major structures, routes and useful sightlines, then place smaller objects. Use world-space AABB checks to find candidate collisions; inspect reported intersections instead of treating every overlap as an error. Intentional embedding and empty space inside bounds both matter.

When traversal is part of the brief, connect destinations with usable routes and test access through the placed doors, gates and crossings with the intended actor. Terrain and paths are scene infrastructure unless included in the asset brief. Use each asset's intended placement origin; hide an optional presentation base only through a supported part/variant rather than burying the whole plant or prop.

For a scene GLB, export with composeSceneGLB(parts, options). Select material optimization and animation retention deliberately. Review skipped-part warnings and confirm required inputs survived. For an application, retain the individual inputs and reproducible placement/runtime configuration. Inspect either result in its destination scene, including traversal, collision, contact, and relevant camera paths.

Report input assets, important transforms, intentional intersections, exporter warnings, and interactions actually checked. Do not infer playability from an overlap-free layout alone.

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 Kiln Compose Scene AI skill do?

Compose existing assets into an exported scene or interactive proving environment. Use Kiln welding to fit assets into a game's own geometry batches, materials, collision and interaction systems.

Why use Kiln Compose Scene on TypingMind?

Because you install it once and use it with any model. Kiln Compose Scene 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 Kiln Compose Scene in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/instruktlabs/kiln/tree/main/skills/kiln-compose-scene. 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 Kiln Compose Scene?

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 Kiln Compose Scene?

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

Is the Kiln Compose Scene AI skill free?

Yes. It is published on GitHub by instruktlabs 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 👇