Kiln Hosted logo

Kiln Hosted

Organization
instruktlabs
kiln-hosted

Create, inspect, revise and deliver editable 3D assets through Kiln's connected hosted service, or reopen assets saved in that account. Use for hosted Kiln work; keep an existing local Kiln workspace on its local workflow unless the user chooses hosted storage.

Overview

Publisherinstruktlabs
Repositorykiln
Skill namekiln-hosted
Stars
292
Forks
24
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Kiln Hosted 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/plugins/kiln-hosted/skills/kiln-hosted
  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/plugins/kiln-hosted/skills/kiln-hosted .claude/skills/kiln-hosted
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kiln Hosted 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 Hosted 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 Hosted 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.

Work with hosted Kiln

Use the connected Kiln tools for the requested asset work. Account connection and sign-in belong to the host and Kiln website; never ask for a password, token or code in chat. If the connection is unavailable, explain that step without pretending a local installation can access the hosted account.

Read the program contract before authoring new source. kiln_discover retrieves geometry helpers, examples and input shapes; kiln_capabilities reports hosted runtime facts. Use the tool schemas currently exposed by this connection. Renderer setup and local CLI instructions in general engine references are not steps for this hosted workflow.

Create and review

Match the brief's subject, scale, style and destination. Standalone assets need no project. Use geometry recipes for construction, curved surfaces and joints that must fit or move; search Discovery for unfamiliar helper contracts. Preserve experimental labels and limitations in the catalog. The authoring frame is metres, +X forward, +Y up, +Z right.

Submit new source once to kiln_validate or kiln_render, then copy the returned programRef exactly for later reads, edits and views, including after a failed build. Use kiln_source to obtain exact anchors and kiln_edit for revisions; keep the new reference and inspect build success separately from edit success.

Inspect returned images and structural findings against the brief. Select camera views that answer a concrete shape, joint, interior or motion question. Use exact returned part paths and numeric inspection for required fit or clearance. Read viewFidelity: a CPU fallback can establish shape, not PBR material appearance. Do not claim material quality or destination performance from a passing structural check or an unavailable view.

Hosted calls use quotas. Do not repeat an unchanged render without a new review question. On admission refusal or a quota error, report the limit and preserve existing references; do not switch accounts or keep retrying to evade it.

Materials and saved work

For library materials, use kiln_material_search with scope: 'all', 'presets' or 'saved', and kiln_material_get to read exact saved resources. kiln_material_create accepts a definition with kind: 'preset' or 'procedural'; kiln_material_import retains an imported resource. Read their current schemas and Discovery shapes; supply known provenance and licensing rather than inventing it. Carry the same materialId/revisionId dependency pins through each render, edit, inspection and save that needs them. A program reference alone does not supply material context.

Use kiln_assets_collections to list destinations and kiln_assets_search to browse saved assets. Omit collection to search all configured collections, or select one explicitly. kiln_assets_get reads a selected revision and its downloads; kiln_assets_restore returns its exact source reference for editing. Preserve the collection, asset ID and revision ID together. The hosted presentation uses these domain operations from the shared engine contract; follow their advertised schemas.

Deliver the requested result

For a requested saved or downloadable asset, save the reviewed final programRef with kiln_save, using the requested collection or the documented default. For a revision, supply its asset ID and parent revision so earlier work stays intact. Use the same material dependencies and reviewed backdrop. Do not save every draft or save a preview-only exploration unless the user requested persistence.

Use kiln_present on the exact saved revision when the host supports an interactive viewer, including ChatGPT; a text download link alone does not display that viewer. Use kiln_export for the requested files or editable bundle. Return actual download links from the result; they require the owning browser account and expire. Get fresh links by reopening the saved revision when needed. Present an interactive card only when the host supports it; otherwise use the supplied links/resources. Never invent public links or claim native attachment support.

Report the result, what was reviewed and any remaining limitation. Unsaved work expires after seven days. Saved assets remain within quota until deleted; account and deletion controls are on the Kiln website, not additional hidden MCP tools.

Frequently asked questions

What does the Kiln Hosted AI skill do?

Create, inspect, revise and deliver editable 3D assets through Kiln's connected hosted service, or reopen assets saved in that account. Use for hosted Kiln work; keep an existing local Kiln workspace on its local workflow unless the user chooses hosted storage.

Why use Kiln Hosted on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/instruktlabs/kiln/tree/main/plugins/kiln-hosted/skills/kiln-hosted. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kiln Hosted?

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 Hosted?

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

Is the Kiln Hosted 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 👇