Fab

Community

kevinpbuckley

fab

Search Fab's public free catalog (including Quixel Megascans) and directly import eligible assets without adding them to the account library, or discover/import the signed-in Epic account's owned Fab library. Use for free Fab/Quixel searches, owned-library questions, compatibility checks, and Fab imports. No purchasing or entitlement claiming.

Overview

Publisher	kevinpbuckley
Repository	`VibeUE`
Skill name	`fab`
Stars	735
Forks	161
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/fab
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.

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/fab .claude/skills/fab

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fab 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 Fab 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 Fab 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.

Fab asset import

FabService supports two deliberately separate paths:

Public free catalog: search exact zero-price listings and directly import eligible glTF/GLB downloads. This does not sign in, purchase, claim an entitlement, or add the listing to My Library.
Owned library: use the editor/launcher Epic session to list and import assets already owned by the account, including migrated Unreal Marketplace items.

Public free flow (Quixel/Megascans and other sellers)

Call search_free_catalog(query="", seller_filter="Quixel Megascans", format_filter="gltf"). Results are compact and include id, title, seller, price, formats, thumbnail, and an opaque next_cursor. Results require an exact-zero Personal tier; UEFN-reference-only offers are excluded. No authentication is required.
Show the chosen result and the Fab EULA to the user. Never set accept_eula=true on the user's behalf. It must represent their explicit acceptance.
Call import_free_asset(listing_id, quality="High", format="gltf", license_slug="personal", accept_eula=true). The service re-fetches the listing and requires the selected license price to still be exactly zero before it requests a signed download.
Poll import_status(listing_id) until imported or failed, then verify a returned asset path with unreal.EditorAssetLibrary.does_asset_exist(path).

Direct free imports land under /Game/Fab/Free/<Title>. The original archive is cached under the project's Saved/Fab/Free directory; no raw-file export API is exposed. ZIP paths are validated before extraction. The first version supports Fab glTF/GLB ZIPs through automated Unreal Interchange import. That is suitable for Quixel 3D assets, but it does not reproduce every private Megascans material setup or support every Fab product format yet.

Owned-library flow

Call auth_status() first. If it is not authenticated, tell the user to open the Fab window or launch the editor from the Epic Games Launcher.
Call list_library(...); use refresh=true only when the account library may have changed.
Call get_asset(asset_id) to inspect versions and compatibility.
Call import_asset(asset_id, ...), then poll import_status(asset_id).
Verify the returned /Game/... paths before reporting success.

Owned BuildPatch packs and plugins are supported. Sparse or non-BuildPatch owned assets may still be discoverable without being importable through import_asset; use the public-free path only when the listing is currently free and provides a supported source format.

Rules

Owned complete projects

Owned COMPLETE_PROJECT products are downloaded into Saved/Fab/Projects/<asset-id>. Poll until status: "staged" or failed; staged is a terminal download state, not an import into the active project. Inspect the returned staging_root, source .uproject engine association, and vendor merge instructions. Save and close Unreal before copying approved content folders into the host. Preserve vendor package paths, check destination collisions, and do not merge the sample project's config or .uproject. The remote build-service version string alone does not establish asset compatibility.

Import rules

Never purchase, claim, call add-to-library, or accept a license on the user's behalf.
Never treat a search filter as proof of price. import_free_asset performs the authoritative zero-price check immediately before download.
Never expose signed download URLs or offer to save distributable raw asset files elsewhere.
Imports are asynchronous and idempotent within the editor session; poll with a finite interval.
These Fab web endpoints are unofficial and may change. Surface their errors rather than retrying the same request blindly.

Every method returns a JSON string with success: true|false. Errors include error_code and error. If every method returns error_code: "UNSUPPORTED", the engine install VibeUE was built against lacks the engine Fab plugin (Engine/Plugins/Fab) and FabService was compiled out (issue #525) — the rest of VibeUE is unaffected. Report this to the user; do not retry. Discover exact signatures with discover_python_class('unreal.FabService'). Current methods: auth_status, list_library, get_asset, search_free_catalog, import_asset, import_free_asset, and import_status.

Frequently asked questions

What does the Fab AI skill do?

Why use Fab on TypingMind?

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

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

Which AI models can use Fab?

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 Fab?

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

Is the Fab 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

Android Clean Architecture

affaan-m

CommunityPopular

Android と Kotlin Multiplatform プロジェクトのクリーンアーキテクチャパターン — モジュール構造、依存関係ルール、UseCase、Repository、データ層パターン。

Blackbox

Delegate coding tasks to the Blackbox AI multi-model CLI.

Comps Analysis

Build comparable-company valuation workbooks in Excel.

Weights And Biases

W&B: log ML experiments, sweeps, model registry, dashboards.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Fab asset import

Public free flow (Quixel/Megascans and other sellers)

Owned-library flow

Rules

Owned complete projects

Import rules

Frequently asked questions

Related AI Skills

Set up your own AI workspace now