Lucian Uxui logo

Lucian Uxui

Community
Seokwoooo
lucian-uxui

Builds sites, pages and components from Lucian UX/UI Prompt (lucianlabs.dev/uxui-prompt), a growing library of polished, dependency-free interactive UI elements with light and dark themes, keyboard and touch support and reduced motion. It covers buttons, toggles, inputs, menus and tabs, cards, sign-in and sign-up, toasts, loaders, empty and error states, charts, app-level tools like editors, dashboards, schedulers and kanban boards, and website sections and motion such as heroes, pricing, testimonials, sign-up forms, text and scroll animations, product showcases and animated charts. Searches the library, fetches only the chosen elements and ports them into the project's framework and theme. Use when the user names lucian-uxui, Lucian UX/UI or lucianlabs elements, or asks to build UI that should use them, e.g. "build a landing page with lucian-uxui", "lucian-uxui 스킬로 사이트 만들어줘", "루샨 UX/UI 요소로 로그인 화면 만들어줘". Not for backend work or for editing the library itself.

Overview

PublisherSeokwoooo
Repositorylucian-uxui
Skill namelucian-uxui
Stars
15
Forks
3
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Lucian Uxui 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/Seokwoooo/lucian-uxui/tree/main/skills/lucian-uxui
  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/Seokwoooo/lucian-uxui.git /tmp/lucian-uxui
mkdir -p .claude/skills
cp -r /tmp/lucian-uxui/skills/lucian-uxui .claude/skills/lucian-uxui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lucian Uxui 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 Lucian Uxui 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 Lucian Uxui 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.

Lucian UX/UI

Lucian UX/UI Prompt is a library of interactive UI elements. Each element is one self-contained snippet: a <style> block scoped to .uNNN, a root <div class="ux uNNN">, and a <script>. Every element reads its colors from --ux-* theme tokens. The library keeps growing (400 elements now, thousands later), so never assume what it contains. Search it every time.

All access goes through the bundled CLI. It caches on disk and falls back to a GitHub mirror when lucianlabs.dev is unreachable. <skill-dir> is the folder that contains this SKILL.md:

sh
node <skill-dir>/scripts/lucian-uxui.mjs <command>
CommandUse
search <words...>Best matches for one UI part, such as search pricing toggle or search 로그인. Add --category <slug> or --limit 20 to narrow or widen.
listCategories with counts. list --category <slug> lists every element in one category.
get <id> [<id>...]Full code for up to 8 elements. Fetch only the ones you will port.
tokensThe --ux-* light and dark tokens plus the .ux base rules that every element needs.
infoData source, catalog version and cache folder, for troubleshooting.

Add --lang ko for Korean copy. The default is --lang en. Use --out <path> with get or tokens to write files instead of printing them.

Workflow

  1. Read the project. Find the framework (React, Next, Vue, Svelte, Astro, plain HTML), the styling approach (CSS modules, Tailwind, global CSS), the theming approach (data-theme, a .dark class, CSS variables) and the language of the site's copy. If there is no project yet, use what the user asked for. If they named nothing, use plain HTML, CSS and JS.
  2. Break the request into UI parts, for example: header nav, hero call-to-action button, monthly/yearly pricing toggle, sign-up form, FAQ, success toast, empty state. You build the page layout and sections (hero, pricing grid, footer) yourself. Lucian supplies the interactive parts inside them.
  3. Search once per part. If the user names specific elements by number or gallery link (#055, 55, lucianlabs.dev/uxui-prompt/#055), skip the search for them and get those exact elements. English keywords match best, and Korean also works. Read the one-line summaries and pick the element whose behavior fits the part. Prefer a Lucian element whenever a reasonable match exists, rather than writing your own. Build from scratch only when nothing fits, and match the Lucian look with the same tokens.
  4. Fetch what you picked: get <ids>, at most a few at a time. Also run tokens once per project.
  5. Port each element following references/porting.md. Read it before your first port.
  6. Check both themes, a narrow mobile width (375px), keyboard use and prefers-reduced-motion.
  7. Report. End your reply with a list of the elements you used. Give one line per element in the form #ID title: where it is used, what you adapted, https://lucianlabs.dev/uxui-prompt/#ID, and then list anything you could not check.

Language

Use the language of the site's copy: --lang ko for a Korean site and --lang en for everything else. When the language is unclear, use English. Element text is sample copy either way. Replace it with the project's real content.

Rules

  • Use only code returned by get. Never invent element IDs or reconstruct an element from memory or from its summary.
  • Keep the first line of each element, the <!-- Lucian UX/UI Prompt #ID · MIT License ... --> comment, at the top of the component file you create from it. The license requires it.
  • Do not dump the whole catalog into context or download every element. Use search, and use list --category to browse.
  • Port an element's structure, shapes and motion values (durations, curves, delays) as they are. Adapt the framework, data and colors, not the design.

When the CLI cannot run

  • Network blocked (exit code 3, common in sandboxes such as Codex): the CLI needs HTTPS access to lucianlabs.dev or, as a fallback, raw.githubusercontent.com. Request network permission for the command and rerun it. If the network stays unavailable and nothing is cached, tell the user. Do not substitute invented elements.
  • No Node.js: use curl with the same data:
    sh
    curl -fsSL https://lucianlabs.dev/uxui-prompt/api/v1/en/catalog.tsv | grep -i "toggle"   # columns: id, cat, category, title, tags, shape, hash, summary
    curl -fsSL https://lucianlabs.dev/uxui-prompt/api/v1/en/e/056.txt                      # one element
    curl -fsSL https://lucianlabs.dev/uxui-prompt/api/v1/en/tokens.css                     # tokens

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 Lucian Uxui AI skill do?

Builds sites, pages and components from Lucian UX/UI Prompt (lucianlabs.dev/uxui-prompt), a growing library of polished, dependency-free interactive UI elements with light and dark themes, keyboard and touch support and reduced motion. It covers buttons, toggles, inputs, menus and tabs, cards, sign-in and sign-up, toasts, loaders, empty and error states, charts, app-level tools like editors, dashboards, schedulers and kanban boards, and website sections and motion such as heroes, pricing, testimonials, sign-up forms, text and scroll animations, product showcases and animated charts. Searche...

Why use Lucian Uxui on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Seokwoooo/lucian-uxui/tree/main/skills/lucian-uxui. 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 Lucian Uxui?

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 Lucian Uxui?

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

Is the Lucian Uxui AI skill free?

Yes. It is published on GitHub by Seokwoooo 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 👇