Ui Composition Engine logo

Ui Composition Engine

Community
thakur698
ui-composition-engine

Defines concrete layout libraries, premium bento systems, and strict composition constraints to prevent repetitive slop.

Overview

Publisherthakur698
Repositoryuniversal-ui-skills
Skill nameui-composition-engine
Stars
5
Forks
0
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 thakur698 on GitHub. Read the source before you install it.

Installation

Install the Ui Composition Engine 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/thakur698/universal-ui-skills/tree/main/.agents/plugins/universal-ui/skills/ui-composition-engine
  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/thakur698/universal-ui-skills.git /tmp/universal-ui-skills
mkdir -p .claude/skills
cp -r /tmp/universal-ui-skills/.agents/plugins/universal-ui/skills/ui-composition-engine .claude/skills/ui-composition-engine
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ui Composition Engine 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 Ui Composition Engine 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 Ui Composition Engine 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.

UI Composition Engine

Mission

Abstract rules like "avoid repetitive layouts" fail in practice. The Composition Engine defines a library of layout families, a first-class premium Bento system, and strict mechanical rules for combining them across Desktop and Mobile.


Layout Families

The agent must consciously select from these structural families:

  • ASYMMETRIC HERO: Off-center focal points, unequal column weights, dramatic visual balance.
  • EDITORIAL SPLIT: Hard 50/50 vertical division pairing bold typography with high-impact media.
  • FULL-WIDTH VISUAL: Immersive, edge-to-edge media carrying narrative weight.
  • PREMIUM BENTO: Asymmetric, compartmentalized tiles with high media dominance and variable cell sizes.
  • STICKY STORY / SPLIT-PIN: Pinned media or diagram on one side while narrative points scroll past.
  • OFFSET GRID: Staggered items breaking strict row/column alignment.
  • MASONRY: Interlocking tiles of varying heights.
  • STACKED STORY: Narrative, sequential horizontal blocks with staged reveals.
  • DENSE DATA: High information density matrices, tables, or telemetry clusters.
  • IMMERSIVE IMAGE: Photography or 3D visual dictates the structural geometry.
  • TEXT-LED: Typography is the primary visual asset; zero/minimal imagery.
  • INTERACTION-LED: The interface is an interactive canvas/tool, not a passive document.
  • DIAGRAM-LED: Technical, architectural, and structural system visualization.

The Premium Bento System

A Bento layout must NEVER mean "many identical rounded cards arranged in a generic grid with an icon in each card."

Core Bento Requirements:

  1. Visual Hierarchy & Anchors: 1 or 2 cells MUST act as dominant visual anchors (e.g. col-span-2 row-span-2 or full-width banner).
  2. Variable Cell Sizes & Asymmetry: Mix large hero cells ($50%\text{--}65%$ area) with compact detail cells.
  3. Media Dominance: Feature real visual assets—full-bleed screenshots, interactive models, live latency maps, technical diagrams—not empty text boxes.
  4. Editorial Captions: Pair visual tiles with terse, high-impact editorial copy rather than paragraph dumps.
  5. Edge-Aligned Content & Insets: Align telemetry numbers, badges, or code tokens cleanly to cell perimeters.
  6. Intentional Rhythm & Negative Space: Avoid uniform card walls; introduce optical breathing room and varied aspect ratios ($16:9$, $1:1$, $21:9$).
  7. Interactive Cells: Include live preview toggles, scrubbable widgets, or hover-reactive states where appropriate.

Banned Bento Anti-Patterns:

  • ❌ 6 identical white-on-white or dark-on-dark cards with identical padding and radius.
  • ❌ Every card containing a random generic icon in a rounded square.
  • ❌ Meaningless placeholder metric cards ("99.9% Faster") without concrete data context.
  • ❌ Decorative mini dashboards that lack functional meaning.

Strict Composition Rules

  1. Variance Rule: No layout family may dominate the whole page. For an 8-section landing page, you MUST use a minimum of 4 distinct composition families.
  2. Fatigue Rule: Maximum 2 consecutive image/text splits.
  3. Bento Rule: No empty bento cells; exact cell count must match content.
  4. Hero Rule: No repeated hero structures (do not use a Hero layout twice on one page).
  5. Mobile Recomposition: Mobile composition MUST be intentionally recomposed. Do not just blindly flex-direction: column. Consider thumb-zones, sticky navs, and horizontal scrolling for dense data.
  6. Icon-Grid Ban: Do not use [Icon] + Title + Description grids repeated 3–6 times as the primary feature presentation. Prefer media-rich, diagram-led, or bento compositions.

Execution

Before implementing, the agent must output a COMPOSITION MAP assigning a specific layout family to each section of the UI:

text
COMPOSITION MAP:
- Hero: ASYMMETRIC HERO (Diagram-led terminal + live endpoint status)
- Proof: FULL-WIDTH LOGO STRIP (Monochrome verified SVG marks)
- Features: PREMIUM BENTO (Anchor cell with live telemetry map + 2 technical sub-tiles)
- Deep Dive: STICKY STORY (Pinned architecture diagram + 3 scrolling integration phases)
- Performance: DENSE DATA (Sub-millisecond latency benchmark matrix)
- CTA: EDITORIAL SPLIT (Single focused action + typography)

Frequently asked questions

What does the Ui Composition Engine AI skill do?

Defines concrete layout libraries, premium bento systems, and strict composition constraints to prevent repetitive slop.

Why use Ui Composition Engine on TypingMind?

Because you install it once and use it with any model. Ui Composition Engine 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 Ui Composition Engine in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thakur698/universal-ui-skills/tree/main/.agents/plugins/universal-ui/skills/ui-composition-engine. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ui Composition Engine?

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 Ui Composition Engine?

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

Is the Ui Composition Engine AI skill free?

Yes. It is published on GitHub by thakur698 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 👇