Ui Media Composition logo

Ui Media Composition

Community
thakur698
ui-media-composition

Media-first composition system prioritizing images, video, illustrations, and diagrams over generic icon grids.

Overview

Publisherthakur698
Repositoryuniversal-ui-skills
Skill nameui-media-composition
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 Media Composition 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-media-composition
  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-media-composition .claude/skills/ui-media-composition
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ui Media Composition 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 Media Composition 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 Media Composition 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 Media Composition

Mission

Universal UI Skills treats IMAGE, VIDEO, ILLUSTRATION, DIAGRAM, TYPOGRAPHY, LAYOUT, and MOTION as the primary visual storytelling language.

Whenever building a website, app, dashboard, or product experience with Universal UI Skills, use more and more images than icons. Primary visual communication MUST be carried by rich visual assets: real photography, product renders, live UI captures, 3D artwork, custom illustrations, or technical diagrams.

Icons are strictly utility tools (navigation, actions, system controls), NOT the default visual language. Never use icons as a lazy replacement for meaningful visual media.


Three Non-Negotiable Composition Rules

  1. Maximize Image Prominence: Populate sections with rich imagery, product renders, photography, and diagrams rather than icon lists. Images carry the narrative; icons do not.
  2. Zero Pills: Do NOT create pills. Strictly avoid rounded-full pill badges, floating pill tags, pill chips, or pill containers (e.g. <span class="rounded-full px-3 py-1 bg-...">...</span>). Use crisp typography, subtle borders, or spatial layout instead.
  3. No Background Color Behind Icons: Do NOT add background colors, tinted boxes, colored circles, square containers, or glass tiles behind icons. Icons must sit directly on the background surface or inline with copy without decorative box fills.

Visual Hierarchy Priority

  1. Product imagery / photography (Hardware, UI, real contexts)
  2. Custom illustrations / diagrams (Technical architectures, workflows, editorial concepts)
  3. Rich media / video (Product reveals, interactive frame scrubbing, loops)
  4. Typography + composition (Asymmetric bento scales, editorial type hierarchies)
  5. Interactive visual objects (Live sandboxes, canvas models, responsive widgets)
  6. Premium animated icons (Stateful Rive runtimes, lightweight Lottie vector sequences)
  7. Static utility icons (Minimal functional glyphs for common navigation/actions)

INTERACTIVE HERO MANDATE

For website UI tasks, DO NOT default to:

  • centered headline
  • subtitle
  • two buttons
  • static image
  • generic gradient background
  • empty whitespace
  • generic SaaS hero template

The default hero must be an intentional visual experience.

REQUIRED:

  1. A product-specific visual concept.
  2. Meaningful imagery, product render, illustration, video, diagram, environmental scene, or other rich media.
  3. Purposeful motion or interaction.
  4. Strong visual depth/layering where appropriate.
  5. Responsive behavior that preserves the concept on mobile.

PREFERRED:

  • animated image layers
  • parallax depth
  • cursor/reactive visuals
  • scroll-linked transformation
  • video or frame sequencing
  • interactive product visualization
  • layered typography/media choreography
  • animated diagrams
  • Rive/Lottie interactive visual objects where they add meaning

The hero should communicate the product before the user reads every word.

Do not add animation merely to satisfy this rule. Motion must reinforce hierarchy, product meaning, spatial depth, interaction, or storytelling.


The Feature Communication Decision Flow

text
Feature / Capability to Communicate
      │
      ▼
Can this be communicated better with imagery/diagrams/media?
      │
      ├─────► [YES] ──► Use Product Image / Custom Illustration / Architecture Diagram
      │
     [NO]
      │
      ▼
Does an interactive visual object improve it?
      │
      ├─────► [YES] ──► Use Stateful Rive Object / Lottie Motion Sequence
      │
     [NO]
      │
      ▼
Is a utility icon actually required for immediate operational recognition?
      │
      ├─────► [YES] ──► Use Minimal, Semantic Utility Icon (NO background color/box)
      │
     [NO]
      │
      ▼
Use Strong Typography & Layout Composition Instead (NO pill badges)

The Icon Policy

Permitted Uses of Icons (Utility Only):

  • Navigation & headers (menu, back, home)
  • Search inputs & filter triggers
  • Dialog dismiss / close buttons
  • Settings & system toggles
  • Media playback controls (play, pause, volume)
  • Directional indicators / arrows / pagination
  • Accessibility controls
  • Small utility actions (copy code, download, external link)
  • Semantic status indicators (verified checkmark, error dot)

Prohibited Uses of Icons:

  • ❌ Background Color Behind Icons: Never add background color behind icons. Do not place icons inside colored boxes, tinted squares, rounded circles, or glass tiles (e.g., <div class="bg-primary/10 rounded-xl p-3"><Icon /></div>). Icons must rest directly on the surface.
  • ❌ Pills & Pill Badges: Never wrap icons or text in rounded-full pill badges, floating pill chips, or pill containers.
  • ❌ Feature Storytelling: Do not build generic [Icon] + Title + Description grids repeated 3–6 times as the main feature section. Use images and diagrams instead.
  • ❌ Hero Visuals: Do not place a large floating icon where a product screenshot, diagram, or illustration belongs.
  • ❌ Product Differentiation: Do not use generic icons to explain complex architectural advantages.
  • ❌ Empty Card Filler: Do not slap an icon into a card just because there is empty space.
  • ❌ Replacing Real Visual Media: If a photograph, interactive model, data visualization, or technical diagram is more expressive, you MUST use the richer media.
  • ❌ Emoji Substitutions: Never substitute emojis for semantic icons.

Media-First Planning Framework

Before implementing any substantial visual section, determine the Media Plan:

1. Media Type

  • Photograph: High-fidelity editorial, lifestyle, hardware, or contextual imagery.
  • Product Screenshot / Live UI: Actual application interface, code terminal, or viewport render.
  • Illustration: Purposeful editorial art, technical drawing, or narrative concept.
  • Generated Artwork: Thematic visual generated via AI image tools.
  • Technical Diagram: Interactive architecture map, pipeline flow, or network topology.
  • Animation / Lottie / Rive: Stateful interactive vector motion or micro-narrative.
  • Video / Media Stream: Scrubbed video walkthrough, product reveal, or hardware detail.
  • 2D/3D Canvas: Interactive physics canvas, shader backdrop, or spatial model.

2. Media Role

  • HERO: Anchor visual establishing immediate product identity.
  • BACKGROUND: Subtle atmospheric texture, depth gradient, or ambient video loop.
  • FOCAL VISUAL: Primary focal point of a section (e.g. interactive terminal, diagram).
  • NARRATIVE VISUAL: Step-by-step imagery illustrating a user journey or transformation.
  • SUPPORTING VISUAL: Secondary context accompanying a specific feature statement.
  • COMPARISON: Before / After, side-by-side diff, or benchmark contrast.
  • PROOF: Social proof showcase, customer integration badge, certification mark.
  • INTERACTION SURFACE: Directly clickable, pannable, or scrubbable visual component.

3. Media Scale

  • Full Bleed: Edge-to-edge spanning $100\text{vw}$ for maximum immersive impact.
  • Large Editorial: Spanning 8–10 columns of a 12-column grid ($>65%$ container width).
  • Medium / Balanced: 50/50 split container or asymmetric primary tile.
  • Supporting: Compact inset within an asymmetric bento cell or disclosure panel.

4. Media Treatment

  • Clean Framed: Elevated container with subtle $1\text{px}$ border and ambient drop shadow.
  • Masked / Silhouette: Object isolated from background or masked via geometric clip-path.
  • Layered / Overlapped: Visual elements breaking container boundaries to create z-axis depth.
  • Split Bleed: Image pinned to one viewport edge while content is contained.
  • Window Frame: macOS / browser window header styling for developer & product tools.

Media Performance & Optimization

Every media asset must include performance hygiene:

  1. Responsive Sizing: Use <picture> with srcset or Next.js <Image> for device-scaled resolution.
  2. Explicit Dimensions: Always specify width and height or aspect-ratio to prevent Cumulative Layout Shift (CLS).
  3. Lazy Loading: Native loading="lazy" on all images below the initial viewport fold.
  4. Decoding: Set decoding="async" on non-critical images.
  5. Video Efficiency: Use modern codecs (AV1 / VP9 / H.265), muted autoplay with playsinline, and explicit poster images.

Frequently asked questions

What does the Ui Media Composition AI skill do?

Media-first composition system prioritizing images, video, illustrations, and diagrams over generic icon grids.

Why use Ui Media Composition on TypingMind?

Because you install it once and use it with any model. Ui Media Composition 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 Media Composition 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-media-composition. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ui Media Composition?

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 Media Composition?

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

Is the Ui Media Composition 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 👇