Ui Reference First

Community

thakur698

ui-reference-first

Enforces a reference-analysis phase before coding, ensuring design decisions are extracted from concrete examples.

Overview

Publisher	thakur698
Repository	`universal-ui-skills`
Skill name	`ui-reference-first`
Stars	5
Forks	0
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 thakur698 on GitHub. Read the source before you install it.

Installation

Install the Ui Reference First 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/thakur698/universal-ui-skills/tree/main/.agents/plugins/universal-ui/skills/ui-reference-first
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/thakur698/universal-ui-skills/tree/main/.agents/plugins/universal-ui/skills/ui-reference-first

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

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/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-reference-first .claude/skills/ui-reference-first

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

Use it in TypingMind

Enable Ui Reference First 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 Reference First 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 Reference First 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 Reference-First Pipeline

Mission

Do not rely on the LLM's generic baseline aesthetic. Real design relies on moodboards and references. The Reference-First Pipeline ensures that concrete metrics, media strategies, and scroll choreography are extracted from visual references before any code is generated.

The Pipeline

text
USER BRIEF
   ↓
REFERENCE SEARCH / GENERATION
   ↓
REFERENCE BOARD
   ↓
DESIGN & MEDIA ANALYSIS
   ↓
COMPOSITION MAP (with Scroll & Media Intent)
   ↓
IMPLEMENTATION

Execution Steps

Locate or Generate References:
- If the user provides an image or URL, perform visual analysis.
- If the agent supports image generation or web search, generate/find structural references for specific sections (e.g. Hero visual, sticky workflow, bento grid, mobile layout).
Extract Metrics (The Design Analysis): Do not just say "it looks nice". Mechanically extract:
- Grid & Layout Family: (e.g. 12-column, asymmetric 60/40, bento matrix, sticky split)
- Media Strategy: (e.g. Full-bleed editorial photography, interactive terminal, 3D device render, technical node diagram)
- Scroll & Motion Behaviors: (e.g. Pinned viewport stage, parallax background layer, scroll fade, video scrubbing)
- Typography: (e.g. Display sans, tight tracking, monospace technical accents)
- Spacing & Density: (e.g. 8px baseline, expansive 140px section gutters, dense telemetry clusters)
- Shape Language: (e.g. 8px unified radius, sharp borders, glass highlight overlay)
- Color & Contrast: (e.g. Neutral dark base #09090b with single #10b981 emerald accent)
Build Composition Map:
- Translate extracted metrics into the concrete section blueprints (layout families, media roles, scroll triggers).

Example Composition Map Extraction

text
COMPOSITION MAP:
- Hero:
  - Layout: ASYMMETRIC HERO
  - Media: Live interactive terminal + sub-10ms SLA indicator
  - Motion: Staged entrance (terminal scale-in + headline fade-up)
- Proof Strip:
  - Layout: FULL-WIDTH LOGO WALL
  - Media: Monochrome verified SVG brand marks
- Features:
  - Layout: PREMIUM BENTO
  - Media: Anchor tile with global edge telemetry map; 2 technical sub-tiles
  - Scroll: Staggered reveal upon 30% viewport entry
- Story Section:
  - Layout: STICKY STORY (SPLIT-PIN)
  - Media: Pinned cluster architecture visual
  - Scroll: Sticky left column while 3 deployment phases scroll on right

Rules

The agent MUST explicitly state the extracted reference metrics, media plan, and scroll choreography before writing CSS or markup.
Do not blindly copy references: extract the underlying structural, media, and interaction strategy.

Frequently asked questions

What does the Ui Reference First AI skill do?

Enforces a reference-analysis phase before coding, ensuring design decisions are extracted from concrete examples.

Why use Ui Reference First on TypingMind?

Because you install it once and use it with any model. Ui Reference First 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 Reference First 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-reference-first. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ui Reference First?

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 Reference First?

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

Is the Ui Reference First 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

Auteur

NousResearch

OrganizationPopular

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Hyperframes

Render MP4/WebM videos from HTML compositions.

Ip As Logo

Design minimal cute IP mascot marks readable at 32px.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

UI Reference-First Pipeline

Mission

The Pipeline

Execution Steps

Example Composition Map Extraction

Rules

Frequently asked questions

Related AI Skills

Set up your own AI workspace now