TypingMindTypingMindThe best frontend for AI
Ui Preflight logo

Ui Preflight

Community
thakur698
ui-preflight

The final, binary mechanical gate that prevents broken or fundamentally flawed designs from being delivered.

Overview

Publisherthakur698
Repositoryuniversal-ui-skills
Skill nameui-preflight
Stars
5
Forks
0
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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 Preflight 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-preflight
  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-preflight .claude/skills/ui-preflight
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ui Preflight 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 Preflight 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 Preflight 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 Pre-Flight Gates

Mission

While the Visual Critic scores aesthetics, the Pre-Flight Gate enforces hard mechanical rules. A design that fails ANY pre-flight gate is NOT DONE.

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.

Hard Pre-Flight Matrix

Evaluate the design against these binary (PASS/FAIL) rules:

Layout & Composition Gates:

  • FAIL: CTA wraps on desktop. (Primary action buttons must fit on a single line).
  • FAIL: Same composition repeated too many times. (Violates the Variance Rule).
  • FAIL: Generic card grid used without reason. (Bento/Grids must have distinct purpose and hierarchy).
  • FAIL: Bento is merely repeated cards. (Bento layouts must feature asymmetric spans and visual anchors).
  • FAIL: PILL_CONTAINER_OR_BADGE. (Created pill badges, tags, chips, floating pill eyebrows, or rounded-full pill containers).
  • FAIL: ICON_BACKGROUND_CONTAINER. (Added background color, tinted box, circle backdrop, or container tile behind an icon).
  • FAIL: ICON_SUBSTITUTION / INSUFFICIENT_IMAGE_PRIORITY. (Relied on icons instead of prioritizing rich images, real photography, product renders, illustrations, or diagrams for content communication).
  • FAIL: Static icon used where animated/interactive visual belongs. (Static glyph used when a Lottie/Rive or canvas interaction would materially clarify the feature).
  • FAIL: Same eyebrow pattern repeated. (e.g., "FEATURES", "BENEFITS" in small colored caps above every H2).
  • FAIL: GHOST_CARD_ELEVATION. (Competing border and wide soft shadow on the same element).
  • FAIL: ZERO_OFFSET_GLOW_HALO. (Glow halo masquerading as depth; shadows must have a y-offset).
  • FAIL: SIDE_STRIPE_BORDER. (Colored left/right edge stripe on cards or callouts).
  • FAIL: UNBALANCED_OR_OVERFLOW_MEASURE. (Body line measure > 75ch, or missing text-wrap: balance on multi-line headlines).

Scroll & Motion Gates:

  • FAIL: Scroll animation exists without purpose. (Animation must communicate hierarchy, state, or storytelling).
  • FAIL: Parallax makes text hard to read. (Text displacement must never compromise legibility).
  • FAIL: Sticky section traps user interaction. (Sticky/pinned sections must release smoothly without scroll trapping).
  • FAIL: Video is required to understand core content but cannot load. (Must provide static image/text fallback).
  • FAIL: Motion ignores reduced-motion behavior. (Must strictly honor prefers-reduced-motion).
  • FAIL: Scroll effects cause visible jank. (Must use GPU-accelerated transforms and throttled listeners).
  • FAIL: Visual hierarchy depends entirely on animation. (Content must remain fully comprehensible when static).
  • FAIL: IMAGE_HOVER_ANIMATION. (Animating an image directly on hover; feedback belongs on the container).

Accessibility & Platform Gates:

  • FAIL: No mobile fallback / Broken pinned layout. (Mobile viewports must not horizontally scroll or trap pins).
  • FAIL: Insufficient contrast. (Text contrast below $4.5:1$ on body copy).
  • FAIL: Placeholder imagery. (Fake/generic placeholder boxes left in final render).
  • FAIL: Broken loading/error/empty state. (Edge cases not handled).
  • FAIL: BROWSER_SURFACES_UNTINTED. (Default browser selection, blue focus ring, or unthemed scrollbars on themed UI).
  • FAIL: MOBILE_INPUT_ZOOM_RISK. (Form inputs with font-size < 16px on mobile viewports).

Hero Gates:

  • FAIL: HERO_STATIC_TEMPLATE. (Website hero is substantially composed of headline + paragraph + primary CTA + secondary CTA + static decorative/background image with no meaningful visual interaction, motion, transformation, or product-specific visual storytelling. Exception: Documented reason related to brief, product, accessibility, performance, or platform constraints.)
  • PASS: HERO_VISUAL_STORY. (The hero has a distinct visual concept, meaningful media, purposeful motion/interaction, clear hierarchy, product-specific storytelling, coherent reduced-motion fallback, and mobile translation.)

Execution

  • The agent MUST explicitly print the Pre-Flight Matrix check in its final report.
  • If ANY item is marked FAIL, the agent must halt, fix the issue, and re-run the Pre-Flight check.

Frequently asked questions

What does the Ui Preflight AI skill do?

The final, binary mechanical gate that prevents broken or fundamentally flawed designs from being delivered.

Why use Ui Preflight on TypingMind?

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

Which AI models can use Ui Preflight?

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 Preflight?

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

Is the Ui Preflight 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.

Related AI Skills

View all
affaan-m logo

Api Design

affaan-m
CommunityPopular

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

39.1K
261.1K
Instructions
View
affaan-m logo

Accessibility

affaan-m
CommunityPopular

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

39.1K
261.1K
Instructions
View
NousResearch logo

Archify

NousResearch
OrganizationPopular

Validated interactive HTML diagrams, upstream-maintained.

53.5K
250.4K
Instructions
View
NousResearch logo

Auteur

NousResearch
OrganizationPopular

Design and build cinematic, award-level web pages.

53.5K
250.4K
25 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇