Layout Block Intelligence logo

Layout Block Intelligence

Community
phazurlabs
layout-block-intelligence

500+ individual section patterns — heroes, feature grids, pricing tables, testimonials, CTAs, footers, FAQs, stats, timelines — each with specs, spacing, and code. Use when choosing or building one section. For ordering sections into a whole page, use page-composition-engine.

Overview

Publisherphazurlabs
Repositorysumi
Skill namelayout-block-intelligence
Stars
58
Forks
11
Bundled files
6
LicenseApache-2.0
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.

  • 6 bundled files

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

  • Open source

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

Installation

Install the Layout Block Intelligence 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/phazurlabs/sumi/tree/main/skills/layout-block-intelligence
  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/phazurlabs/sumi.git /tmp/sumi
mkdir -p .claude/skills
cp -r /tmp/sumi/skills/layout-block-intelligence .claude/skills/layout-block-intelligence
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Layout Block Intelligence 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 Layout Block Intelligence 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 Layout Block Intelligence 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.

Layout Block Intelligence — 500+ Production Section Patterns

Mental model

A page is a sequence of blocks, and each block has exactly one job. When a page feels wrong it is usually not the styling — it is two blocks doing the same job, or a block doing none.

  • One block, one argument. A hero makes a claim. Social proof supports it. A feature grid explains it. Pricing converts it. If you cannot name a block's argument, delete it.
  • Alternate density. Dense, then open, then dense. Uniform density reads as a wall regardless of how good the individual blocks are.
  • Every block needs a mobile form, and it is rarely "the same but narrower". A four-column feature grid becomes a two-by-two, not a four-high stack.
  • Spacing carries the grouping. Space between blocks must exceed space within them, or the eye cannot find the seams.

For ordering blocks into a whole page, that is page-composition-engine. This skill is the blocks themselves.

Index

BlockVariantsReference
Herocentered, split, full-bleed, video, gradienthero-section-patterns.md
Feature grid3-col, 4-col, alternating, icon-ledcontent-section-patterns.md
Content sectionprose, media-left, media-right, stat rowcontent-section-patterns.md
CTA bannersimple, email capture, split, full-bleedcta-pricing-patterns.md
Pricing table2-tier, 3-tier, comparison matrix, togglecta-pricing-patterns.md
Testimonialscard grid, carousel, single quote, videosocial-proof-patterns.md
Logo wall, ratings, review display—social-proof-patterns.md
Top nav as a page blockstandard, mega, transparent-over-heronavigation-footer-patterns.md
Footerminimal, sitemap, newsletter, meganavigation-footer-patterns.md
KPI card row, data widgets, chart cards—dashboard-data-patterns.md

Reference architecture

FileCoversLines
references/hero-section-patterns.mdhero anatomy, breakpoints, variants926
references/content-section-patterns.mdfeature and content blocks810
references/navigation-footer-patterns.mdnav and footer blocks638
references/cta-pricing-patterns.mdconversion blocks635
references/social-proof-patterns.mdtestimonials, logos, ratings616
references/dashboard-data-patterns.mddashboard blocks571

What every reference file contains

  1. The block's job in one sentence
  2. Universal anatomy — the parts every variant shares
  3. Breakpoint specifications, not just a mobile note
  4. Each variant with the condition that selects it
  5. Production HTML/CSS or TSX
  6. The anti-pattern that variant invites

Routing

For heroes — anatomy, breakpoint specs, and variants from centered and split to full-bleed: read references/hero-section-patterns.md.

For content sections — universal block specs plus the 3-column, 4-column and alternating feature-grid variants: read references/content-section-patterns.md.

For conversion blocks — CTA banners, email-capture CTAs, and pricing tables with the psychology behind each: read references/cta-pricing-patterns.md.

For social proof — testimonial grids and carousels, logo walls, and review displays: read references/social-proof-patterns.md.

For navigation and footers as page blocks — standard top nav, mega menu, transparent-over-hero, and footer variants: read references/navigation-footer-patterns.md.

For dashboard blocks — layout patterns, the dashboard spacing system, KPI card rows and data-widget variants: read references/dashboard-data-patterns.md.

Cross-References

  • component-patterns-code — Individual component implementation (buttons, inputs, modals, cards)
  • screen-flow-patterns — Full page types and navigation flows between pages
  • ui-pattern-intelligence — 200+ UI interaction patterns with benchmarks
  • visual-design-mastery — Color, typography, and composition scoring
  • platform-visual-standards — Platform-specific adaptations (iOS 26, Material 3, CSS)
  • performance-states-patterns — Loading, error, skeleton states for every block
  • accessibility-inclusive-design — WCAG requirements per block type
  • sector-style-intelligence — Industry-specific block styling and sequencing
  • interaction-motion-design — Animation and transition patterns for blocks
  • page-composition-engine — How to stack blocks into complete pages
  • responsive-block-patterns — Detailed breakpoint transformations for every block
  • conversion-optimization-patterns — Which blocks convert best and where to place them

Production Code Patterns

Section Wrapper (React/TSX + Tailwind)

tsx
interface SectionProps {
  children: React.ReactNode;
  background?: 'white' | 'gray' | 'dark' | 'brand' | 'gradient';
  padding?: 'sm' | 'md' | 'lg' | 'xl';
  maxWidth?: 'narrow' | 'standard' | 'wide' | 'full';
  id?: string;
}

const paddingMap = { sm: 'py-8 md:py-12 lg:py-16', md: 'py-12 md:py-16 lg:py-20', lg: 'py-16 md:py-20 lg:py-24', xl: 'py-20 md:py-28 lg:py-32' };
const maxWidthMap = { narrow: 'max-w-3xl', standard: 'max-w-6xl', wide: 'max-w-7xl', full: 'max-w-full' };
const bgMap = { white: 'bg-white text-gray-900', gray: 'bg-gray-50 text-gray-900', dark: 'bg-gray-900 text-white', brand: 'bg-blue-600 text-white', gradient: 'bg-gradient-to-br from-blue-600 to-purple-700 text-white' };

export function Section({ children, background = 'white', padding = 'lg', maxWidth = 'standard', id }: SectionProps) {
  return (
    <section id={id} className={bgMap[background]}>
      <div className={`mx-auto px-4 sm:px-6 lg:px-8 ${maxWidthMap[maxWidth]} ${paddingMap[padding]}`}>{children}</div>
    </section>
  );
}

Section Header

tsx
export function SectionHeader({ label, title, description, align = 'center' }: { label?: string; title: string; description?: string; align?: 'left' | 'center' }) {
  const cls = align === 'center' ? 'text-center mx-auto' : 'text-left';
  return (
    <div className={`max-w-2xl mb-12 lg:mb-16 ${cls}`}>
      {label && <p className="text-sm font-semibold uppercase tracking-wider text-blue-600 mb-3">{label}</p>}
      <h2 className="text-3xl sm:text-4xl lg:text-5xl font-bold tracking-tight">{title}</h2>
      {description && <p className="mt-4 text-lg text-gray-600 leading-relaxed">{description}</p>}
    </div>
  );
}

CSS Custom Properties

css
:root {
  --section-py: clamp(3rem, 8vw, 7.5rem);
  --section-px: clamp(1rem, 5vw, 5rem);
  --section-max-width: 72rem;
  --section-title-size: clamp(1.875rem, 4vw, 3rem);
  --section-header-gap: clamp(2rem, 4vw, 4rem);
}
.section { padding: var(--section-py) var(--section-px); }
.section__inner { max-width: var(--section-max-width); margin-inline: auto; }

Block Quality Checklist

  • Content flexibility: handles short AND long content without breaking?
  • Responsive at 5 breakpoints (1440, 1024, 768, 480, 320)?
  • Empty state: what renders with 0 items?
  • Overflow state: what happens with 50+ items?
  • Heading hierarchy: H2 section, H3 items, no skipping?
  • ARIA landmarks: section + aria-labelledby?
  • Keyboard navigation: all elements reachable?
  • Images lazy-loaded below fold?
  • prefers-reduced-motion respected?
  • Consistent spacing, no magic numbers?
  • Type scale followed, no orphaned heading words?
  • Color contrast WCAG AA (4.5:1 text, 3:1 UI)?
  • Visible focus indicators on interactive elements?
  • Skeleton loading state for async content?
  • Print styles render reasonably?
  • RTL language support considered?

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 Layout Block Intelligence AI skill do?

500+ individual section patterns — heroes, feature grids, pricing tables, testimonials, CTAs, footers, FAQs, stats, timelines — each with specs, spacing, and code. Use when choosing or building one section. For ordering sections into a whole page, use page-composition-engine.

Why use Layout Block Intelligence on TypingMind?

Because you install it once and use it with any model. Layout Block Intelligence 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 Layout Block Intelligence in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/phazurlabs/sumi/tree/main/skills/layout-block-intelligence. 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 Layout Block Intelligence?

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 Layout Block Intelligence?

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

Is the Layout Block Intelligence AI skill free?

Yes. It is published on GitHub by phazurlabs under the Apache-2.0 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 👇