Landing Page Generator logo

Landing Page Generator

CommunityPopular
FlorianBruniaux
landing-page-generator

Generate complete, deploy-ready landing pages from any repository. Use when creating a homepage for an open-source project, building a project website, converting a README into a marketing page, or standardizing landing pages across multiple repos.

Overview

PublisherFlorianBruniaux
Repositoryclaude-code-ultimate-guide
Skill namelanding-page-generator
Stars
6K
Forks
782
Bundled files
12
LicenseCC-BY-SA-4.0
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.

  • 12 bundled files

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

  • Open source

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

Installation

Install the Landing Page Generator 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.
  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/FlorianBruniaux/claude-code-ultimate-guide.git /tmp/claude-code-ultimate-guide
mkdir -p .claude/skills
cp -r /tmp/claude-code-ultimate-guide/examples/skills/landing-page-generator .claude/skills/landing-page-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Landing Page Generator 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 Landing Page Generator 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 Landing Page Generator 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.

Landing Page Generator

Generate a complete, deploy-ready landing page from any repository by analyzing its documentation and structure.

When to Use This Skill

  • Creating a landing page for a GitHub repository
  • Generating static sites from existing documentation
  • Standardizing landing pages across multiple projects
  • Converting README content to marketing/showcase pages

What This Skill Does

  1. Analyze Repository: Read README.md, CHANGELOG.md, package.json/VERSION, docs/, assets/
  2. Extract Content: Identify title, tagline, features, installation, screenshots
  3. Map to Sections: Hero, Features, Install, FAQ, Footer (+ optional: Risk Banner, Pricing)
  4. Generate Landing: Create complete static site (HTML + CSS + JS)
  5. Deploy-Ready Output: Include GitHub Actions workflow for GitHub Pages

How to Use

Basic Usage

/landing-page-generator from ~/path/to/repo

With Options

/landing-page-generator from ~/path/to/repo --risk-banner --pricing-table

Available Options

OptionDescriptionDefault
--risk-bannerAdd prominent warning/disclaimer banner above foldfalse
--pricing-tableInclude pricing comparison sectionfalse
--screenshots <path>Path to screenshots folder./assets/
--theme [dark|light]Color theme variantdark
--searchEnable Cmd+K searchtrue
--output <path>Output directory./[repo-name]-landing/

Workflow

Step 1: Repository Analysis

Read and analyze these files from the source repo:

README.md        → Primary content source (title, tagline, features, install)
CHANGELOG.md     → Version info, recent changes
package.json     → Version number, dependencies, metadata
VERSION          → Alternative version source
docs/            → Additional documentation pages
assets/          → Screenshots, images
LICENSE          → License type for badge

Step 2: Content Extraction Map

SourceTarget SectionExtraction Method
README title/badgesHeroFirst H1 + shield.io badge lines
README TL;DRHero taglineFirst paragraph or blockquote after title
README featuresFeatures gridH2/H3 sections with bullet lists
README installQuick StartCode blocks with shell commands
README usageExamplesCode blocks with examples
README FAQFAQDetails/summary or H3+P patterns
CHANGELOGWhat's NewLatest 1-3 releases
assets/*.pngScreenshotsGallery section

Step 3: Section Generation

Generate these sections in order:

  1. Header (sticky)

    • Logo/project name
    • Nav links: Features, Install, FAQ
    • Actions: Search (Cmd+K), GitHub Star, primary CTA
  2. Risk Banner (if --risk-banner)

    • Orange/warning style above fold
    • Clear, visible disclaimer text
    • Link to detailed disclosure section
  3. Hero Section

    • Title from README H1
    • Tagline from TL;DR/first paragraph
    • Stats badges (version, license, platform)
    • CTAs: "Quick Start" (primary), "View on GitHub" (secondary)
  4. Architecture/Overview (if diagram in README)

    • ASCII diagram converted to styled block
    • Or overview cards
  5. Features Grid

    • 4-6 feature cards from README features
    • Icon + title + description pattern
  6. Pricing Table (if --pricing-table)

    • Plans comparison table
    • Multipliers/usage table if present
  7. Screenshots Gallery (if assets exist)

    • Tab-based or carousel gallery
    • Captions from alt text
  8. Quick Start Section

    • One-liner install command (featured code block)
    • Setup steps
    • First usage example
  9. Risk Disclosure (if --risk-banner)

    • Full disclaimer section
    • ToS considerations
    • Recommendations
  10. FAQ Section

    • Generated from README FAQ or common questions
    • Collapsible details pattern
  11. Related Projects (if links in README)

    • Cards linking to dependencies/related repos
  12. Footer

    • Quick links
    • License badge
    • Version info
    • Author/repo links

Step 4: Output Structure

[project-name]-landing/
├── index.html              # Main landing page
├── styles.css              # Complete stylesheet
├── search.js               # Cmd+K search functionality
├── search-data.js          # Search index (FAQ, features)
├── favicon.svg             # Generated or copied
├── robots.txt              # SEO
├── CLAUDE.md               # Project instructions
├── README.md               # Landing repo documentation
├── assets/                 # Copied screenshots
│   └── [copied from source]
└── .github/
    └── workflows/
        └── static.yml      # GitHub Pages deployment

Step 5: Validation Checkpoint

Before finalizing, verify:

  • All sections render correctly in a browser
  • Links point to valid targets (GitHub repo, docs, install commands)
  • Responsive layout works at mobile (375px), tablet (768px), and desktop (1280px) widths
  • Accessibility: skip links present, ARIA labels on interactive elements, color contrast passes WCAG AA

Tech Stack

  • No build step: Pure HTML + CSS + JS
  • Search: MiniSearch lazy-loaded from CDN with fallback
  • Deployment: GitHub Pages via Actions
  • Styling: CSS custom properties, responsive, dark theme default
  • Accessibility: Skip links, ARIA labels, keyboard navigation

CSS Patterns (from established landings)

Component Classes

css
/* Buttons */
.btn, .btn-primary, .btn-secondary, .btn-github-star, .btn-outline

/* Cards */
.feature-card, .comparison-card, .path-card

/* Layout */
.container, .features-grid, .hero, .section

/* Utilities */
.visually-hidden, .skip-link

CSS Variables

css
:root {
  --color-bg: #0d1117;
  --color-surface: #161b22;
  --color-border: #30363d;
  --color-text: #c9d1d9;
  --color-text-muted: #8b949e;
  --color-primary: #58a6ff;
  --color-success: #3fb950;
  --color-warning: #d29922;
  --color-danger: #f85149;
  --space-xs: 0.25rem;
  --space-sm: 0.5rem;
  --space-md: 1rem;
  --space-lg: 1.5rem;
  --space-xl: 2rem;
  --radius: 6px;
}

Example

User: /landing-page-generator from ~/projects/my-project --risk-banner --pricing-table

Output:

Creates ~/projects/my-project-landing/ with:

  • Complete landing page showcasing the multi-provider router
  • Prominent ToS risk banner (orange, above fold)
  • Provider cards (Anthropic, Copilot, Ollama)
  • Pricing tables from README
  • Screenshots gallery
  • GitHub Pages deployment ready

Tips

  • Always include --risk-banner for projects with legal/ToS considerations
  • Screenshots significantly improve landing quality - ensure assets/ is populated
  • The skill preserves README language (English/French)
  • Review generated FAQ - may need customization
  • Test responsive design after generation

References

See references/landing-pattern.md for detailed pattern documentation. See assets/ for reusable templates and snippets.

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 Landing Page Generator AI skill do?

Generate complete, deploy-ready landing pages from any repository. Use when creating a homepage for an open-source project, building a project website, converting a README into a marketing page, or standardizing landing pages across multiple repos.

Why use Landing Page Generator on TypingMind?

Because you install it once and use it with any model. Landing Page Generator 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 Landing Page Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples/skills/landing-page-generator. 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 Landing Page Generator?

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 Landing Page Generator?

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

Is the Landing Page Generator AI skill free?

Yes. It is published on GitHub by FlorianBruniaux under the CC-BY-SA-4.0 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 👇