Hero Generator logo

Hero Generator

Community
kostja94
hero-generator

When the user wants to design, optimize, or audit hero sections (above-the-fold main visual area). Also use when the user mentions "hero," "hero section," "hero area," "above the fold," "above the fold content," "landing hero," "main banner," "banner section," "first fold," "hero section design," "hero conversion," "split layout hero," "centered hero," or "hero alignment." For homepage, use homepage-generator.

Overview

Publisherkostja94
Repositorymarketing-skills
Skill namehero-generator
Stars
979
Forks
137
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 kostja94 on GitHub. Read the source before you install it.

Installation

Install the Hero 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/kostja94/marketing-skills.git /tmp/marketing-skills
mkdir -p .claude/skills
cp -r /tmp/marketing-skills/skills/components/branding/hero .claude/skills/hero-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hero 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 Hero 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 Hero 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.

Components: Hero Section

Guides hero section design for conversion and first impressions. The hero is where users spend ~80% of initial viewing time; first impressions form in milliseconds.

When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Initial Assessment

Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for value proposition, audience, and Section 12 (Visual Identity).

Identify:

  1. Page type: Homepage, landing, product, pricing
  2. Primary goal: Signup, trial, purchase, learn more
  3. Platform: Web, mobile, both

Core Components (Four Essentials)

  • Headline (H1): 6–10 words max; instantly communicate core value and benefit. Answer "What's in it for me?" within seconds.
  • Subheading: Clear, concise explanation reinforcing why the product/service is valuable.
  • Primary CTA: Single, prominent action button visible without scrolling. One per hero to avoid choice overload.
  • Visual: High-quality image, video, or animation that amplifies the message.

Optional but Effective

  • Trust cues: 1–3 elements (reviews, logos, statistics)
  • Secondary CTA: For users not ready for primary action

Layout Types

Hero is a Spotlight layout—single focus, primary element with secondary around it. Choose layout by content balance and conversion goal.

LayoutStructureBest for
Split (50/50)Text left, visual right (or vice versa); equal weightProduct, SaaS; clear value + demo
Split (75/25)Text dominant; smaller image columnCopy-heavy; trust-first
Split (25/75 "Signpost")Small image beside primary contentMinimal visual; emphasis on headline
CenteredText + CTA centered; visual full-width or stackedBrand, landing; single CTA
Full-width imageImage background; overlay textEmotional; lifestyle, brand

Responsive: Split layouts stack vertically on mobile (text above image); centered maintains center. Mobile-first; ensure CTA above fold on small screens.

Alignment

AxisOptionsUse
HorizontalLeft, center, rightLeft align for text-heavy; center for minimal
VerticalTop, center, bottomCenter for full-viewport hero; top for short hero

Best Practices

3-Second Rule

The hero must answer three questions within 3 seconds: What is this? Why should I care? What should I do next? ~80% of users never scroll beyond the hero; make an immediate impact.

Messaging

  • No guessing required; message must be instantly clear.
  • Single primary CTA to avoid choice overload.
  • Action-oriented, benefit-focused copy.
  • Emotional intent first: Evoke emotion (trust, excitement, confidence) before users read the headline. Avoid generic phrases ("Welcome to Our Website") or overly clever wordplay.

Visuals

  • Fast-loading; avoid heavy assets that delay LCP
  • Brand-aligned; use typography and colors from brand-visual-generator
  • Support the message; don't distract
  • Frontend aesthetics: For motion (staggered reveals, hover), spatial composition, and backgrounds—see brand-visual-generator Frontend Aesthetics

Technical

  • Mobile-first design
  • Lightweight for quick loading
  • Ensure LCP (Largest Contentful Paint) optimization

SEO Considerations

  • Headline often contains <h1>; include primary keyword
  • Hero content in initial HTML; avoid JS-only rendering. See rendering-strategies
  • Image optimization: Alt text, format (WebP), LCP, responsive—see image-optimization

UX Guidelines

Hierarchy

  • Headline > Subheading > CTA
  • Visual should complement, not compete with, text

Accessibility

RequirementPractice
ContrastText over images: >=4.5:1; use overlay if needed
Touch targetsCTA >=44x44px
KeyboardCTA keyboard-accessible; visible focus indicator
Screen readersProper heading order; image alt text; aria-label for icon-only buttons
Reduced motionRespect prefers-reduced-motion for animations
InteractionCTA has cursor-pointer; hover uses color/opacity (not scale) to avoid layout shift

Testing

  • A/B test headline, CTA copy, and visuals
  • Measure bounce rate, conversion rate, time to first interaction

Output Format

  • Hero structure (headline, subheading, CTA, visual)
  • Copy suggestions
  • Technical checklist (LCP, accessibility, image optimization)
  • Testing recommendations

Related Skills

  • card: Hero vs card—hero is single above-fold; cards are repeated units in grid
  • grid: Hero is one section; content below often uses grid (products, features)
  • cta-generator: Hero typically contains primary CTA
  • trust-badges-generator: Trust cues in hero
  • logo-generator: Logo appears in hero context
  • brand-visual-generator: Typography, colors, spacing for hero design
  • homepage-generator: Hero is central to homepage design
  • landing-page-generator: Hero is step 1 of landing page flow; campaign pages
  • image-optimization: Hero image optimization (alt, WebP, LCP, responsive)
  • rendering-strategies: Content in initial HTML; SSR/SSG for hero

Frequently asked questions

What does the Hero Generator AI skill do?

When the user wants to design, optimize, or audit hero sections (above-the-fold main visual area). Also use when the user mentions "hero," "hero section," "hero area," "above the fold," "above the fold content," "landing hero," "main banner," "banner section," "first fold," "hero section design," "hero conversion," "split layout hero," "centered hero," or "hero alignment." For homepage, use homepage-generator.

Why use Hero Generator on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kostja94/marketing-skills/tree/main/skills/components/branding/hero. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Hero 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 Hero Generator?

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

Is the Hero Generator AI skill free?

Yes. It is published on GitHub by kostja94 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 👇