Taste Landing Page logo

Taste Landing Page

Community
madebymustafa
taste-landing-page

Landing page structure and conversion craft: the 8-second rule, audience-driven hero patterns, section order that sells (hook → problem → proof → price → close), CTA discipline, social proof placement, pricing psychology, and mobile-first section behavior. Use when generating or restructuring any marketing page. Stack on the design-taste core skill.

Overview

Publishermadebymustafa
Repositorydesign-taste
Skill nametaste-landing-page
Stars
198
Forks
10
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 madebymustafa on GitHub. Read the source before you install it.

Installation

Install the Taste Landing Page 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/madebymustafa/design-taste/tree/main/skills/taste-landing-page
  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/madebymustafa/design-taste.git /tmp/design-taste
mkdir -p .claude/skills
cp -r /tmp/design-taste/skills/taste-landing-page .claude/skills/taste-landing-page
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Taste Landing Page 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 Taste Landing Page 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 Taste Landing Page 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.

taste-landing-page

A landing page has one job: move the reader from curiosity to a decision. Structure is the copy; this skill is the structure.

1. THE 8-SECOND READ (Design the Top Third First)

In 8 seconds a visitor must answer three questions — without scrolling:

  1. What is this? — the H1 names the product/outcome, not the category ("Analytics that don't need a data team" > "Enterprise analytics platform").
  2. Who is it for? — the subline names the audience ("For indie founders and one-person SaaS").
  3. What do I do? — exactly one primary CTA, visible, contrasting, above the fold.

If the top third doesn't answer all three, the rest of the page is a discount.

2. SECTION ORDER (The Selling Sequence)

  1. Hero — promise + primary CTA (+ the product if it's visual evidence).
  2. Proof strip — logos, user count, or press. Trust before claims.
  3. The problem — one pain, named in the reader's words (not "modern teams need…"). Keep to 3 lines.
  4. The mechanism — 3 features max, each one sentence + one proof point. More than 3 features on a landing page = a spec sheet, not a pitch.
  5. The proof — metric callouts with numbers, customer quote with a name + title, or both. Claims without proof here die here.
  6. How it works — 3 steps only (for products that need explaining).
  7. Pricing — 3 tiers max; highlight the middle. Never 4+ tiers on a landing page.
  8. The close — one line of residual doubt ("No credit card. Set up in 4 minutes.") + the CTA again + a human touch ("Talk to a human →").

Every section earns its place by answering the objection a reader has at that moment. If a section doesn't answer a question, it's decoration.

3. HERO PATTERNS (Pick One, Per Audience)

AudiencePatternExample H1 shape
Developer toolProblem → mechanism"Type less. Ship more." + terminal/product panel
B2B buyerOutcome + qualification"Cut support tickets 40% with self-serve onboarding"
ConsumerDesire + friction-removal"Your photos, organized while you sleep"
EnterpriseCategory + evidence"Identity security for regulated industries" + compliance chips
Solo/passionIdentity + invitation"Build the portfolio that gets you hired"

Never combine two patterns (outcome AND identity in one H1 reads as confused). Never let the hero show a product screenshot before the promise is understood.

4. CTA DISCIPLINE

  • One primary CTA per viewport. Secondary actions are text links or quiet buttons; two equal buttons = no button.
  • The primary CTA label says the outcome or the action: "Start free trial" > "Get started" > "Submit". First-person labels ("Start my free trial") lift clicks on consumer pages.
  • The CTA color is the accent — and the accent appears nowhere else within that viewport.
  • The final CTA is the same label as the hero CTA. Never rename it mid-page.
  • Form CTAs: minimize fields (email + password for trials; company name only when the offer is enterprise).

5. PROOF & TRUST PLACEMENT

  • Logos: grayscale, before features; ≤ 6 logos (more reads as fake).
  • Metric callouts: number + what it measures + source line. "18.4% trial→paid" means nothing; "18.4% trial→paid among 4,120 teams" means something.
  • Quotes: attribution with name, title, company — never "John D. from California".
  • Compliance chips (SOC 2, GDPR, ISO 27001) sit beside pricing and the form, where decisions happen — not buried in the footer.
  • One guarantee where risk is highest: near the form ("14-day free trial. Cancel in two clicks.").

6. PRICING PSYCHOLOGY (Three Tiers, Anchored)

  • Three tiers: entry (free or cheap), featured (most popular — visually distinct, one accent), top (premium or "contact us").
  • The featured tier is the anchor: it's what comparison happens against; make it visually distinct but not aggressive.
  • List the most valuable line item first in each tier. Convert $29/month to "≈ $1/day" for consumer audiences; annual billing with "2 months free" for B2B.
  • Never display three price columns of equal visual weight — the eye must land on one.

7. MOBILE BEHAVIOR (The Second Page)

  • Same section order on mobile; hero subline and proof strip reorder first (proof before features on small screens).
  • CTAs: full-width, ≥ 48px tall, thumb-reachable at both ends of the scroll.
  • Tables become stacked cards or horizontal scroll with a hint; pricing tiers stack with the featured tier FIRST on mobile.

8. CHECKLIST (Fail the Page If…)

  • The top third doesn't answer what/who/do within 8 seconds.
  • More than one primary CTA per viewport.
  • Features listed without proof nearby.
  • Any claim without a source line on the same viewport.
  • Pricing with equal-weight columns or 4+ tiers.
  • A section that answers no objection.
  • Hero CTA label different from the final CTA label.

Frequently asked questions

What does the Taste Landing Page AI skill do?

Landing page structure and conversion craft: the 8-second rule, audience-driven hero patterns, section order that sells (hook → problem → proof → price → close), CTA discipline, social proof placement, pricing psychology, and mobile-first section behavior. Use when generating or restructuring any marketing page. Stack on the design-taste core skill.

Why use Taste Landing Page on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/madebymustafa/design-taste/tree/main/skills/taste-landing-page. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Taste Landing Page?

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 Taste Landing Page?

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

Is the Taste Landing Page AI skill free?

Yes. It is published on GitHub by madebymustafa 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 👇