agentleFS
teodstrteodstr/garage/skills/landing-page/SKILL.md

landing-page

Skill0 starsChanged 2 days agoMITView on GitHub

Write and build a landing page that tests demand for an offer: one visitor, one promise, real proof, one call to action, an accessible single-file HTML page, and the numbers to read after launch (visitors, sign-ups, conversion by source). Use when a founder wants a landing page, a waitlist, a pre-order page, or to test an idea online. Triggers: "landing page", "waitlist", "pre-order page", "homepage copy", "smoke test", "page d'atterrissage", "page de lancement", "liste d'attente", "page de vente", "página de aterrizaje", "lista de espera", "página de preventa".

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use operational-enterprise-ai, product-proof-saas and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • boraoztuncSkill

    operational-enterprise-ai

    Create or redesign enterprise AI, automation, security, and operations product pages that explain system boundaries, approvals, auditability, exceptions, and rollback. Use for dark cinematic heroes, hairline grids, metric pauses, expandable solution rows, case-study evidence, security proof, and qualified demo or waitlist handoffs.

    Also in 3 projects that use this

  • boraoztuncSkill

    product-proof-saas

    Create or redesign SaaS and AI product landing pages where a real workflow, interface, or deterministic demo is the central proof. Use for pale atmospheric shells, product UI in the hero, prompt-to-output stories, audience tabs, compact feature modules, honest pricing comparisons, and FAQ handoffs.

    Also in 3 projects that use this

  • Dragoon0xSkill

    pricing-page

    Present pricing in ways that reduce friction and increase clarity. Handles tier naming, feature comparison, anchor pricing, and plan selection psychology. Use when designing pricing pages, plan selectors, or upgrade prompts.

    Also in 3 projects that use this

  • Dragoon0xSkill

    onboarding-flow

    Design first-run experiences that create the aha moment fast. Reduces time-to-value by sequencing actions, progressive disclosure, and contextual guidance. Use when building signup flows, product tours, or empty states.

    Also in 3 projects that use this

  • shawnpangSkill

    lead-scoring

    When a founder needs to qualify inbound leads, define their ICP, build a lead scoring model, set MQL criteria, or route prospects through pipeline stages. Activate when the user mentions lead scoring, ICP, MQL, SQL, lead qualification, inbound leads, or pipeline design.

    Also in 3 projects that use this

  • claude-office-skillsSkill

    email-marketing

    Email marketing automation - campaign creation, sequence building, A/B testing, deliverability optimization, and analytics

    Also in 4 projects that use this

  • +2 more from boraoztunc

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 41 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After brand-identity if a name and colors exist, but a plain page works too.

    line 21
  2. Distinctive:

    Not for a full website or a search engine strategy.

    line 22
  3. Distinctive:

    Stay honest: if the product does not exist yet, say "join the waitlist" or "pre-order, delivery planned for…".

    line 35
  4. Distinctive:

    Every claim, testimonial and number on the page is real.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 41 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Landing page

A landing page is often the first real experiment of a startup: if strangers will not leave an email, they are unlikely to pay. This skill writes the page, builds it as a single HTML file, and sets the numbers that decide what happens next.

When to use

  • To test demand before building (a smoke test), to collect a waitlist, or to take pre-orders.
  • After brand-identity if a name and colors exist, but a plain page works too.
  • Not for a full website or a search engine strategy.

Inputs

  1. Target visitor, problem, promise and any real proof (quotes, numbers, logos with permission).
  2. The one action wanted: an email, a pre-order, a demo request.
  3. Brand elements if they exist, and where the form data should go.

Method

  1. One page, one visitor, one action. Choose the target visitor and the single call to action; remove links that lead away from it.
  2. Write the top of the page first: a headline that states the result for the visitor (not the technology), a line that says how, the call to action, and an image of the product or of the result. Test: a stranger understands what it is and who it is for in five seconds.
  3. Then the rest: the problem in the customers' own words (from customer-interviews), how it works in three steps, real proof, answers to the main objections (price, trust, time), a short FAQ, and the call to action again.
  4. Stay honest: if the product does not exist yet, say "join the waitlist" or "pre-order, delivery planned for…". Never invent testimonials, counters or scarcity. For pre-orders, state the delivery date and the refund terms.
  5. Build it as one HTML file: semantic headings, alternative text on images, readable contrast, works on a phone. The form posts to a service the founder chooses (a form tool, a newsletter tool or a spreadsheet), and a short privacy notice says how the emails will be used (GDPR in the European Union).
  6. Plan the test: where the visitors will come from (it matters as much as the page), how many, the target conversion decided in advance, and the duration. Test two headlines at most.
  7. Read the results: visitors and conversion by source, questions people asked, and the decision against the criteria set before launch.

Output

### Page plan
Visitor: … | Promise: … | Call to action: … | Success if …% of … visitors from … within … days

### Copy
Headline: … | Line under it: … | Button: …
Sections: problem, how it works, proof, objections, FAQ

### HTML
<one accessible file, form address to configure, privacy notice included>

Quality bar

  • The headline states a result for a specific visitor, and the page has one main call to action.
  • Every claim, testimonial and number on the page is real; nothing fakes scarcity or social proof.
  • The page is accessible, works on a phone, and explains how collected data is used.
  • The traffic plan and the success criterion are written before launch.
  • Written in the user's language, with the terms below.

Terminology

EnglishFrançaisEspañol
Landing pagePage d'atterrissage (landing page)Página de aterrizaje (landing page)
Call to action (CTA)Appel à l'actionLlamada a la acción
Above the foldHaut de page, partie visible sans défilerPrimera pantalla
Conversion rateTaux de conversionTasa de conversión
WaitlistListe d'attenteLista de espera
A/B testTest A/BPrueba A/B

Sources

  • Krug, S. (2014). Don't Make Me Think, Revisited (3rd ed.). New Riders.
  • Ries, E. (2011). The Lean Startup. Crown Business.
  • W3C. (2023). Web Content Accessibility Guidelines (WCAG) 2.2. https://www.w3.org/TR/WCAG22/

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.