agentleFS
manish1803manish1803/nextjs-fullstack-skills/skills/03-product-saas/landing-page-conversion/SKILL.md

landing-page-conversion

Skill2 starsChanged 4 months agoMITView on GitHub

Design and build high-converting landing/marketing pages — hero sections, social proof, pricing sections, and CTA placement grounded in conversion best practices. Use whenever the user builds a landing page, marketing site, product page, or asks how to improve conversion rate.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep body copy scannable: short paragraphs, bolded key phrases, bullet lists over dense paragraphs.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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 Conversion Optimization Skill

Page structure that converts (default order, adapt to product)

  1. Hero: one clear value proposition (what it does + who it's for), a single primary CTA above the fold, minimal supporting copy. Avoid a hero that has to explain the product before the value is clear.
  2. Social proof band: logos/testimonials/usage stats directly under the hero — reduces bounce before the visitor has to think.
  3. Problem → solution: 2-4 sections mapping a specific user pain to how the product solves it, not a generic feature list.
  4. Feature showcase: visual (screenshot/demo/3D) paired with a short benefit statement per feature — benefit first, feature second.
  5. Pricing (if applicable): clear tiers, one visually emphasized "recommended" tier, transparent about what's included — hidden pricing hurts conversion for self-serve SaaS.
  6. FAQ / objection handling: address the top 4-6 real objections (security, migration effort, pricing concerns) directly.
  7. Final CTA: restate the value prop, repeat the primary action.

CTA discipline

  • One primary CTA per section, consistent wording/color for the primary action throughout the page (don't dilute with 4 different competing CTAs).
  • Primary CTA copy states the outcome, not the mechanism: "Start building free" over generic "Submit"/"Click here."
  • Secondary CTA (e.g. "Watch demo," "View docs") visually subordinate to the primary.

Trust & friction reduction

  • Show pricing/no-credit-card-required language near signup CTAs if true — uncertainty about cost is a top drop-off cause.
  • Testimonials with a real name, role, and company (with photo/logo) convert meaningfully better than unattributed quotes.
  • Page load speed is a conversion factor, not just a technical metric — hero image/video must be optimized (see performance-seo-optimization skill); a slow hero directly costs conversions.

Copy principles

  • Headlines speak to the visitor's outcome ("Ship your SaaS in weeks"), not the company's internal jargon ("Our proprietary platform").
  • Keep body copy scannable: short paragraphs, bolded key phrases, bullet lists over dense paragraphs.

Anti-patterns to flag

  • Hero section requiring scroll to understand what the product does
  • More than one visually-competing primary CTA in the same viewport
  • Pricing page with vague "Contact us" as the only option for a self-serve-appropriate product
  • Heavy unoptimized hero video/image tanking LCP

Example prompt this skill should trigger on

"Build a landing page for our new SaaS product that converts visitors into signups."

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.