Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create, optimize, or audit campaign landing pages for paid ads, email, or other traffic. Also use when the user mentions "landing page," "PPC landing page," "SEM landing page," "conversion page," "campaign page," "lead capture page," "landing page optimization," "LP conversion," "single-page funnel," or "squeeze page." Not for the main site homepage; use homepage-generator.
.claude/skills/mkurman-landing-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 110% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 126% | 0% |
| case-21 | ✓→✗ | ▼ Worse | 92% | 0% |
|---------|----------| | 1. Stop the scroll | Capture attention in ~2.6 seconds | Headline, subheadline, hero image or video | | 2. Earn trust | Social proof before the ask | Logos, testimonials, ratings, customer count | | 3. Explain value | Benefits, features, use cases | Clear copy; who it's for, what it does | | 4. Remove doubt | Objection handling | FAQ, guarantees, comparison | | 5. Make the ask | Single primary CTA | One clear action; repeat at logical points |
Every element should serve one of these five functions. Pages with multiple competing offers get ~266% fewer leads.
Who it's for] + Specific outcome] + Time/qualifier]
When you need many landing pages (e.g., city-specific, product-specific, integration-specific), use programmatic-seo: one template + data = hundreds or thousands of LPs. Apply landing page structure (5-step flow, CTA, trust) to the template; see template-page-generator for template design. Example: "Product] for City]" LPs with local data; "App A] + App B]" integration signup pages.
| Type | Use | CTA Destination | |------|-----|-----------------| | Click-through | Warm audience before sending to offer; best for SaaS, subscriptions | pricing-page, products-page, signup | | Lead capture | Collect email for nurture; forms 5 fields or fewer (longer forms cause ~81% abandonment) | newsletter-signup, contact-page | | Product-focused | Deep-dive features and benefits; product launch | products-page, features-page | | Comparison | X vs Y; competitor brand keyword ads; commercial intent | alternatives-page, features-page, pricing-page | | Use cases / Solutions | For integrated products hard to split into tools | features-page, services-page | | Free tools | Standalone utilities; lead gen; same ICP; excerpt from product | tools-page-generator; tool page as LP when gated | | Bridge/bonus | Extra incentive to purchase through your link | pricing-page, products-page | | Webinar/event | Event registration; collect signups before live | resources-page (webinar as resource) |
Pull content from (step 2–4):
CTA sends to:
Internal linking:
Before shipping a landing page, verify:
| Category | Check | |----------|-------| | Visual | No emojis as icons (use SVG); icons from consistent set (Heroicons/Lucide); hover states don't cause layout shift | | Interaction | All clickable elements have cursor-pointer; hover provides clear feedback; transitions 150–300ms | | Accessibility | Images have alt text; form inputs have labels; color not sole indicator; prefers-reduced-motion respected | | Layout | No horizontal scroll on mobile; content not hidden behind fixed nav; responsive at 375px, 768px, 1024px | | Performance | Load time under 2.5s; LCP optimized; images use WebP/lazy loading where appropriate | | Images | See image-optimization for alt, format, responsive, lazy loading |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 12,746 | 13,142 | +3% | 1 | 1 | 0% | 2,058 | 3,605 | +75% | 0 | 0 | — |
case-11 | pass→pass | 12,105 | 13,698 | +13% | 1 | 1 | 0% | 1,927 | 3,726 | +93% | 0 | 0 | — |
case-20 | pass→pass | 28,471 | 28,053 | -1% | 1 | 1 | 0% | 4,014 | 5,692 | +42% | 0 | 0 | — |
case-01 | fail→fail | 28,180 | 31,790 | +13% | 1 | 1 | 0% | 4,295 | 6,910 | +61% | 0 | 0 | — |
case-02 | fail→fail | 22,563 | 22,200 | -2% | 1 | 1 | 0% | 3,434 | 5,228 | +52% | 0 | 0 | — |
case-03 | fail→pass | 11,136 | 11,786 | +6% | 1 | 1 | 0% | 1,646 | 3,464 | +110% | 0 | 0 | — |
case-04 | fail→fail | 14,048 | 14,832 | +6% | 1 | 1 | 0% | 2,218 | 3,841 | +73% | 0 | 0 | — |
case-06 | pass→pass | 12,802 | 6,642 | -48% | 1 | 1 | 0% | 1,736 | 2,631 | +52% | 0 | 0 | — |
case-07 | pass→pass | 10,865 | 6,154 | -43% | 1 | 1 | 0% | 1,726 | 2,573 | +49% | 0 | 0 | — |
case-08 | pass→pass | 15,475 | 13,536 | -13% | 1 | 1 | 0% | 2,343 | 3,728 | +59% | 0 | 0 | — |
case-09 | fail→pass | 13,343 | 9,885 | -26% | 1 | 1 | 0% | 1,977 | 3,237 | +64% | 0 | 0 | — |
case-10 | pass→pass | 11,173 | 7,735 | -31% | 1 | 1 | 0% | 1,648 | 2,774 | +68% | 0 | 0 | — |
case-12 | fail→pass | 9,548 | 2,662 | -72% | 1 | 1 | 0% | 1,487 | 1,978 | +33% | 0 | 0 | — |
case-13 | pass→pass | 11,609 | 2,374 | -80% | 1 | 1 | 0% | 1,838 | 1,928 | +5% | 0 | 0 | — |
case-14 | pass→pass | 8,621 | 6,802 | -21% | 1 | 1 | 0% | 1,361 | 2,676 | +97% | 0 | 0 | — |
case-15 | pass→pass | 15,919 | 2,520 | -84% | 1 | 1 | 0% | 2,517 | 1,971 | -22% | 0 | 0 | — |
case-16 | pass→pass | 10,650 | 7,730 | -27% | 1 | 1 | 0% | 1,668 | 2,767 | +66% | 0 | 0 | — |
case-17 | pass→pass | 14,095 | 7,543 | -46% | 1 | 1 | 0% | 2,125 | 2,777 | +31% | 0 | 0 | — |
case-18 | fail→pass | 5,743 | 2,313 | -60% | 1 | 1 | 0% | 854 | 1,934 | +126% | 0 | 0 | — |
case-19 | pass→pass | 10,284 | 2,233 | -78% | 1 | 1 | 0% | 1,665 | 1,864 | +12% | 0 | 0 | — |
case-21 | pass→fail | 19,180 | 29,193 | +52% | 1 | 1 | 0% | 3,317 | 6,358 | +92% | 0 | 0 | — |
case-22 | pass→pass | 16,567 | 15,450 | -7% | 1 | 1 | 0% | 2,719 | 4,039 | +49% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.