Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when designing or rewriting a high-converting landing page (single-offer page) for SaaS/apps/services. Covers structure, layout patterns, conversion strategies, copywriting, SEO/AEO, and common pitfalls.
.claude/skills/mengto-landing-page/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 95% | 21 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -7% | 0% |
A landing page is not a homepage. A homepage serves multiple intents. A landing page wins one intent: one offer → one audience → one primary action.
Gather (ask if missing):
1) Headline (outcome + audience) 2) Subheadline (clarifies “how” + adds specificity) 3) Primary CTA (clear verb + what they get) 4) One proof signal (logo strip / stat / short testimonial) 5) Hero visual (product screenshot/video) or a strong illustration
6) Problem → solution (1 section) 7) Benefits (3–5, outcome-driven) 8) How it works (3 steps) 9) Social proof (testimonials/case study)
10) FAQ (6–12 Q/A) 11) Risk reversal (trial, cancel anytime, guarantee) 12) Final CTA (same as top)
Best when:
Best when:
Best when:
Best when:
If traffic is from ads:
Pick at least one:
Examples:
Format:
Example:
Work in this order: 1) Hero 2) Benefits 3) How it works 4) Proof 5) FAQ 6) Final CTA
Rule: don’t rebuild the whole page each time. Iterate section-by-section to keep control.
Use:
noindex (or keep it behind a non-indexed path)Add:
Optional:
Return: 1) Page outline (sections + order) 2) Hero copy (headline, subheadline, CTA, proof line) 3) Benefits section (3–5 bullets) 4) How it works (3 steps) 5) FAQ (6–12 Q/A) 6) SEO/AEO (indexing recommendation + title/meta if indexed) 7) Layout recommendation (A/B/C/D + why)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 17,993 | 17,964 | -0% | 1 | 1 | 0% | 3,236 | 4,562 | +41% | 0 | 0 | — |
case-02 | fail→pass | 18,368 | 17,136 | -7% | 1 | 1 | 0% | 3,474 | 4,499 | +30% | 0 | 0 | — |
case-03 | fail→pass | 23,665 | 19,166 | -19% | 1 | 1 | 0% | 4,182 | 4,890 | +17% | 0 | 0 | — |
case-04 | pass→pass | 12,141 | 13,579 | +12% | 1 | 1 | 0% | 2,385 | 3,876 | +63% | 0 | 0 | — |
case-05 | pass→pass | 13,269 | 11,138 | -16% | 1 | 1 | 0% | 2,424 | 3,410 | +41% | 0 | 0 | — |
case-06 | pass→pass | 23,386 | 19,158 | -18% | 1 | 1 | 0% | 4,396 | 4,768 | +8% | 0 | 0 | — |
case-07 | pass→pass | 12,733 | 10,159 | -20% | 1 | 1 | 0% | 2,306 | 3,198 | +39% | 0 | 0 | — |
case-08 | fail→pass | 10,045 | 7,177 | -29% | 1 | 1 | 0% | 1,747 | 2,647 | +52% | 0 | 0 | — |
case-09 | pass→pass | 6,864 | 8,187 | +19% | 1 | 1 | 0% | 1,334 | 2,833 | +112% | 0 | 0 | — |
case-10 | pass→pass | 9,182 | 8,213 | -11% | 1 | 1 | 0% | 1,761 | 2,876 | +63% | 0 | 0 | — |
case-11 | fail→pass | 12,160 | 5,697 | -53% | 1 | 1 | 0% | 2,030 | 2,349 | +16% | 0 | 0 | — |
case-12 | fail→pass | 12,850 | 4,929 | -62% | 1 | 1 | 0% | 2,355 | 2,200 | -7% | 0 | 0 | — |
case-13 | pass→pass | 5,370 | 5,028 | -6% | 1 | 1 | 0% | 937 | 2,089 | +123% | 0 | 0 | — |
case-14 | pass→pass | 9,289 | 8,049 | -13% | 1 | 1 | 0% | 1,668 | 2,750 | +65% | 0 | 0 | — |
case-15 | pass→pass | 13,295 | 11,774 | -11% | 1 | 1 | 0% | 2,369 | 3,489 | +47% | 0 | 0 | — |
case-16 | pass→pass | 15,923 | 7,907 | -50% | 1 | 1 | 0% | 2,560 | 2,800 | +9% | 0 | 0 | — |
case-17 | pass→pass | 7,972 | 6,214 | -22% | 1 | 1 | 0% | 1,433 | 2,577 | +80% | 0 | 0 | — |
case-18 | fail→pass | 23,563 | 8,543 | -64% | 1 | 1 | 0% | 5,524 | 2,828 | -49% | 0 | 0 | — |
case-19 | fail→pass | 13,114 | 8,943 | -32% | 1 | 1 | 0% | 2,173 | 2,904 | +34% | 0 | 0 | — |
case-20 | pass→pass | 12,950 | 10,018 | -23% | 1 | 1 | 0% | 2,303 | 3,277 | +42% | 0 | 0 | — |
case-21 | pass→pass | 11,427 | 7,806 | -32% | 1 | 1 | 0% | 1,890 | 2,715 | +44% | 0 | 0 | — |
case-22 | pass→pass | 11,989 | 11,297 | -6% | 1 | 1 | 0% | 2,099 | 3,340 | +59% | 0 | 0 | — |
case-23 | pass→pass | 10,996 | 8,803 | -20% | 1 | 1 | 0% | 1,885 | 2,829 | +50% | 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. 23 cases were attempted. The headline lift of +30 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.