Install any skill in seconds. Free to start, no credit card required.
Get Started Free →单页 SaaS 落地页, 含 hero/features/social-proof/pricing/CTA
.claude/skills/nexu-io-saas-landing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 94% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 53% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 5% | 0% |
【模板: SaaS Landing】 【意图】完整的 SaaS 产品落地页, 把用户内容映射到标准 sections。 【布局】
【设计细节】
md: 断点, 移动端单栏| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 25,690 | 26,929 | +5% | 1 | 1 | 0% | 6,204 | 6,395 | +3% | 0 | 0 | — |
case-02 | fail→fail | 26,749 | 27,066 | +1% | 1 | 1 | 0% | 6,182 | 6,373 | +3% | 0 | 0 | — |
case-03 | fail→fail | 26,493 | 26,608 | +0% | 1 | 1 | 0% | 6,189 | 6,380 | +3% | 0 | 0 | — |
case-04 | pass→pass | 15,493 | 25,399 | +64% | 1 | 1 | 0% | 3,291 | 6,371 | +94% | 0 | 0 | — |
case-05 | pass→pass | 18,295 | 26,088 | +43% | 1 | 1 | 0% | 4,152 | 6,353 | +53% | 0 | 0 | — |
case-06 | pass→pass | 27,159 | 25,922 | -5% | 1 | 1 | 0% | 6,064 | 6,353 | +5% | 0 | 0 | — |
case-07 | fail→fail | 16,046 | 27,673 | +72% | 1 | 1 | 0% | 3,765 | 6,361 | +69% | 0 | 0 | — |
case-08 | fail→fail | 10,899 | 26,658 | +145% | 1 | 1 | 0% | 1,789 | 6,349 | +255% | 0 | 0 | — |
case-09 | fail→fail | 26,327 | 25,329 | -4% | 1 | 1 | 0% | 6,171 | 6,362 | +3% | 0 | 0 | — |
case-10 | pass→pass | 25,807 | 25,006 | -3% | 1 | 1 | 0% | 5,799 | 6,358 | +10% | 0 | 0 | — |
case-11 | fail→pass | 20,244 | 25,234 | +25% | 1 | 1 | 0% | 4,219 | 6,371 | +51% | 0 | 0 | — |
case-12 | pass→pass | 19,605 | 27,556 | +41% | 1 | 1 | 0% | 3,975 | 6,350 | +60% | 0 | 0 | — |
case-13 | fail→fail | 26,256 | 29,976 | +14% | 1 | 1 | 0% | 6,170 | 6,361 | +3% | 0 | 0 | — |
case-14 | pass→pass | 19,430 | 28,555 | +47% | 1 | 1 | 0% | 3,781 | 6,351 | +68% | 0 | 0 | — |
case-15 | pass→pass | 12,128 | 27,877 | +130% | 1 | 1 | 0% | 2,546 | 6,355 | +150% | 0 | 0 | — |
case-16 | fail→fail | 18,268 | 28,125 | +54% | 1 | 1 | 0% | 4,028 | 6,364 | +58% | 0 | 0 | — |
case-17 | pass→pass | 18,644 | 25,586 | +37% | 1 | 1 | 0% | 3,997 | 6,351 | +59% | 0 | 0 | — |
case-18 | fail→pass | 22,312 | 27,673 | +24% | 1 | 1 | 0% | 5,172 | 6,362 | +23% | 0 | 0 | — |
case-19 | pass→pass | 10,540 | 25,169 | +139% | 1 | 1 | 0% | 1,719 | 6,037 | +251% | 0 | 0 | — |
case-20 | fail→fail | 28,280 | 28,567 | +1% | 1 | 1 | 0% | 6,186 | 6,377 | +3% | 0 | 0 | — |
case-21 | pass→pass | 27,288 | 27,814 | +2% | 1 | 1 | 0% | 6,188 | 6,379 | +3% | 0 | 0 | — |
case-22 | pass→pass | 17,117 | 23,144 | +35% | 1 | 1 | 0% | 4,228 | 5,074 | +20% | 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 -20 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.