Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Criterios de evaluación para auditorías de funnel NGX, incluyendo checklist visual, UX, copy y conversión
.claude/skills/aiskillstore-ngx-funnel-criteria/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -12% | 0% |
Esta skill proporciona los criterios de evaluación para auditar landing pages, checkouts y flujos de conversión del funnel NGX.
Activa esta skill cuando necesites:
| Elemento | Correcto | Incorrecto | Puntos | |----------|----------|------------|--------| | Color primario | #6D00FF | Cyan, colores brillantes | 4 | | Fondo principal | #0A0A0A | Blanco, grises claros | 4 | | Cards | Gradiente oscuro + blur | Fondos sólidos | 4 | | Bordes | rgba(255,255,255,0.05) | Bordes gruesos | 4 | | Sombras | Múltiples capas + neón | Sombras simples | 4 |
| Criterio | Sí | No | Puntos | |----------|----|----|--------| | Valor claro en <3 segundos | ✓ | ✗ | 8 | | Headline confronta problema/deseo | ✓ | ✗ | 6 | | Subheadline explica solución | ✓ | ✗ | 5 | | Diferenciador visible | ✓ | ✗ | 6 |
| Criterio | Cumple | No cumple | Puntos | |----------|--------|-----------|--------| | Usa fórmula CONFRONTA→FUNDAMENTA→RESUELVE | ✓ | ✗ | 5 | | Tratamiento correcto (tú/usted) | ✓ | ✗ | 4 | | Menciona agentes correctos | ✓ | ✗ | 3 | | Sin promesas absolutas | ✓ | ✗ | 4 | | Sin términos prohibidos | ✓ | ✗ | 4 |
| Criterio | Óptimo | Problema | Puntos | |----------|--------|----------|--------| | CTA visible above the fold | ✓ | ✗ | 5 | | Formulario ≤4 campos | ✓ | ✗ | 4 | | Mobile responsive | ✓ | ✗ | 5 | | Touch targets ≥44px | ✓ | ✗ | 3 | | Navegación clara | ✓ | ✗ | 3 |
| Criterio | Presente | Ausente | Puntos | |----------|----------|---------|--------| | CTA claro y específico | ✓ | ✗ | 4 | | Garantía visible | ✓ | ✗ | 3 | | Prueba social | ✓ | ✗ | 3 | | Precio/valor claro | ✓ | ✗ | 3 | | Eliminación de fricción | ✓ | ✗ | 2 |
Alertar inmediatamente si:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,002 | 15,919 | -6% | 1 | 1 | 0% | 2,740 | 4,055 | +48% | 0 | 0 | — |
case-02 | fail→fail | 18,785 | 16,546 | -12% | 1 | 1 | 0% | 3,348 | 4,079 | +22% | 0 | 0 | — |
case-03 | fail→fail | 16,750 | 16,763 | +0% | 1 | 1 | 0% | 2,812 | 4,053 | +44% | 0 | 0 | — |
case-04 | fail→pass | 33,861 | 4,783 | -86% | 1 | 1 | 0% | 2,919 | 1,821 | -38% | 0 | 0 | — |
case-05 | fail→pass | 15,806 | 3,228 | -80% | 1 | 1 | 0% | 2,661 | 1,637 | -38% | 0 | 0 | — |
case-06 | fail→pass | 9,831 | 2,558 | -74% | 1 | 1 | 0% | 1,622 | 1,479 | -9% | 0 | 0 | — |
case-07 | pass→pass | 7,802 | 4,326 | -45% | 1 | 1 | 0% | 1,209 | 1,764 | +46% | 0 | 0 | — |
case-08 | fail→pass | 10,958 | 2,736 | -75% | 1 | 1 | 0% | 1,755 | 1,541 | -12% | 0 | 0 | — |
case-09 | pass→pass | 9,664 | 3,648 | -62% | 1 | 1 | 0% | 1,501 | 1,667 | +11% | 0 | 0 | — |
case-10 | pass→pass | 12,193 | 5,439 | -55% | 1 | 1 | 0% | 1,899 | 1,900 | +0% | 0 | 0 | — |
case-11 | pass→pass | 9,642 | 3,050 | -68% | 1 | 1 | 0% | 1,535 | 1,529 | -0% | 0 | 0 | — |
case-12 | pass→pass | 10,412 | 2,482 | -76% | 1 | 1 | 0% | 1,607 | 1,473 | -8% | 0 | 0 | — |
case-13 | fail→pass | 8,764 | 1,928 | -78% | 1 | 1 | 0% | 1,249 | 1,390 | +11% | 0 | 0 | — |
case-18 | fail→pass | 12,596 | 3,917 | -69% | 1 | 1 | 0% | 2,013 | 1,803 | -10% | 0 | 0 | — |
case-14 | pass→pass | 12,511 | 7,262 | -42% | 1 | 1 | 0% | 1,923 | 2,152 | +12% | 0 | 0 | — |
case-15 | pass→pass | 10,796 | 4,591 | -57% | 1 | 1 | 0% | 1,458 | 1,844 | +26% | 0 | 0 | — |
case-16 | pass→pass | 4,915 | 2,715 | -45% | 1 | 1 | 0% | 690 | 1,515 | +120% | 0 | 0 | — |
case-17 | pass→pass | 10,426 | 6,714 | -36% | 1 | 1 | 0% | 1,656 | 2,181 | +32% | 0 | 0 | — |
case-19 | fail→pass | 9,848 | 2,328 | -76% | 1 | 1 | 0% | 1,443 | 1,454 | +1% | 0 | 0 | — |
case-20 | pass→pass | 16,835 | 13,584 | -19% | 1 | 1 | 0% | 3,180 | 3,827 | +20% | 0 | 0 | — |
case-21 | pass→pass | 20,453 | 15,844 | -23% | 1 | 1 | 0% | 3,209 | 3,500 | +9% | 0 | 0 | — |
case-22 | pass→fail | 16,370 | 13,862 | -15% | 1 | 1 | 0% | 3,310 | 3,975 | +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 +32 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.