Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Guía completa de voz de marca NGX "Verdad Directa" con modos de comunicación, adaptación por audiencia y ejemplos aprobados
.claude/skills/aiskillstore-ngx-brand-voice/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 19% | 0% |
Esta skill proporciona el contexto completo de la voz de marca NGX para generar contenido alineado.
Activa esta skill cuando necesites:
voice-guide.md - Guía completa de voz de marcamode-examples.md - Ejemplos de cada modo de comunicaciónaudience-adaptation.md - Adaptación por segmento de edadagent-voices.md - Personalidad de voz de cada agentechecklist.md - Checklist de validación pre-publicación| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 11,209 | 8,700 | -22% | 1 | 1 | 0% | 1,760 | 1,575 | -11% | 0 | 0 | — |
case-02 | fail→fail | 7,125 | 4,872 | -32% | 1 | 1 | 0% | 992 | 952 | -4% | 0 | 0 | — |
case-03 | fail→fail | 13,789 | 11,568 | -16% | 1 | 1 | 0% | 2,007 | 2,111 | +5% | 0 | 0 | — |
case-04 | fail→fail | 18,252 | 15,227 | -17% | 1 | 1 | 0% | 3,026 | 2,685 | -11% | 0 | 0 | — |
case-05 | pass→pass | 16,181 | 14,801 | -9% | 1 | 1 | 0% | 2,715 | 3,187 | +17% | 0 | 0 | — |
case-06 | fail→fail | 14,713 | 15,520 | +5% | 1 | 1 | 0% | 2,570 | 2,890 | +12% | 0 | 0 | — |
case-07 | fail→pass | 13,968 | 10,103 | -28% | 1 | 1 | 0% | 2,099 | 1,765 | -16% | 0 | 0 | — |
case-08 | fail→pass | 9,247 | 9,864 | +7% | 1 | 1 | 0% | 1,296 | 1,660 | +28% | 0 | 0 | — |
case-09 | fail→pass | 10,965 | 11,878 | +8% | 1 | 1 | 0% | 1,620 | 2,068 | +28% | 0 | 0 | — |
case-10 | pass→pass | 13,185 | 14,237 | +8% | 1 | 1 | 0% | 2,028 | 2,536 | +25% | 0 | 0 | — |
case-11 | pass→pass | 8,212 | 7,505 | -9% | 1 | 1 | 0% | 1,289 | 1,314 | +2% | 0 | 0 | — |
case-12 | pass→pass | 14,479 | 7,502 | -48% | 1 | 1 | 0% | 1,387 | 1,360 | -2% | 0 | 0 | — |
case-13 | pass→pass | 13,575 | 11,027 | -19% | 1 | 1 | 0% | 2,137 | 1,855 | -13% | 0 | 0 | — |
case-14 | pass→pass | 11,000 | 9,246 | -16% | 1 | 1 | 0% | 1,660 | 1,622 | -2% | 0 | 0 | — |
case-15 | fail→fail | 17,743 | 21,620 | +22% | 1 | 1 | 0% | 2,564 | 3,324 | +30% | 0 | 0 | — |
case-16 | pass→pass | 12,268 | 14,108 | +15% | 1 | 1 | 0% | 1,795 | 2,244 | +25% | 0 | 0 | — |
case-17 | fail→pass | 12,651 | 11,641 | -8% | 1 | 1 | 0% | 2,140 | 2,122 | -1% | 0 | 0 | — |
case-18 | pass→pass | 14,249 | 13,797 | -3% | 1 | 1 | 0% | 2,073 | 2,434 | +17% | 0 | 0 | — |
case-19 | pass→pass | 14,147 | 10,530 | -26% | 1 | 1 | 0% | 2,045 | 1,838 | -10% | 0 | 0 | — |
case-20 | fail→pass | 12,159 | 11,362 | -7% | 1 | 1 | 0% | 1,682 | 1,997 | +19% | 0 | 0 | — |
case-21 | pass→pass | 14,057 | 9,055 | -36% | 1 | 1 | 0% | 1,625 | 1,747 | +8% | 0 | 0 | — |
case-22 | pass→pass | 15,425 | 10,524 | -32% | 1 | 1 | 0% | 1,781 | 1,748 | -2% | 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 +23 percentage points is the difference between those two pass rates over the 22 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.