Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Genera instrucciones operativas y la estructura de capítulos para un proyecto de libro viajero de recetas donde niños asocian platos con emociones específicas para desarrollar inteligencia emocional.
.claude/skills/ecnu-icalk-disen-ar-gui-a-de-proyecto-para-recetario-viajero-emocional-infantil/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 29% | 0% |
Genera instrucciones operativas y la estructura de capítulos para un proyecto de libro viajero de recetas donde niños asocian platos con emociones específicas para desarrollar inteligencia emocional.
Actúa como un diseñador de contenido educativo especializado en inteligencia emocional infantil. Tu tarea es crear una guía detallada de instrucciones para un proyecto de "Recetario Emocional Viajero" dirigido a niños (aprox. 8 años). El objetivo es que los niños desarrollen y expresen emociones asertivamente a través de la cocina y la escritura.
Al generar la guía, debes cumplir estrictamente con los siguientes requisitos:
Cada entrada del libro debe contener las siguientes secciones:
El tono debe ser inspirador, claro y estructurado, facilitando la comprensión tanto para los niños como para sus padres.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 13,640 | 19,297 | +41% | 1 | 1 | 0% | 1,983 | 3,593 | +81% | 0 | 0 | — |
case-11 | fail→pass | 15,635 | 13,089 | -16% | 1 | 1 | 0% | 2,374 | 2,890 | +22% | 0 | 0 | — |
case-01 | fail→pass | 16,750 | 21,308 | +27% | 1 | 1 | 0% | 2,709 | 3,984 | +47% | 0 | 0 | — |
case-02 | fail→pass | 17,237 | 16,417 | -5% | 1 | 1 | 0% | 2,631 | 3,432 | +30% | 0 | 0 | — |
case-03 | fail→pass | 16,983 | 16,584 | -2% | 1 | 1 | 0% | 2,641 | 3,414 | +29% | 0 | 0 | — |
case-04 | fail→fail | 14,893 | 17,386 | +17% | 1 | 1 | 0% | 2,318 | 3,489 | +51% | 0 | 0 | — |
case-05 | fail→fail | 12,275 | 18,187 | +48% | 1 | 1 | 0% | 1,919 | 3,665 | +91% | 0 | 0 | — |
case-07 | fail→pass | 12,123 | 19,345 | +60% | 1 | 1 | 0% | 1,931 | 3,647 | +89% | 0 | 0 | — |
case-08 | pass→pass | 11,450 | 14,776 | +29% | 1 | 1 | 0% | 1,665 | 3,082 | +85% | 0 | 0 | — |
case-09 | pass→pass | 15,306 | 13,888 | -9% | 1 | 1 | 0% | 2,372 | 2,810 | +18% | 0 | 0 | — |
case-10 | fail→fail | 14,958 | 16,071 | +7% | 1 | 1 | 0% | 2,365 | 3,191 | +35% | 0 | 0 | — |
case-12 | pass→pass | 10,481 | 8,717 | -17% | 1 | 1 | 0% | 1,567 | 1,960 | +25% | 0 | 0 | — |
case-13 | fail→fail | 10,144 | 8,972 | -12% | 1 | 1 | 0% | 1,642 | 1,952 | +19% | 0 | 0 | — |
case-14 | pass→pass | 10,464 | 16,173 | +55% | 1 | 1 | 0% | 1,563 | 3,392 | +117% | 0 | 0 | — |
case-15 | pass→pass | 14,413 | 12,398 | -14% | 1 | 1 | 0% | 2,223 | 2,657 | +20% | 0 | 0 | — |
case-16 | pass→pass | 10,922 | 9,904 | -9% | 1 | 1 | 0% | 1,829 | 2,296 | +26% | 0 | 0 | — |
case-17 | fail→pass | 8,322 | 3,940 | -53% | 1 | 1 | 0% | 1,292 | 1,352 | +5% | 0 | 0 | — |
case-18 | pass→pass | 16,699 | 15,909 | -5% | 1 | 1 | 0% | 2,683 | 3,386 | +26% | 0 | 0 | — |
case-19 | fail→pass | 10,153 | 8,575 | -16% | 1 | 1 | 0% | 1,624 | 1,976 | +22% | 0 | 0 | — |
case-20 | pass→pass | 17,001 | 16,966 | -0% | 1 | 1 | 0% | 2,956 | 3,711 | +26% | 0 | 0 | — |
case-21 | pass→pass | 14,568 | 10,110 | -31% | 1 | 1 | 0% | 2,230 | 2,092 | -6% | 0 | 0 | — |
case-22 | pass→pass | 12,081 | 13,582 | +12% | 1 | 1 | 0% | 2,107 | 3,087 | +47% | 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 +36 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.