Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Define a creator's brand foundation — niche, audience, positioning, content pillars, voice/tone, and bio — so every post is consistent and on-brand. Use when asked to define a creator brand, find a niche, set content pillars, write a voice guide, craft a bio, or build a brand kit for a personal brand or channel. Produces a reusable one-page brand kit that other content skills can read so output sounds like you, every time.
.claude/skills/mohitagw15856-creator-brand-kit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 51% | 0% |
La diferencia entre un creador que crece y uno que solo produce contenido es la consistencia — mismo nicho, misma voz, pilares reconocibles. Este skill construye la base que otros skills de contenido leen: tu nicho, a quién sirves, cómo suenas y de qué hablas. Es el "lee primero" del stack de creadores.
Dado un descripción aproximada (handle, qué publican, vibra), construye el kit completo de todas formas — propón un nicho y pilares claros, e etiqueta las decisiones como (borrador — confirmar). Empuja hacia la especificidad: "fitness" no es un nicho; "entrenamiento de fuerza para trabajadores de escritorio mayores de 40" sí lo es.
Pregunta por (si no están ya proporcionados):
Un kit de marca de una página, reutilizable:
Quiénes son, con qué luchan, a qué aspiran, dónde se reúnen.
3–5 pilares (los temas recurrentes de los que publicas), cada uno con: qué cubre, por qué sirve a la audiencia, y 2–3 ideas de posts de ejemplo. Busca una mezcla de crecimiento (alcance), nutrición (confianza) y conversión (venta).
Cómo pegar esto en otros skills (o en la caja "🧠 Tu contexto" del Playground / un CONTEXT.md) para que content-repurposer]], hook-writer]], short-form-script]] y newsletter-writer]] todos suenen como tú.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 26,703 | 20,761 | -22% | 1 | 1 | 0% | 4,276 | 3,897 | -9% | 0 | 0 | — |
case-02 | fail→fail | 17,610 | 22,339 | +27% | 1 | 1 | 0% | 2,924 | 4,509 | +54% | 0 | 0 | — |
case-03 | fail→fail | 31,455 | 23,659 | -25% | 1 | 1 | 0% | 4,699 | 4,468 | -5% | 0 | 0 | — |
case-04 | pass→fail | 28,450 | 23,936 | -16% | 1 | 1 | 0% | 2,083 | 4,388 | +111% | 0 | 0 | — |
case-05 | pass→pass | 7,573 | 8,770 | +16% | 1 | 1 | 0% | 1,337 | 2,226 | +66% | 0 | 0 | — |
case-06 | pass→fail | 12,824 | 7,337 | -43% | 1 | 1 | 0% | 2,029 | 1,896 | -7% | 0 | 0 | — |
case-07 | fail→fail | 17,833 | 19,397 | +9% | 1 | 1 | 0% | 2,652 | 3,772 | +42% | 0 | 0 | — |
case-08 | fail→pass | 17,573 | 16,818 | -4% | 1 | 1 | 0% | 3,040 | 3,650 | +20% | 0 | 0 | — |
case-09 | fail→pass | 42,090 | 21,328 | -49% | 1 | 1 | 0% | 3,195 | 4,495 | +41% | 0 | 0 | — |
case-10 | pass→pass | 24,458 | 22,015 | -10% | 1 | 1 | 0% | 3,817 | 4,680 | +23% | 0 | 0 | — |
case-11 | fail→pass | 19,411 | 19,190 | -1% | 1 | 1 | 0% | 2,954 | 4,252 | +44% | 0 | 0 | — |
case-12 | fail→fail | 19,611 | 26,643 | +36% | 1 | 1 | 0% | 3,239 | 4,744 | +46% | 0 | 0 | — |
case-13 | fail→fail | 17,907 | 19,981 | +12% | 1 | 1 | 0% | 2,943 | 3,836 | +30% | 0 | 0 | — |
case-14 | fail→pass | 17,240 | 21,199 | +23% | 1 | 1 | 0% | 2,819 | 4,447 | +58% | 0 | 0 | — |
case-15 | fail→pass | 14,160 | 16,929 | +20% | 1 | 1 | 0% | 2,457 | 3,705 | +51% | 0 | 0 | — |
case-16 | fail→pass | 16,595 | 19,052 | +15% | 1 | 1 | 0% | 2,905 | 4,267 | +47% | 0 | 0 | — |
case-17 | fail→pass | 18,611 | 18,017 | -3% | 1 | 1 | 0% | 3,061 | 3,769 | +23% | 0 | 0 | — |
case-18 | fail→fail | 20,185 | 20,003 | -1% | 1 | 1 | 0% | 3,331 | 4,044 | +21% | 0 | 0 | — |
case-19 | fail→pass | 15,864 | 16,513 | +4% | 1 | 1 | 0% | 2,727 | 3,631 | +33% | 0 | 0 | — |
case-20 | fail→fail | 15,212 | 20,028 | +32% | 1 | 1 | 0% | 2,531 | 4,146 | +64% | 0 | 0 | — |
case-21 | fail→pass | 17,619 | 18,310 | +4% | 1 | 1 | 0% | 2,908 | 4,007 | +38% | 0 | 0 | — |
case-22 | fail→pass | 14,977 | 18,380 | +23% | 1 | 1 | 0% | 2,321 | 3,717 | +60% | 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. 2 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.