Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn one piece of content into a full multi-platform pack — X/Twitter thread, LinkedIn post, newsletter section, Instagram carousel, and a short-form video script — each rewritten natively for its platform, not copy-pasted. Use when asked to repurpose content, atomize a blog post or video, turn one idea into many posts, or get more mileage from a piece. Produces ready-to-post drafts per platform with hooks, formatting, and CTAs tuned to each.
.claude/skills/mohitagw15856-content-repurposer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 123% | 0% |
Los creadores no tienen un problema de contenido — tienen un problema de distribución. Una buena idea debe convertirse en una semana de posts. Este skill atomiza una única fuente (un blog, transcripción de vídeo, newsletter o notas en bruto) en borradores nativos de plataforma — cada uno reescrito para cómo la gente realmente lee en esa plataforma, nunca solo truncado.
Dado un origen (o un tema aproximado), produce el paquete completo de todas formas — extrae la idea central y reformúlala por plataforma. Si el origen es superficial, extrae la idea única más fuerte y construye alrededor de ella. Marca cualquier estadística/ejemplo inventado (asumir — reemplazar). Nunca emitas el mismo texto cinco veces con saltos de línea diferentes.
Pregunta por (si no está ya proporcionado):
Empieza con La idea central en una frase (todo lo demás está subordinado a ella). Luego, por plataforma:
Un tweet gancho que haga scroll, luego 5–9 tweets cada uno llevando un argumento, un tweet CTA final. Apretado, saltos de línea, sin relleno.
Una línea gancho + cuerpo de párrafo corto (mucho espacio en blanco), un aprendizaje concreto, un CTA suave / pregunta para impulsar comentarios. Sin spam de hashtags (3–5 máximo).
Una opción de línea de asunto, una preview de una línea, y una sección de 150–250 palabras con un aprendizaje claro y enlace saliente.
Diapositiva 1 = el gancho; diapositivas 2–6 = un punto cada una (≤12 palabras por diapositiva + una frase de cuerpo); diapositiva final = CTA. Da el texto en pantalla y el caption.
Una línea gancho de 0–3s, los argumentos del cuerpo con pistas de texto en pantalla, y un desenlace/CTA. 30–45s de copia hablada.
Termina con:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→fail | 24,938 | 29,743 | +19% | 1 | 1 | 0% | 4,214 | 6,183 | +47% | 0 | 0 | — |
case-06 | pass→fail | 12,323 | 23,393 | +90% | 1 | 1 | 0% | 2,082 | 4,957 | +138% | 0 | 0 | — |
case-01 | fail→fail | 23,030 | 20,132 | -13% | 1 | 1 | 0% | 3,997 | 4,512 | +13% | 0 | 0 | — |
case-02 | fail→pass | 21,594 | 18,000 | -17% | 1 | 1 | 0% | 3,901 | 4,294 | +10% | 0 | 0 | — |
case-03 | fail→pass | 22,435 | 18,347 | -18% | 1 | 1 | 0% | 3,830 | 4,123 | +8% | 0 | 0 | — |
case-04 | pass→fail | 14,939 | 21,384 | +43% | 1 | 1 | 0% | 2,657 | 4,611 | +74% | 0 | 0 | — |
case-07 | fail→fail | 12,804 | 17,669 | +38% | 1 | 1 | 0% | 1,987 | 3,871 | +95% | 0 | 0 | — |
case-08 | fail→pass | 13,428 | 18,153 | +35% | 1 | 1 | 0% | 2,163 | 3,762 | +74% | 0 | 0 | — |
case-09 | fail→pass | 24,454 | 21,496 | -12% | 1 | 1 | 0% | 3,880 | 4,409 | +14% | 0 | 0 | — |
case-10 | pass→pass | 19,425 | 22,200 | +14% | 1 | 1 | 0% | 3,710 | 4,920 | +33% | 0 | 0 | — |
case-11 | fail→fail | 17,801 | 27,522 | +55% | 1 | 1 | 0% | 3,032 | 5,422 | +79% | 0 | 0 | — |
case-12 | fail→fail | 9,428 | 21,635 | +129% | 1 | 1 | 0% | 1,479 | 4,512 | +205% | 0 | 0 | — |
case-13 | fail→fail | 17,801 | 18,780 | +5% | 1 | 1 | 0% | 2,821 | 4,038 | +43% | 0 | 0 | — |
case-14 | fail→fail | 14,750 | 21,498 | +46% | 1 | 1 | 0% | 2,356 | 4,753 | +102% | 0 | 0 | — |
case-15 | fail→fail | 12,803 | 17,102 | +34% | 1 | 1 | 0% | 2,292 | 3,935 | +72% | 0 | 0 | — |
case-16 | pass→pass | 16,122 | 17,907 | +11% | 1 | 1 | 0% | 3,210 | 3,877 | +21% | 0 | 0 | — |
case-17 | pass→pass | 13,157 | 20,129 | +53% | 1 | 1 | 0% | 2,404 | 4,107 | +71% | 0 | 0 | — |
case-18 | fail→fail | 11,919 | 17,380 | +46% | 1 | 1 | 0% | 2,282 | 4,170 | +83% | 0 | 0 | — |
case-19 | fail→fail | 21,068 | 31,785 | +51% | 1 | 1 | 0% | 3,990 | 6,538 | +64% | 0 | 0 | — |
case-20 | fail→pass | 9,993 | 18,920 | +89% | 1 | 1 | 0% | 1,901 | 4,239 | +123% | 0 | 0 | — |
case-21 | pass→fail | 13,576 | 17,681 | +30% | 1 | 1 | 0% | 2,082 | 4,252 | +104% | 0 | 0 | — |
case-22 | fail→fail | 12,528 | 28,433 | +127% | 1 | 1 | 0% | 2,398 | 6,325 | +164% | 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 +5 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 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.