Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Motor de crescimento para produtos digitais -- growth hacking, SEO, ASO, viral loops, email marketing, CRM, referral programs e aquisicao organica.
.claude/skills/growth-engine/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-19 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
| case-09 | ✗→✓ | ▲ Improved | — | — |
Motor de crescimento para produtos digitais -- growth hacking, SEO, ASO, viral loops, email marketing, CRM, referral programs e aquisicao organica. Ativar para: criar estrategia de growth, SEO tecnico, ASO para app stores, programa de referral, email marketing, viral coefficient, funil de aquisicao, conteudo para crescimento organico, campanhas de lancamento.
> O melhor marketing e um produto que as pessoas amam. -- Sam Altman > Crescimento real comeca com um produto que vale a pena recomendar.
AQUISICAO: Como as pessoas descobrem a Auri? Meta: 10.000 visitantes/mes -> 1.000 cadastros Canais: SEO, Product Hunt, Influencers tech, PR
ATIVACAO: Quando o usuario experimenta o primeiro valor? Meta: 60% completam primeira conversa em 24h Metrica: First Conversation Rate (FCR)
RETENCAO: As pessoas voltam? Meta: D7 = 30%, D30 = 15%, D90 = 8% Metrica: WAC (Weekly Active Conversationalists)
RECEITA: As pessoas pagam? Meta: 8% trial->Pro conversao Metrica: MRR, ARPU, LTV
REFERENCIA: As pessoas indicam? Meta: NPS > 50, Viral Coefficient > 0.3 Metrica: Referrals per user, K-factor
<title>Auri -- O Assistente de Voz que Realmente Pensa | para Alexa</title> <meta name="description" content="Auri transforma seu Alexa em um assistente com Claude AI. Analise de negocios, decisoes estrategicas e memoria real.">
<meta property="og:title" content="Auri -- IA de Voz para Alexa"> <meta property="og:description" content="O primeiro assistente de voz com raciocinio real. Powered by Claude.">
<script type="application/ld+json"> { "@context": "https://schema.org", "@type": "SoftwareApplication", "name": "Auri", "operatingSystem": "Amazon Alexa", "applicationCategory": "AI Assistant", "offers": {"@type": "Offer", "price": "0"}, "aggregateRating": {"@type": "AggregateRating", "ratingValue": "4.8", "ratingCount": "127"} } </script>
High Intent (converter):
Informacional (educar):
Long tail (baixa competicao):
skill_name: "Auri -- IA de Voz Inteligente" invocation: "auri"
short_description: > Auri transforma seu Alexa em um assistente verdadeiramente inteligente. Powered by Claude AI -- pensa, recorda e evolui com voce.
long_description: > Chega de respostas rasas. Auri e o primeiro assistente de voz com raciocinio real para o mercado brasileiro.
O QUE A AURI FAZ:
COMO COMECAR: Diga "Alexa, abrir Auri" e comece a conversar naturalmente.
example_phrases:
keywords: "ia, inteligencia artificial, assistente inteligente, claude, negocios"
Loop 1: WORD-OF-MOUTH ORGANICO Trigger: usuario tem conversa impressionante com Auri Acao: comenta com amigos/nas redes Meta: cada usuario traz 0.3 novos usuarios (K=0.3)
Loop 2: SHARE DE INSIGHTS Trigger: Auri gera insight especialmente bom Acao: botao "Compartilhar esse insight" -> post pronto para redes Meta: 5% das conversas geram um share
Loop 3: REFERRAL PROGRAM Incentivo: Ganhe 1 mes Pro por cada amigo que assinar Meta: 10% dos usuarios Pro indicam pelo menos 1 pessoa
def calculate_k_factor(percent_who_invite, invites_per_user, conversion_rate): k = percent_who_invite invites_per_user conversion_rate if k >= 1: status = "Crescimento viral (cada usuario traz mais de 1)" elif k >= 0.5: status = "Bom (crescimento acelerado)" elif k >= 0.2: status = "Ok (crescimento suportado)" else: status = "Baixo (crescimento lento)" return {"k_factor": round(k, 2), "status": status, "interpretation": f"Cada 100 usuarios trazem {int(k100)} novos"}
Dia 0 -- Boas-vindas (imediato apos cadastro) Assunto: "Bem-vindo a Auri. Aqui esta como comecar." Body: Tutorial em 3 passos, link para primeira conversa, dica de uso
Dia 1 -- Ativacao (se nao fez primeira conversa) Assunto: "Sua Auri esta esperando voce" Body: Os 3 tipos de perguntas que mais impressionam, CTA urgente
Dia 3 -- Educacao Assunto: "O que 100 usuarios da Auri descobriram essa semana" Body: Case real + insight surpreendente + feature escondida
Dia 7 -- Upsell (se usou pelo menos 3x) Assunto: "Voce esta usando 80% do limite gratuito" Body: O que Pro desbloqueia, oferta especial por 48h, prova social
Dia 14 -- Reativacao (se parou de usar) Assunto: "Saudade, nome]. O que aconteceu?" Body: Pergunta genuina, link para retorno facil, nova feature
1 semana antes:
Dia de lancamento (meia-noite PT):
Posicionamento: Tagline: "The Alexa skill that actually thinks"
| Comando | Acao | |---------|------| | /growth-audit | Auditoria completa de growth | | /seo-analysis | Analise SEO da landing page | | /aso-optimize | Otimiza metadata da skill Alexa | | /viral-loop | Projeta viral loop para o produto | | /email-sequence | Cria sequencia de email marketing | | /launch-plan | Plano de lancamento completo | | /referral-program | Desenha programa de referral |
analytics-product - Complementary skill for enhanced analysismonetization - Complementary skill for enhanced analysisproduct-design - Complementary skill for enhanced analysisproduct-inventor - Complementary skill for enhanced analysisUser request:
> Review this campaign asset with @growth-engine, identify the main conversion problem, and produce an improved version grounded in the available evidence.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +50 percentage points is the difference between those two pass rates over the 21 comparable cases.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.