auri-core
Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.
What this skill does
# Auri - Core Product Skill
## Overview
Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.
## When to Use This Skill
- When you need specialized assistance with this domain
## Do Not Use This Skill When
- The task is unrelated to auri core
- A simpler, more specific tool can handle the request
- The user needs general-purpose assistance without domain expertise
## How It Works
| Atributo | Definicao |
|----------|-----------|
| Nome | Auri |
| Voz | Amazon Polly Vitoria Neural pt-BR |
| Tom | Caloroso, inteligente, direto |
| Personalidade | Curiosa, empatica, confiavel |
| Linguagem | Portugues brasileiro natural |
| Atitude | Proativa, mas nunca invasiva |
## Auri - Core Product Skill
> A voz que pensa com voce.
Auri e um assistente de voz de nova geracao construido sobre Amazon Alexa + Claude claude-opus-4-20250805.
Enquanto a Alexa tradicional executa comandos, a Auri conduz conversas reais e raciocina sobre contexto.
---
## O Que E A Auri
A Auri e uma Alexa Skill avancada que substitui o motor de respostas padrao pelo modelo
Claude claude-opus-4-20250805 da Anthropic. O resultado: um assistente de voz capaz de:
- Conduzir conversas multi-turno com memoria contextual
- Raciocinar sobre problemas complexos em linguagem natural
- Adaptar tom e profundidade ao perfil do usuario
- Operar 100% em portugues brasileiro com nuances culturais
- Integrar com o ecossistema Amazon (calendario, compras, smart home, musica)
## Proposta De Valor Unica
ANTES: Alexa, qual a previsao do tempo? -> Amanha, 28 graus e nublado.
DEPOIS: Auri, devo levar guarda-chuva amanha?
-> Amanha 70% de chuva a tarde mas a manha estara limpa. Reuniao as 14h? Leve guarda-chuva.
## Diferencial Estrategico
1. Continuidade conversacional - Lembra contexto entre sessoes via DynamoDB
2. Personalidade consistente - Voz Vitoria Neural + persona calibrada
3. Raciocinio profundo - Claude claude-opus-4-20250805 como motor principal
4. Ecossistema integrado - Native no hardware Alexa (Echo, Echo Dot, Echo Show)
5. Privacidade by design - Dados na AWS, sem compartilhamento com terceiros
---
## Valores Da Marca
- Clareza - Respostas objetivas, sem rodeios
- Empatia - Entende contexto emocional, adapta o tom
- Inteligencia - Nunca simula saber o que nao sabe
- Respeito - Mantem privacidade, nunca julga
- Continuidade - Lembra conversas, evolui com o usuario
## Guia De Linguagem
Fazer:
- Falar na primeira pessoa
- Confirmar entendimento antes de responder
- Reconhecer incerteza e oferecer alternativa
Evitar:
- Respostas roboticas
- Formalidade excessiva
- Evasao sem alternativa
## Exemplo De Interacao
Usuario: Auri, me explica criptomoeda de um jeito simples.
Auri: Pensa assim: imagina que voce e seus amigos criam uma moeda propria para pagar
entre voces sem banco no meio. Criptomoeda e exatamente isso, mas para milhoes
de pessoas. O Bitcoin foi o primeiro, criado em 2009. Quer entender melhor?
## Ssml - Voz Otimizada
Exemplo de marcacao SSML para Amazon Polly Vitoria Neural:
<voice name=Vitoria><prosody rate=medium pitch=+2%>Ola! Eu sou a Auri.</prosody>
<break time=300ms/><prosody>Como posso te ajudar hoje?</prosody></voice>
---
## Visao Geral Da Arquitetura
Fluxo de dados: Echo -> ASK SDK (Python v2) -> Lambda Python 3.12 -> Claude claude-opus-4-20250805
Componentes AWS: DynamoDB (memoria), Polly Vitoria Neural (voz), CloudWatch (logs), Secrets Manager (keys)
### 3.1 Dependencias
ask-sdk-core==1.19.0 | ask-sdk-model==1.85.0 | boto3==1.34.0 | anthropic==0.25.0 | python-dotenv==1.0.0
### 3.2 Lambda Handler Principal
Codigo Python - lambda_function.py:
sb = CustomSkillBuilder()
sb.add_request_handler(ConversationIntentHandler())
sb.add_global_request_interceptor(MemoryLoadInterceptor())
sb.add_global_response_interceptor(MemorySaveInterceptor())
lambda_handler = sb.lambda_handler()
### 3.3 Handler De Conversa Com Claude
Codigo Python - handlers/conversation.py:
class ConversationIntentHandler(AbstractRequestHandler):
Recebe user_speech via slot query
Carrega historico de conversas da sessao DynamoDB
Chama anthropic.Anthropic().messages.create(
model=claude-opus-4-20250805, max_tokens=300,
system=system_prompt, messages=history+[user_speech])
Salva resposta no historico, retorna SSML com voz Vitoria
### 3.4 Dynamodb Schema
Tabela: auri-user-memory | PK: user_id | SK: session_date | TTL: 90 dias
Campos: profile (name, plan, preferences), long_term_memory[], usage_stats{}
BillingMode: PAY_PER_REQUEST | TimeToLive: habilitado (auto-expira)
### 3.5 Interaction Model
invocationName: auri
ConversationIntent: slot query (AMAZON.SearchQuery)
Samples: {query}, me fala sobre {query}, o que e {query}, explica {query}
StopIntent: tchau, ate mais, encerrar
### 3.6 Configuracao Lambda
FunctionName: auri-core-handler | Runtime: python3.12 | Timeout: 15s | Memory: 512MB
Env vars: ANTHROPIC_API_KEY_SECRET, DYNAMODB_TABLE=auri-user-memory, POLLY_VOICE=Vitoria
CLAUDE_MODEL=claude-opus-4-20250805, MAX_TOKENS_VOICE=300
---
### 3.7 Exemplos De Codigo Completos
Handler de Conversa (handlers/conversation.py):
DynamoDB Schema:
---
## Planos E Precos
| Plano | Preco | Limites | Target |
|-------|-------|---------|--------|
| Free | R$ 0 | 10 perguntas/dia | Experimentacao |
| Pro | R$ 29/mes | Ilimitado, memoria 90 dias | Usuario individual |
| Business | R$ 99/mes | Multi-usuario ate 5, 1 ano | Familia/PME |
| Enterprise | Sob consulta | Ilimitado, SLA | Corporativo |
## Detalhamento
Free: 10 perguntas/dia, sem memoria entre sessoes, voz Vitoria Neural.
Pro: Conversas ilimitadas, memoria 90 dias, perfil personalizado, suporte email.
Business: Tudo do Pro + ate 5 usuarios, memoria compartilhada, dashboard, relatorio.
Enterprise: Ilimitado, persona customizavel, integracao CRM/ERP, SLA 99.9%.
## Projecao De Receita (Ano 1)
Meta conservadora: Pro 250 x R\9 = R$ 7.250/mes | Business 25 x R\9 = R$ 2.475/mes
MRR Ano 1: R$ 9.725/mes (~R$ 117k ARR)
Meta otimista: Pro 800 = R$ 23.200/mes | Business 80 = R$ 7.920/mes
MRR Ano 1: R$ 31.120/mes (~R$ 373k ARR)
## Unit Economics
| Metrica | Pro | Business |
|---------|-----|----------|
| CAC | R$ 45 | R$ 120 |
| LTV | R$ 522 (18m) | R$ 2.376 (24m) |
| LTV/CAC | 11.6x | 19.8x |
| Churn | 5%/mes | 3%/mes |
| Margem bruta | ~86% | ~90% |
---
## Fase 1 - Lancamento Mvp (Meses 1-3)
Objetivo: Validar product-market fit com early adopters brasileiros.
| Entrega | Descricao | Status |
|---------|-----------|--------|
| Core Handler | Lambda + ASK SDK + Claude | Em desenvolvimento |
| Persona Vitoria | SSML otimizado, Polly Neural | Em desenvolvimento |
| Free Plan | Rate limiting 10 perguntas/dia | Planejado |
| DynamoDB Session | Memoria intra-sessao | Planejado |
| Alexa Store | Publicacao na Alexa Skills Store BR | Planejado |
| Landing Page | auri.com.br com CTA | Planejado |
KPIs Fase 1: 500 habilitacoes, 40% retornam semana 2, NPS > 50, latencia < 2s.
## Fase 2 - Personalizacao (Meses 4-6)
| Entrega | Descricao |
|---------|-----------|
| Long-term Memory | DynamoDB persistente 90 dias (Pro) |
| User Profiling | Nome, preferencias, contexto |
| Pro Plan Launch | Via Amazon In-Skill Purchasing |
| Analytics Dashboard | Usuario Pro ve padroes de uso |
KPIs Fase 2: 200 conversoes Free->Pro, WAC > 150, sessao > 4min, churn < 7%.
## Fase 3 - Multi-Modal (Meses 7-12)
| Entrega | Descricao |
|---------|-----------|
| Echo Show Support | Respostas visuais para displays |
| Calendar Integration | Agenda via voz |
| Auri Web App | Interface web para historico |
| Business Plan Launch | Multi-usuario, dashboard familiar |
KPIs Fase 3: WAC > 1.000, MRR > R$ 15.000, Business: 50 clientes, rating > 4.5.
## Fase 4 - Ecossistema (Ano 2+)
| Entrega | Descricao |
|---------|--Related in Cloud & DevOps
appbuilder-action-scaffolder
IncludedCreate, implement, deploy, and debug Adobe Runtime actions with consistent layout, validation, and error handling. Use this skill whenever the user needs to add actions to an App Builder project, understand action structure (params, response format, web/raw actions), configure actions in the manifest, use App Builder SDKs (State, Files, Events, database), deploy and invoke actions via CLI, debug action issues, or implement patterns such as webhook receivers, custom event providers, journaling consumers, large payload redirects, action sequence pipelines, and Asset Compute workers. Also trigger when users mention serverless functions in Adobe context, action logging, IMS authentication for actions, or cron-style scheduled actions.
orchestrating-datacloud
IncludedSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. Use this skill when the user needs a multi-step Data Cloud pipeline, cross-phase troubleshooting, or data space and data kit management. TRIGGER when: user needs a multi-step Data Cloud pipeline, asks to set up or troubleshoot Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase sf data360 workflow. DO NOT TRIGGER when: work is isolated to a single phase (use the matching phase-specific skill), the task is STDM/session tracing/parquet telemetry (use observing-agentforce), standard CRM SOQL (use querying-soql), or Apex implementation (use generating-apex).
github-project-automation
IncludedAutomate GitHub repository setup with CI/CD workflows, issue templates, Dependabot, and CodeQL security scanning. Includes 12 production-tested workflows and prevents 18 errors: YAML syntax, action pinning, and configuration. Use when: setting up GitHub Actions CI/CD, creating issue/PR templates, enabling Dependabot or CodeQL scanning, deploying to Cloudflare Workers, implementing matrix testing, or troubleshooting YAML indentation, action version pinning, secrets syntax, runner versions, or CodeQL configuration. Keywords: github actions, github workflow, ci/cd, issue templates, pull request templates, dependabot, codeql, security scanning, yaml syntax, github automation, repository setup, workflow templates, github actions matrix, secrets management, branch protection, codeowners, github projects, continuous integration, continuous deployment, workflow syntax error, action version pinning, runner version, github context, yaml indentation error
sf-datacloud
IncludedSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. TRIGGER when: user needs a multi-step Data Cloud pipeline, asks to set up or troubleshoot Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase `sf data360` workflow. DO NOT TRIGGER when: work is isolated to a single phase (use the matching sf-datacloud-* skill), the task is STDM/session tracing/parquet telemetry (use sf-ai-agentforce-observability), standard CRM SOQL (use sf-soql), or Apex implementation (use sf-apex).
fabric-cli
IncludedUse this skill for Fabric.so CLI workflows with the `fabric` terminal command: diagnose/install/login, search or browse a Fabric library, save notes/links/files, create folders, ask the Fabric AI assistant, manage tasks/workspaces, generate shell completion, check subscription usage, produce JSON output, and use Fabric as persistent agent memory. Do not use for Microsoft Fabric/Azure/Power BI `fab`, Daniel Miessler's Fabric framework, Python Fabric SSH, Fabric.js, or textile/fashion fabric.
lark
IncludedLark/Feishu CLI skills: lark-cli operations for docs, markdown, sheets, base, calendar, im, mail, task, okr, drive, wiki, slides, whiteboard, apps, approval, attendance, contact, vc, minutes, event. Use when the user needs to operate Lark/Feishu resources via lark-cli, send messages, manage documents, spreadsheets, calendars, tasks, OKRs, deploy web pages, or any Feishu/Lark workspace operations.