wizz-method 1.18.3 → 2.0.0

package/README.md

@@ -17,11 +17,11 @@ O ponto de entrada técnico é o `wizz-router`: ele faz a triagem e manda pedido
 | Agente | Faz | Rota para (skills globais) |
 |---|---|---|
 | 🧭 `wizz-maestro` | Lê o pedido e despacha o agente certo | todos os agentes wizz/wizz |
-| 🎨 `wizz-designer` | Design visual, landing, motion, 3D | premium-landing-ui-researcher, ui-ux-pro-max, motion-3d-director, taste-skill, ui-component-curator |
-| ✍️ `wizz-copy` | Copy, e-mail, headlines | copywriting, email-sequence, humanizer, copy-editing |
-| 🔍 `wizz-seo` | SEO tradicional e de IA | seo-audit, ai-seo, schema-markup, programmatic-seo, site-architecture |
-| 📈 `wizz-growth` | Marketing, CRO, lançamento, preço, churn | marketing-ideas, page-cro, launch-strategy, pricing-strategy, churn-prevention |
-| 📢 `wizz-ads` | Mídia paga | paid-ads, ad-creative, analytics-tracking |
+| 🎨 `wizz-designer` | Design visual, landing, motion, 3D | wizz-premium-landing-ui-researcher, wizz-ui-ux-pro-max, wizz-motion-3d-director, wizz-taste-skill, wizz-ui-component-curator |
+| ✍️ `wizz-copy` | Copy, e-mail, headlines | wizz-copywriting, wizz-email-sequence, wizz-humanizer, wizz-copy-editing |
+| 🔍 `wizz-seo` | SEO tradicional e de IA | wizz-seo-audit, wizz-ai-seo, wizz-schema-markup, wizz-programmatic-seo, wizz-site-architecture |
+| 📈 `wizz-growth` | Marketing, CRO, lançamento, preço, churn | wizz-marketing-ideas, wizz-page-cro, wizz-launch-strategy, wizz-pricing-strategy, wizz-churn-prevention |
+| 📢 `wizz-ads` | Mídia paga | wizz-paid-ads, wizz-ad-creative, wizz-analytics-tracking |
 | 🧠 `wizz-memoria` | Memória do projeto | cerebro |
 
 Os papéis de dev e produto reusam os agentes WIZZ (Mary, John, Winston, Amelia, Sally, Paige), personalizados em PT-BR pelos overrides em `src/modules/wizz/overrides/`.

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "wizz-method",
-  "version": "1.18.3",
+  "version": "2.0.0",
   "description": "Wizz Method — método de agência orientado por IA em PT-BR (fork independente do BMad Method)",
   "keywords": [
     "agile",
@@ -32,8 +32,8 @@
     "src/modules",
     "src/scripts",
     "src/skills-lib",
-    "!src/skills-lib/huashu-design/assets/**/*.mp3",
-    "!src/skills-lib/canvas-design/canvas-fonts/**/*.ttf",
+    "!src/skills-lib/wizz-huashu-design/assets/**/*.mp3",
+    "!src/skills-lib/wizz-canvas-design/canvas-fonts/**/*.ttf",
     "web-bundles",
     "skills-registry.yaml",
     "wizz-modules.yaml",

package/skills-registry.yaml

@@ -77,57 +77,57 @@ areas:
     # soltas. Nada foi fundido: todos os arquivos e references continuam intactos.
     skills:
       # ── Porta 1: DIREÇÃO (decidir antes de construir) ──
-      - id: decision-maker
+      - id: wizz-decision-maker
         entry: true
         door: direcao
-        when: "PORTA de direção: todo trabalho de decidir ANTES de construir. Brief visual inicial (6 decisões de estética + 3 lógicas) no kickoff. Puxa: taste-skill (direção anti-slop de brief novo) e motion-3d-director (decidir caminho motion/3D/vídeo)."
+        when: "PORTA de direção: todo trabalho de decidir ANTES de construir. Brief visual inicial (6 decisões de estética + 3 lógicas) no kickoff. Puxa: wizz-taste-skill (direção anti-slop de brief novo) e wizz-motion-3d-director (decidir caminho motion/3D/vídeo)."
         rel:
-          pairs_with: [taste-skill, motion-3d-director]
-      - id: taste-skill
+          pairs_with: [wizz-taste-skill, wizz-motion-3d-director]
+      - id: wizz-taste-skill
         door: direcao
         when: "Anti-slop em briefs NOVOS: lê o brief, define a direção e audita contra defaults de AI. Também cobre projeto EXISTENTE: audita o código atual, lista problemas, prioriza fixes (protocolo de redesign)."
-      - id: motion-3d-director
+      - id: wizz-motion-3d-director
         door: direcao
         when: "Direção de motion/animação, 3D, WebGL, scroll cinematográfico, image-to-video. Decide o caminho ANTES de implementar."
 
       # ── Porta 2: CONSTRUÇÃO E POLISH DE UI ──
-      - id: ui-ux-pro-max
+      - id: wizz-ui-ux-pro-max
         entry: true
         door: construcao
-        when: "PORTA de construção: criar/melhorar UI (design system, paleta, tipografia, componente, página). Puxa: premium-landing-ui-researcher (landing premium greenfield), ui-component-curator (1 componente em projeto existente), impeccable (gate de polish/acessibilidade), taste-skill (anti-slop em código existente, protocolo de redesign), huashu-design (protótipo HTML hi-fi/variantes/review) e react-components (Stitch→React)."
-      - id: premium-landing-ui-researcher
+        when: "PORTA de construção: criar/melhorar UI (design system, paleta, tipografia, componente, página). Puxa: wizz-premium-landing-ui-researcher (landing premium greenfield), wizz-ui-component-curator (1 componente em projeto existente), wizz-impeccable (gate de polish/acessibilidade), wizz-taste-skill (anti-slop em código existente, protocolo de redesign), wizz-huashu-design (protótipo HTML hi-fi/variantes/review) e wizz-react-components (Stitch→React)."
+      - id: wizz-premium-landing-ui-researcher
         door: construcao
         when: "Projeto NOVO (greenfield): cria landing premium do zero, hero, 3D high-end. Estratégia source-first."
-      - id: ui-component-curator
+      - id: wizz-ui-component-curator
         door: construcao
         when: "Projeto EXISTENTE: qual componente/efeito adicionar que combina com o estilo atual."
-      - id: impeccable
+      - id: wizz-impeccable
         door: construcao
         when: "Gate de polish/qualidade de frontend: hardening de UI, acessibilidade, anti-padrões. Refina o que já existe."
-      - id: huashu-design
+      - id: wizz-huashu-design
         door: construcao
         when: "Direção visual + protótipo HTML hi-fi, exploração de variantes, review 5-dim, export MP4/GIF."
-      - id: react-components
+      - id: wizz-react-components
         door: construcao
         when: "Converter design (Stitch MCP) em componentes React/Vite."
 
       # ── Porta 3: MOTION E ASSETS (executar animação e gerar mídia) ──
-      - id: animate
+      - id: wizz-animate
         entry: true
         door: motion
-        when: "PORTA de motion/assets: executar animação e gerar mídia. Craft de micro-interação (regras do Emil Kowalski: saída > entrada, só transform/opacity, reduced-motion). Puxa: design-motion-principles (auditar animação existente), remotion-best-practices (vídeo em React), canvas-design (PNG/PDF por código) e algorithmic-art (visual generativo)."
-      - id: design-motion-principles
+        when: "PORTA de motion/assets: executar animação e gerar mídia. Craft de micro-interação (regras do Emil Kowalski: saída > entrada, só transform/opacity, reduced-motion). Puxa: wizz-design-motion-principles (auditar animação existente), wizz-remotion-best-practices (vídeo em React), wizz-canvas-design (PNG/PDF por código) e wizz-algorithmic-art (visual generativo)."
+      - id: wizz-design-motion-principles
         door: motion
         when: "Auditor de movimento: revisa animação existente e aponta scale(0) no início, easing cru, reduced-motion faltando; pesa contenção/polimento/diversão pelo contexto."
-      - id: remotion-best-practices
+      - id: wizz-remotion-best-practices
         door: motion
         when: "MONTAR o filme: vídeo em React (Remotion) com áudio, SFX, legenda e timing com precisão de frame. No pipeline de vídeo é o Remotion que faz a montagem final; o hyperframes só desenha as telas mudas (regra: HyperFrames desenha, Remotion monta — ver _shared/video-pipeline.md do módulo wizz)."
         rel:
           after: [hyperframes]
-      - id: canvas-design
+      - id: wizz-canvas-design
         door: motion
         when: "Gerar PNG/PDF editável por código (carrossel, quote card, infográfico) com fonte/cor/logo sempre certos. Traz canvas-fonts."
-      - id: algorithmic-art
+      - id: wizz-algorithmic-art
         door: motion
         when: "Visual generativo por código (flow fields, ruído, partículas) para fundo/textura de hero, único a cada render, sem cara de banco de imagem."
       - id: ctc-align
@@ -138,7 +138,7 @@ areas:
         when: "DESENHAR telas de vídeo em HTML/CSS (HTML→MP4, agent-native, 20+ skills): cena isolada e MUDA — maqueta de WhatsApp/ChatGPT, gráfico animado, título, loop. NÃO usar para montagem com áudio/SFX/legenda sincronizada (posicionador de áudio falhou em produção, ~2,76s de drift; CSS vaza entre telas): a montagem final é do Remotion (regra: HyperFrames desenha, Remotion monta — ver _shared/video-pipeline.md do módulo wizz). Precisa ffmpeg + Node 22 + Chrome headless."
         not_when: "Montagem com áudio/SFX/legenda sincronizada (posicionador de áudio falhou em produção, ~2,76s de drift; CSS vaza entre telas)."
         rel:
-          before: [remotion-best-practices]
+          before: [wizz-remotion-best-practices]
         platform: [darwin, linux]
         # O check confere o SHA fixado, não só a existência da pasta: o bundle é
         # copiado (não clonado), então o pin é gravado num marcador no install.
@@ -194,32 +194,32 @@ areas:
     agent: wizz-copy
     summary: "Copywriting: texto de venda, headlines, páginas, e-mails, sequências."
     skills:
-      - id: copywriting
+      - id: wizz-copywriting
         when: "Escrever copy de venda/página/headline do zero ou reescrever."
-      - id: copy-editing
+      - id: wizz-copy-editing
         when: "Editar/melhorar copy existente (framework Seven Sweeps). Review editorial geral."
-      - id: humanizer
+      - id: wizz-humanizer
         when: "Texto soa AI: remover padrões de escrita de máquina, dar naturalidade."
-      - id: email-sequence
+      - id: wizz-email-sequence
         when: "Sequências de e-mail (onboarding, nurture, lançamento)."
-      - id: cold-email
+      - id: wizz-cold-email
         when: "Cold email / outbound B2B / prospecção."
-      - id: sales-enablement
+      - id: wizz-sales-enablement
         when: "Material de vendas: deck, one-pager, objeções, demo script, playbook."
 
   seo:
     agent: wizz-seo
     summary: "SEO: auditoria, busca, AI search, schema, SEO programático."
     skills:
-      - id: seo-audit
+      - id: wizz-seo-audit
         when: "Ponto de partida: auditar/diagnosticar SEO, queda de tráfego, ranking, core web vitals."
-      - id: ai-seo
+      - id: wizz-ai-seo
         when: "Otimizar pra ser citado por LLMs/AI search (AEO/GEO/LLMO, AI Overviews)."
-      - id: schema-markup
+      - id: wizz-schema-markup
         when: "Implementar dados estruturados / structured data."
-      - id: programmatic-seo
+      - id: wizz-programmatic-seo
         when: "Gerar páginas em escala pra atacar muitas keywords."
-      - id: site-architecture
+      - id: wizz-site-architecture
         when: "Arquitetura de site / topic clusters / estrutura de URLs."
     clis:
       - id: distribb
@@ -235,41 +235,41 @@ areas:
     agent: wizz-growth
     summary: "Growth e conversão: marketing, CRO, lançamento, preço, retenção."
     skills:
-      - id: marketing-ideas
+      - id: wizz-marketing-ideas
         when: "Travou / quer inspiração ampla de marketing. Ponto de partida quando não sabe o canal."
-      - id: marketing-psychology
+      - id: wizz-marketing-psychology
         when: "Aplicar gatilhos/vieses/modelos mentais à persuasão."
-      - id: product-marketing-context
+      - id: wizz-product-marketing-context
         when: "Posicionamento de produto e contexto de marketing do produto."
-      - id: launch-strategy
+      - id: wizz-launch-strategy
         when: "Lançar produto/feature: Product Hunt, GTM, waitlist, beta."
-      - id: pricing-strategy
+      - id: wizz-pricing-strategy
         when: "Preço, planos, freemium, packaging, willingness to pay."
-      - id: paywall-upgrade-cro
+      - id: wizz-paywall-upgrade-cro
         when: "Tela de upgrade in-app / paywall."
-      - id: churn-prevention
+      - id: wizz-churn-prevention
         when: "Churn, retenção, cancelamento, NPS."
-      - id: revops
+      - id: wizz-revops
         when: "Operações de receita: pipeline, métricas, processo de revenue."
-      - id: page-cro
+      - id: wizz-page-cro
         when: "Otimizar conversão de página (home, landing, pricing, feature)."
-      - id: form-cro
+      - id: wizz-form-cro
         when: "Otimizar formulários (fora de signup)."
-      - id: popup-cro
+      - id: wizz-popup-cro
         when: "Otimizar popups/modais."
-      - id: onboarding-cro
+      - id: wizz-onboarding-cro
         when: "Ativação pós-signup / onboarding de usuário."
-      - id: signup-flow-cro
+      - id: wizz-signup-flow-cro
         when: "Fluxo de signup/registro."
-      - id: competitor-alternatives
+      - id: wizz-competitor-alternatives
         when: "Página de comparação vs concorrente / alternatives / battle card."
-      - id: referral-program
+      - id: wizz-referral-program
         when: "Programa de indicação/afiliados."
-      - id: free-tool-strategy
+      - id: wizz-free-tool-strategy
         when: "Ferramenta grátis pra captação de leads."
-      - id: ab-test-setup
+      - id: wizz-ab-test-setup
         when: "Montar A/B test / experimento de conversão."
-      - id: analytics-tracking
+      - id: wizz-analytics-tracking
         when: "Setar/auditar tracking e medição (GA4, GTM, eventos, UTM, atribuição)."
       - id: site-launch-kit
         when: "Site pronto ou quase pronto pra ir ao ar: revisão de pré-lançamento em 15 rodadas corretivas (CTA acima da dobra, barra fixa mobile, tempo de resposta, prova social real, FAQ+FAQPage, imagens reais, endereço, titles, Open Graph, breadcrumbs, alt text, schema local, robots/sitemap, LGPD, medição), com regra anti-invenção e PENDÊNCIAS. Gatilhos: 'vamos subir o site', 'checklist de lançamento', 'revisa antes do deploy', pré-go-live, ou um item isolado (og:image, FAQ com schema, robots.txt). Roda DEPOIS do site construído, ANTES do deploy."
@@ -280,7 +280,7 @@ areas:
       # Módulo lowticket (src/modules/lowticket) — ver nota em ads.skills.
       - id: lowticket-metodologia
         module: lowticket
-        when: "Roteador da base low ticket BR/PT: gatilho → um shard. Régua de preço, garantia e oferta que tem precedência sobre a skill genérica."
+        when: "Roteador da base low ticket BR/PT: gatilho → um shard. Régua de preço, garantia, copy e rastreamento que tem precedência sobre a skill genérica."
         not_when:
           - "SaaS, B2B, site de cliente, high ticket ou mentoria: os números não transferem."
       - id: lowticket-funil
@@ -316,37 +316,37 @@ areas:
     agent: wizz-social
     summary: "Social e roteiros virais: Reels/Shorts, hooks, calendário de conteúdo. Persona Rafa, aplica o Blueprint de Roteiro Viral e roteia para as CLIs de vídeo quando o roteiro vira vídeo."
     skills:
-      - id: social-content
+      - id: wizz-social-content
         when: "Criar/agendar conteúdo de social (LinkedIn, X, TikTok, IG...)."
-      - id: content-strategy
+      - id: wizz-content-strategy
         when: "Decidir O QUE produzir de conteúdo (topic clusters, calendário, pilares)."
-      - id: copy-editing
+      - id: wizz-copy-editing
         when: "Revisar/editar o texto do roteiro ou da legenda antes de publicar."
 
   ads:
     agent: wizz-ads
     summary: "Mídia paga: campanhas Google/Meta/TikTok/LinkedIn, criativos, tracking."
     skills:
-      - id: paid-ads
+      - id: wizz-paid-ads
         when: "Estratégia de campanha, targeting, bidding, ROAS/CPA. Decidir/rodar ads."
-      - id: ad-creative
+      - id: wizz-ad-creative
         when: "Gerar/iterar criativos e headlines de anúncio em escala (RSA, variações)."
-      - id: analytics-tracking
+      - id: wizz-analytics-tracking
         when: "Tracking de conversão pros anúncios (compartilhada com growth)."
-      - id: tracking-audit
+      - id: wizz-tracking-audit
         when: "Auditar rastreamento de oferta de resposta direta. Modo implantação: pixel, CAPI, domínio verificado, eventos priorizados, UTM com ID, repasse do parâmetro nativo pelo checkout, higiene de nomenclatura, compra-teste por rota. Modo diagnóstico: qual transição do funil está furando, medição contra conversão, ROI verdadeiro contra falso, qual dado falta pra decidir."
         not_when:
           - "Plano de medição de SaaS ou produto instrumentado por evento de uso: é analytics-tracking."
           - "Decidir bid, orçamento ou estrutura de campanha: é paid-ads."
         rel:
-          pairs_with: [analytics-tracking, paid-ads]
-          before: [page-cro]
+          pairs_with: [wizz-analytics-tracking, wizz-paid-ads]
+          before: [wizz-page-cro]
       # Módulo lowticket (src/modules/lowticket) — instaladas COM O MÓDULO, não
       # por skills-lib. O campo `module` é o gate: resolveSkillIds as ignora ao
       # copiar de src/skills-lib, e o router continua enxergando as entradas.
       - id: lowticket-metodologia
         module: lowticket
-        when: "Roteador da base low ticket BR/PT: gatilho → um shard (diagnóstico de funil, bid cap, criativo, oferta, página, Instagram, upsell, mineração). Carrega guardrails junto."
+        when: "Roteador da base low ticket BR/PT: gatilho → um shard (diagnóstico de funil, bid cap, criativo, oferta, página, Instagram, player de VSL, upsell, copy, rastreamento, mineração). Carrega guardrails junto."
         not_when:
           - "SaaS, B2B, site de cliente, high ticket ou mentoria: os números não transferem."
       - id: lowticket-trafego
@@ -360,25 +360,25 @@ areas:
     agent: wizz-agent-architect
     summary: "Arquitetura, banco, segurança, infra, decisões técnicas."
     skills:
-      - id: web-security
+      - id: wizz-web-security
         when: "Auditar segurança web, OWASP, XSS/CSRF/injeção/SQLi, IDOR, headers, rate limit (IP+conta), CORS, clickjacking, vazamento de PII na resposta, antes de deploy/PR."
-      - id: auth-and-secrets
+      - id: wizz-auth-and-secrets
         when: "Auth (JWT/OAuth/SSO/Clerk), token no header vs URL, revogar no logout, enumeração de usuário, gestão de secrets, rotação de credenciais."
-      - id: desktop-security
+      - id: wizz-desktop-security
         when: "Segurança desktop/Electron (contextIsolation, code signing)."
-      - id: database-scaling
+      - id: wizz-database-scaling
         when: "Banco lento, queries, índices, N+1, sharding, connection pool."
-      - id: caching-and-queues
+      - id: wizz-caching-and-queues
         when: "Cache (Redis), filas (BullMQ/SQS/Kafka), jobs assíncronos."
-      - id: infrastructure
+      - id: wizz-infrastructure
         when: "Escala de infra: Kubernetes, auto-scaling, CDN, SLOs, load test."
-      - id: cloud-and-infra
+      - id: wizz-cloud-and-infra
         when: "Custo de cloud: right-sizing, spot/reserved, S3 lifecycle, billing AWS/GCP."
-      - id: database-and-deps
+      - id: wizz-database-and-deps
         when: "Dependências/packages, vulnerabilidades, npm audit."
-      - id: supabase-postgres-best-practices
+      - id: wizz-supabase-postgres-best-practices
         when: "Performance e boas práticas de Postgres/Supabase (queries, schema, RLS)."
-      - id: ai-product-design
+      - id: wizz-ai-product-design
         when: "Construir/melhorar um agente ou produto de IA: escrever/revisar system prompt, definir persona/tom, guardrails e recusas, few-shot, chain-of-thought, orquestração multi-agente, handoff, detecção de frustração, generative UI, avaliar qualidade de saída. Base para desenhar os próprios agentes do método. 44 padrões (Owl-Listener, MIT)."
     mcps:
       - id: supabase
@@ -403,19 +403,19 @@ areas:
     agent: wizz-qa
     summary: "QA: verificar o código de fora (testes, E2E, review adversarial)."
     skills:
-      - id: adversarial-reviewer
+      - id: wizz-adversarial-reviewer
         when: "Passe único adversarial, ad hoc, fora de workflow — 'tear this apart' num trecho colado, sem contexto de projeto. Não confundir com wizz-review-adversarial-general (camada interna 'Blind Hunter' chamada só por wizz-code-review) nem com wizz-code-review (orquestrador bmm: 3 camadas paralelas + triagem, para review real de diff/PR)."
       - id: security-audit-pentest
         when: "Auditoria/pentest de segurança do app inteiro — 'auditar segurança', 'pentest', 'encontrar vulnerabilidades', varredura antes de release. Só para teste de segurança AUTORIZADO (seus sistemas ou de clientes com permissão): ferramenta dual-use, nunca usar contra alvo sem autorização."
-      - id: launch-readiness
+      - id: wizz-launch-readiness
         when: "Auditoria de prontidão pra lançamento (Pre-launch Audit), multi-área: técnico/build, segurança, SEO/descoberta, analytics/medição, conteúdo/copy/prova social, legal/LGPD, infra/deploy/rollback. Gatilhos: 'tá pronto pra lançar?', 'auditoria de pré-lançamento', 'checklist de release amplo', 'o que falta antes de ir pra produção'. Gate por estágio: só roda de verdade em mvp/production, e recusa educadamente em estágio de descoberta/ideação. Diagnostica e prioriza por severidade (bloqueia/alto/médio/ok), nunca corrige cego: aponta security-audit-pentest pra aprofundar segurança com prova de exploração e site-launch-kit pra executar a correção quando a superfície do achado é site. Resultado persiste numa seção datada do project-context.md."
         not_when:
           - "Estágio de descoberta/ideação: projeto ainda sem superfície construída pra auditar (sem project-context.md, ou stage 'prototype' vazio)."
           - "Correção de um achado isolado de site já identificado: nesse caso vá direto pra site-launch-kit."
         rel:
           pairs_with: [site-launch-kit, security-audit-pentest]
-      - id: agent-browser
-        when: "Verificação visual/browser, preencher forms, screenshots, testar UI no navegador. CLI já instalado (não é MCP); browser SEMPRE via agent-browser, nunca Playwright."
+      - id: wizz-agent-browser
+        when: "Verificação visual/browser, preencher forms, screenshots, testar UI no navegador. CLI já instalado (não é MCP); browser SEMPRE via wizz-agent-browser, nunca Playwright."
     clis:
       - id: agent-browser
         when: "Dirigir um browser real pra E2E/verificação: navegar, clicar, preencher form, screenshot, console. É CLI, não MCP."
@@ -439,9 +439,9 @@ areas:
     agent: wizz-agent-analyst
     summary: "Análise, pesquisa, brief, kickoff de projeto."
     skills:
-      - id: inicio-de-projeto
+      - id: wizz-inicio-de-projeto
         when: "Kickoff LEVE de engenharia: stack, personas, glossário, princípios, estrutura de pastas, checklist. Atalho sem cerimônia de PRD."
-      - id: implementation-planner
+      - id: wizz-implementation-planner
         when: "Plano técnico de implementação de site/app premium pós-direção aprovada. Pesquisa web/prior-art durante o planejamento usa a tool nativa WebSearch (sem custo/MCP metered — o MCP exa foi removido em 2026-08-25)."
 
   memoria:

package/src/bmm-skills/4-implementation/wizz-code-review/SKILL.md

@@ -5,7 +5,7 @@ description: 'Review code changes adversarially using parallel review layers (Bl
 
 # Code Review Workflow
 
-> **Cross-reference:** this is the orchestrator. It gathers context, runs the review layers declared in `customize.toml` (Blind Hunter, Edge Case Hunter, Verification Gap Reviewer, Acceptance Auditor) as parallel context-free subagents driven by the prompt files under `review-prompts/`, then verifies, triages and presents findings by severity. Use it for a real diff/PR review. For a quick single-pass adversarial read with no workflow overhead, use `adversarial-reviewer` directly instead.
+> **Cross-reference:** this is the orchestrator. It gathers context, runs the review layers declared in `customize.toml` (Blind Hunter, Edge Case Hunter, Verification Gap Reviewer, Acceptance Auditor) as parallel context-free subagents driven by the prompt files under `review-prompts/`, then verifies, triages and presents findings by severity. Use it for a real diff/PR review. For a quick single-pass adversarial read with no workflow overhead, use `wizz-adversarial-reviewer` directly instead.
 
 **Goal:** Review code changes adversarially. No noise, no filler.
 

package/src/bmm-skills/4-implementation/wizz-code-review/customize.toml

@@ -51,7 +51,7 @@ on_complete = ""
 id = "blind-hunter"
 name = "Blind Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Conduct a review of CONTENT.
 Look for what's missing, not only what's wrong.
@@ -70,7 +70,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "edge-case-hunter"
 name = "Edge Case Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/edge-case-hunter.md` completely and follow it as your review instructions.
 
@@ -86,7 +86,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "verification-gap"
 name = "Verification Gap Reviewer"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/verification-gap.md` completely and follow it as your review instructions.
 
@@ -101,7 +101,7 @@ id = "acceptance-auditor"
 name = "Acceptance Auditor"
 when = 'Only when {review_mode} = "full".'
 instruction = """
-Launch a subagent with this prompt:
+Launch a `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 You are an Acceptance Auditor. Review the provided diff against `{spec_file}` and any loaded context docs. Check for: violations of acceptance criteria, deviations from spec intent, missing implementation of specified behavior, contradictions between spec constraints and actual code. Output findings as a Markdown list. Each finding: one-line title, which AC/constraint it violates, and evidence from the diff.
 

package/src/bmm-skills/4-implementation/wizz-code-review/steps/step-02-review.md

@@ -7,7 +7,7 @@ failed_layers: '' # set at runtime: comma-separated list of layers that failed o
 ## RULES
 
 - YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
-- All review subagents must run at the same model capability as the current session.
+- Review subagents run pinned to the platform's Forte tier via `wizz-exec-review` (`opus` in Claude Code) — never at the same model capability as the current session. See `_shared/model-ladder.md`.
 - Run subagents synchronously: launch them together as blocking calls awaited in this turn — never backgrounded or detached, never ending the turn to await results.
 
 ## INSTRUCTIONS

package/src/bmm-skills/4-implementation/wizz-quick-dev/customize.toml

@@ -49,7 +49,7 @@ on_complete = ""
 id = "blind-hunter"
 name = "Blind Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Conduct a review of CONTENT.
 Look for what's missing, not only what's wrong.
@@ -68,7 +68,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "edge-case-hunter"
 name = "Edge Case Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/edge-case-hunter.md` completely and follow it as your review instructions.
 
@@ -84,7 +84,7 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 id = "verification-gap"
 name = "Verification Gap Reviewer"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Read `{skill-root}/review-prompts/verification-gap.md` completely and follow it as your review instructions.
 
@@ -94,13 +94,20 @@ Do not invoke any skill, and do not spawn subagents of your own — you are the
 
 """
 
-# Review layers for the one-shot route.
+# Review layers for the one-shot route. Consumed by step-oneshot.md, the same way
+# step-04-review.md consumes review_layers above.
+#
+# Duplicacao conhecida (2026-09-10): o prompt do Blind Hunter existe em tres copias
+# (aqui, no review_layers acima e no customize.toml do wizz-code-review) e ainda numa
+# quarta, a skill core wizz-review-adversarial-general, que hoje nenhum workflow
+# invoca. Unificar isso num review-prompts/blind-hunter.md, como ja e feito com
+# edge-case-hunter e verification-gap, e decisao em aberto.
 
 [[workflow.oneshot_review_layers]]
 id = "blind-hunter"
 name = "Blind Hunter"
 instruction = """
-Launch a context-free subagent with this prompt:
+Launch a context-free `wizz-exec-review` subagent with this prompt — pinned to the platform's Forte tier (`opus` in Claude Code), never inheriting the session model. Tell the user the tier and count of this dispatch.
 
 Conduct a review of CONTENT.
 Look for what's missing, not only what's wrong.

package/src/bmm-skills/4-implementation/wizz-quick-dev/step-04-review.md

@@ -10,7 +10,7 @@ claims_file: '' # set at runtime: path to the change's own narrative
 
 - YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`. Write any file output in `{document_output_language}`.
 - Review subagents get NO conversation context.
-- All review subagents must run at the same model capability as the current session.
+- Review subagents run pinned to the platform's Forte tier via `wizz-exec-review` (`opus` in Claude Code) — never at the same model capability as the current session. See `_shared/model-ladder.md`.
 - Run subagents synchronously: launch them together, then wait for all results before continuing. Never backgrounded or detached, never ending the turn to await results.
 
 ## INSTRUCTIONS

package/src/bmm-skills/4-implementation/wizz-quick-dev/step-oneshot.md

@@ -19,7 +19,18 @@ Implement the clarified intent directly.
 
 ### Review
 
-Invoke the `wizz-review-adversarial-general` skill in a subagent with the changed files. The subagent gets NO conversation context — to avoid anchoring bias. Launch at the same model capability as the current session. If no sub-agents are available, write the changed files to a review prompt file in `{implementation_artifacts}` and HALT. Ask the human to run the review in a separate session and paste back the findings.
+1. The review layers are `{workflow.oneshot_review_layers}`, resolved during activation. For each layer:
+   - `instruction` empty or missing → drop the layer silently (an override disabled it).
+   - `when` condition present and not satisfied by the current context → drop the layer and tell the user.
+   - otherwise → the layer is active.
+
+   If no layer is active, HALT and escalate to the human.
+
+2. Announce skipped layers first, then launch every active layer before handling any layer's result. Expand `{skill-root}` in each layer's `instruction` to this skill's absolute installed directory — the child's working directory is not yours, so never leave it unresolved in a child prompt. Reviewers get NO conversation context, to avoid anchoring bias: they inspect the changed files in the worktree themselves. When an instruction launches a reviewer subagent, launch that child with the prompt text after expansion; for any other customized instruction, execute it as written. Spawn every reviewer before reading any of their output.
+
+3. If a layer's instruction requires subagents and none are available, write that layer's child prompt under `{implementation_artifacts}`, with every file it points to replaced inline by that file's contents and every other line left exactly as written — that session shares no filesystem with this one, so its prompt has to stand alone. Then HALT. Ask the human to run it in a separate session and paste back the findings.
+
+4. If any layer fails, times out, or returns empty, note it and proceed with the remaining layers. Collect all findings.
 
 ### Classify
 

package/src/core-skills/wizz-editorial-review-prose/SKILL.md

@@ -7,7 +7,7 @@ description: 'Clinical copy-editor that reviews text for communication issues. U
 
 **Goal:** Review text for communication issues that impede comprehension and output suggested fixes in a three-column table.
 
-**Architecture note (delegating bridge):** This skill is a thin bridge. The substantive review logic lives in the global `copy-editing` skill (Seven Sweeps framework — more rigorous than a linear pass) and, when the text reads as AI-generated, the `humanizer` skill. This bridge keeps a stable name/contract because BMM workflows (`wizz-prd`, `wizz-ux`, `wizz-architecture`, `wizz-product-brief`) invoke `wizz-editorial-review-prose` by name. It always returns the same three-column table so those workflows are unaffected.
+**Architecture note (delegating bridge):** This skill is a thin bridge. The substantive review logic lives in the global `wizz-copy-editing` skill (Seven Sweeps framework — more rigorous than a linear pass) and, when the text reads as AI-generated, the `wizz-humanizer` skill. This bridge keeps a stable name/contract because BMM workflows (`wizz-prd`, `wizz-ux`, `wizz-architecture`, `wizz-product-brief`) invoke `wizz-editorial-review-prose` by name. It always returns the same three-column table so those workflows are unaffected.
 
 **Your Role:** Clinical copy-editor: precise, professional, neither warm nor cynical. Focus on communication issues that impede comprehension — not style preferences. NEVER rewrite for preference — only fix genuine issues.
 
@@ -26,16 +26,16 @@ description: 'Clinical copy-editor that reviews text for communication issues. U
 - Identify content type; note code blocks, frontmatter, and structural markup to skip (never edit these).
 
 ### Step 2: Delegate the review
-Invoke the global `copy-editing` skill via the `Skill` tool, passing:
+Invoke the global `wizz-copy-editing` skill via the `Skill` tool, passing:
 - the `content` (prose sections only — code/markup excluded),
 - the `style_guide` if provided (instruct that it is the final authority, except CONTENT IS SACROSANCT),
 - the `reader_type` framing: if `llm`, prioritize unambiguous references, consistent terminology, explicit structure, no hedging; if `humans`, prioritize clarity, flow, readability.
 
-Instruct `copy-editing` to operate in **comprehension-only mode**: minimal intervention, fix prose within existing structure (never restructure), preserve author voice, flag uncertain fixes as a query rather than a definitive change, and NEVER alter what ideas say.
+Instruct `wizz-copy-editing` to operate in **comprehension-only mode**: minimal intervention, fix prose within existing structure (never restructure), preserve author voice, flag uncertain fixes as a query rather than a definitive change, and NEVER alter what ideas say.
 
-**If `reader_type` is `humans`** and the text shows signs of AI-generated writing (inflated symbolism, rule-of-three padding, em-dash overuse, vague attributions, negative parallelisms): also invoke `humanizer` on the affected passages and fold its fixes in.
+**If `reader_type` is `humans`** and the text shows signs of AI-generated writing (inflated symbolism, rule-of-three padding, em-dash overuse, vague attributions, negative parallelisms): also invoke `wizz-humanizer` on the affected passages and fold its fixes in.
 
-**Fallback (skill unavailable):** If `copy-editing` is not installed/resolvable, perform the review inline using these principles — minimal intervention, preserve structure, skip code/markup, query when uncertain, deduplicate identical issues into one entry with all locations listed, merge overlapping fixes, respect author voice — applying Microsoft Writing Style Guide as the baseline.
+**Fallback (skill unavailable):** If `wizz-copy-editing` is not installed/resolvable, perform the review inline using these principles — minimal intervention, preserve structure, skip code/markup, query when uncertain, deduplicate identical issues into one entry with all locations listed, merge overlapping fixes, respect author voice — applying Microsoft Writing Style Guide as the baseline.
 
 ### Step 3: Normalize and output
 Map every confirmed fix into the canonical three-column table. Deduplicate (same issue in multiple places = one entry listing all locations) and merge overlapping fixes before output.

package/src/core-skills/wizz-review-adversarial-general/SKILL.md

@@ -5,7 +5,9 @@ description: 'Perform a Cynical Review and produce a findings report. Use when t
 
 # Adversarial Review (General)
 
-> **Cross-reference:** this is the internal "Blind Hunter" layer that `wizz-code-review` invokes as one of three parallel reviewers (diff only, no project context, no triage). It is not meant to be invoked standalone by a user. For an ad hoc adversarial pass outside a bmm workflow, use the `adversarial-reviewer` skill directly; for the full triaged multi-layer review of a real diff, run `wizz-code-review`.
+> **Cross-reference:** this is the "Blind Hunter" review lens (diff only, no project context, no triage). It is not meant to be invoked standalone by a user. For an ad hoc adversarial pass outside a bmm workflow, use the `wizz-adversarial-reviewer` skill directly; for the full triaged multi-layer review of a real diff, run `wizz-code-review`.
+>
+> **No workflow currently invokes this skill.** `wizz-code-review` and `wizz-quick-dev` both carry the Blind Hunter prompt inline in their `customize.toml` review layers, so this file is a third copy of the same lens rather than its single source. Reconnecting the layers to it, or retiring it, is an open decision — see the note in `wizz-quick-dev/customize.toml`.
 
 **Goal:** Cynically review content and produce findings.
 

package/src/modules/lowticket/README.md

@@ -18,7 +18,7 @@ All five read the Cérebro on activation and **none of them keeps its own memory
 
 ## The loading contract
 
-The knowledge base is 20 shards. It is not loaded whole. Reading everything costs around 36k tokens; a typical answer needs under 5k.
+The knowledge base is 25 shards. It is not loaded whole. Reading everything costs well over 40k tokens; a typical answer needs under 5k.
 
 | Step | Read | When |
 |---|---|---|
@@ -38,7 +38,7 @@ The knowledge here is a distillation: facts, benchmarks, checklists and critical
 
 If you extend a shard, keep it that way: write the fact, never the quote. `knowledge/15-como-estender.md` has the full process.
 
-Three tactics present in the source material are recorded and **not adopted** in `knowledge/guardrails.md`: buying engagement, AI avatars passing as real people, and synthetic testimonials. They are loaded on every activation and stay blocked until the operation's owner decides otherwise.
+Seven tactics present in the source material are recorded and **not adopted** in `knowledge/guardrails.md`: buying engagement, AI avatars passing as real people, synthetic testimonials, borrowing a third party's ID document to verify a profile, using a real person's name as borrowed proof, reposting someone else's video as your own creative, and a struck-through reference price that was never charged. They are loaded on every activation and stay blocked until the operation's owner decides otherwise.
 
 ## Optional config
 

package/src/modules/lowticket/module.yaml

@@ -1,6 +1,6 @@
 code: lowticket
 name: "Wizz Low Ticket"
-description: "Low ticket direct-response playbook for Meta Ads (BR/PT): funnel diagnosis, bid-cap campaigns, creatives, sales pages, upsell ladders and offer mining. Knowledge base in Portuguese, loaded one shard at a time."
+description: "Low ticket direct-response playbook for Meta Ads (BR/PT): funnel diagnosis, bid-cap campaigns, creatives, offers, sales pages, VSL players, upsell ladders, copy diagnosis, tracking setup and offer mining. Knowledge base in Portuguese, loaded one shard at a time."
 default_selected: false
 
 # --- Origin note (read this before editing the knowledge base) ---

package/src/modules/lowticket/skills/lowticket-funil/SKILL.md

@@ -17,7 +17,7 @@ Every offer in the ladder exists because it answers that question for the step b
 
 ## Source of truth
 
-Read the Cérebro state first (via the `cerebro` skill). Then, if `lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md` and the shard `07-funil-upsell.md`, especially §7.4 (the conversion and ticket cascade). Where a generic skill contradicts that shard, the shard wins and you say so.
+Read the Cérebro state first (via the `cerebro` skill). Then, if `lowticket-metodologia` is installed, read `knowledge/INDEX.md` + `knowledge/guardrails.md` and the shard `07-funil-upsell.md`, especially §7.4 (the conversion and ticket cascade) and §7.5-7.9 (pain per step, tone per page, copy rules, the technical block for post-checkout pages and the pre-build checklist). Its sibling shard `07a-copy-humanizacao.md` carries the humanization checklist used before delivering any page. Where a generic skill contradicts that shard, the shard wins and you say so.
 
 This skill has **no memory of its own**. What gets decided goes to the Cérebro; the artifact goes to a file.
 
@@ -92,7 +92,7 @@ If asked for five or more paid steps, say the recommendation is to consolidate.
 
 ### Numbers, only when asked
 
-Treat these as reference, never as a promise: U1 15-25%, U2 20-35% among U1 buyers, downsell 20-35%, final offer 18-28%, total ticket around 1.5x to 2.3x the front. The canonical version is §7.4 of shard `07`.
+Treat these as reference, never as a promise: U1 15-25%, U2 20-35% among U1 buyers, downsell 20-35%, final offer 18-28%, total ticket around 1.5x to 2.3x the front. The canonical version is §7.4 of shard `07`, which also names the likely cause when a step lands below its floor (for example, U1 under 10% points to wrong pain or wrong price) — use that instead of guessing.
 
 ## Hard limits on the copy
 
@@ -105,7 +105,7 @@ Treat these as reference, never as a promise: U1 15-25%, U2 20-35% among U1 buye
 
 Portuguese (BR), spoken register, short sentences, no em-dashes. Concrete scenes instead of abstract emotion: not "você se sente inseguro", but "você abre o computador às 9h e às 11h ainda está tentando descobrir por onde começar". Repeat the product's name instead of cycling through synonyms.
 
-The full anti-AI word list and the rhythm rules are in `references/copy-das-paginas.md`. For a deeper pass, hand the draft to the `humanizer` skill.
+The full anti-AI word list and the rhythm rules are in `references/copy-das-paginas.md`. Before delivering, run the 10-filter checklist in `07a-copy-humanizacao.md` (sibling shard of `07-funil-upsell.md`): fail 3 or more, rewrite.
 
 ## Out of scope