wizz-method 2.1.1 → 2.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (212) hide show
  1. package/README.md +62 -62
  2. package/SECURITY.md +15 -16
  3. package/THIRD-PARTY-NOTICES.md +49 -49
  4. package/package.json +1 -1
  5. package/src/bmm-skills/1-analysis/wizz-agent-analyst/customize.toml +1 -1
  6. package/src/bmm-skills/2-plan-workflows/wizz-agent-pm/customize.toml +1 -1
  7. package/src/bmm-skills/2-plan-workflows/wizz-agent-ux-designer/customize.toml +1 -1
  8. package/src/bmm-skills/3-solutioning/wizz-agent-architect/customize.toml +1 -1
  9. package/src/bmm-skills/4-implementation/wizz-agent-dev/customize.toml +1 -1
  10. package/src/bmm-skills/4-implementation/wizz-code-review/SKILL.md +2 -2
  11. package/src/bmm-skills/4-implementation/wizz-code-review/customize.toml +102 -8
  12. package/src/bmm-skills/4-implementation/wizz-code-review/references/review-economy.md +75 -0
  13. package/src/bmm-skills/4-implementation/wizz-code-review/steps/step-01-gather-context.md +29 -15
  14. package/src/bmm-skills/4-implementation/wizz-code-review/steps/step-02-review.md +13 -10
  15. package/src/bmm-skills/4-implementation/wizz-code-review/steps/step-03-triage.md +11 -5
  16. package/src/bmm-skills/4-implementation/wizz-code-review/steps/step-04-present.md +4 -0
  17. package/src/bmm-skills/4-implementation/wizz-quick-dev/customize.toml +103 -7
  18. package/src/bmm-skills/4-implementation/wizz-quick-dev/references/review-economy.md +75 -0
  19. package/src/bmm-skills/4-implementation/wizz-quick-dev/step-04-review.md +43 -18
  20. package/src/bmm-skills/4-implementation/wizz-quick-dev/step-05-present.md +4 -0
  21. package/src/bmm-skills/4-implementation/wizz-quick-dev/step-oneshot.md +2 -2
  22. package/src/core-skills/_shared/handoff-protocol.md +72 -71
  23. package/src/core-skills/wizz-review-adversarial-general/SKILL.md +1 -1
  24. package/src/modules/lowticket/skills/wizz-lowticket-funil/references/copy-das-paginas.md +39 -39
  25. package/src/modules/lowticket/skills/wizz-lowticket-funil/references/mapa-do-funil.md +23 -23
  26. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/CATALOGO.md +72 -72
  27. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/01-principios.md +10 -10
  28. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/02-diagnostico-funil.md +50 -50
  29. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/03-campanha-bidcap.md +68 -68
  30. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/04-criativos.md +44 -44
  31. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/04a-criativos-ia.md +77 -77
  32. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/04b-criativos-formatos.md +121 -121
  33. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/05-oferta.md +35 -35
  34. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/06-pagina-vendas.md +122 -122
  35. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/06a-instagram.md +93 -93
  36. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/06b-player-vsl.md +57 -57
  37. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/07-funil-upsell.md +83 -83
  38. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/07a-copy-humanizacao.md +61 -61
  39. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/08-pesquisa-publico.md +11 -11
  40. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/09-especialista-coproducao.md +26 -26
  41. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/10-levantar-caixa.md +29 -29
  42. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/11-checklist-roi.md +22 -22
  43. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/12-mineracao-ofertas.md +80 -80
  44. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/12a-mineracao-veredito.md +72 -72
  45. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/12b-fabrica-de-ofertas.md +63 -63
  46. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/12c-anatomia-low-ticket.md +71 -71
  47. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/13-benchmarks-vsl.md +6 -6
  48. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/14-vocabulario.md +53 -51
  49. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/15-como-estender.md +26 -26
  50. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/17-rastreamento.md +76 -76
  51. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/18-copy-desejo-oferta.md +149 -149
  52. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/INDEX.md +45 -45
  53. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/guardrails.md +45 -45
  54. package/src/modules/lowticket/skills/wizz-lowticket-metodologia/knowledge/pontos-em-aberto.md +64 -66
  55. package/src/modules/lowticket/skills/wizz-lowticket-minerador/references/rubrica.md +63 -63
  56. package/src/modules/lowticket/skills/wizz-lowticket-pagina/references/metas-e-medicao.md +23 -23
  57. package/src/modules/lowticket/skills/wizz-lowticket-pagina/references/padroes-de-codigo.md +50 -50
  58. package/src/modules/lowticket/skills/wizz-lowticket-trafego/references/formato-do-diagnostico.md +9 -9
  59. package/src/modules/lowticket/skills/wizz-lowticket-trafego/references/reguas.md +42 -42
  60. package/src/modules/wizz/README.md +27 -27
  61. package/src/modules/wizz/_shared/cerebro.md +37 -37
  62. package/src/modules/wizz/_shared/communication-rules.md +15 -15
  63. package/src/modules/wizz/_shared/despacho-barato.md +6 -6
  64. package/src/modules/wizz/_shared/encerramento.md +23 -23
  65. package/src/modules/wizz/_shared/model-ladder.md +29 -28
  66. package/src/modules/wizz/_shared/planning-gate.md +30 -30
  67. package/src/modules/wizz/_shared/token-economy.md +28 -28
  68. package/src/modules/wizz/_shared/video-pipeline.md +42 -42
  69. package/src/modules/wizz/agents/wizz-ads/SKILL.md +16 -16
  70. package/src/modules/wizz/agents/wizz-ads/customize.toml +21 -21
  71. package/src/modules/wizz/agents/wizz-copy/SKILL.md +18 -18
  72. package/src/modules/wizz/agents/wizz-copy/customize.toml +24 -24
  73. package/src/modules/wizz/agents/wizz-designer/SKILL.md +24 -24
  74. package/src/modules/wizz/agents/wizz-designer/customize.toml +29 -29
  75. package/src/modules/wizz/agents/wizz-growth/SKILL.md +20 -20
  76. package/src/modules/wizz/agents/wizz-growth/customize.toml +34 -34
  77. package/src/modules/wizz/agents/wizz-maestro/SKILL.md +63 -63
  78. package/src/modules/wizz/agents/wizz-maestro/customize.toml +38 -38
  79. package/src/modules/wizz/agents/wizz-memoria/SKILL.md +19 -19
  80. package/src/modules/wizz/agents/wizz-memoria/customize.toml +24 -24
  81. package/src/modules/wizz/agents/wizz-qa/SKILL.md +22 -22
  82. package/src/modules/wizz/agents/wizz-qa/customize.toml +29 -29
  83. package/src/modules/wizz/agents/wizz-seo/SKILL.md +19 -19
  84. package/src/modules/wizz/agents/wizz-seo/customize.toml +27 -27
  85. package/src/modules/wizz/agents/wizz-social/SKILL.md +53 -53
  86. package/src/modules/wizz/agents/wizz-social/customize.toml +37 -37
  87. package/src/modules/wizz/agents/wizz-social/knowledge/analise-imagem-referencia.md +20 -20
  88. package/src/modules/wizz/agents/wizz-social/knowledge/biblioteca-prompts-imagem.md +71 -71
  89. package/src/modules/wizz/agents/wizz-social/knowledge/blueprint-roteiro-viral.md +196 -196
  90. package/src/modules/wizz/agents/wizz-social/knowledge/legenda-instagram.md +32 -32
  91. package/src/modules/wizz/agents/wizz-social/knowledge/prompts-imagem-video.md +48 -48
  92. package/src/modules/wizz/module.yaml +28 -28
  93. package/src/modules/wizz/overrides/wizz-agent-analyst.toml +17 -17
  94. package/src/modules/wizz/overrides/wizz-agent-architect.toml +21 -21
  95. package/src/modules/wizz/overrides/wizz-agent-dev.toml +20 -20
  96. package/src/modules/wizz/overrides/wizz-agent-pm.toml +11 -11
  97. package/src/modules/wizz/overrides/wizz-agent-tech-writer.toml +14 -14
  98. package/src/modules/wizz/overrides/wizz-agent-ux-designer.toml +14 -14
  99. package/src/modules/wizz/subagents/codex/wizz-exec-haiku.toml +17 -17
  100. package/src/modules/wizz/subagents/codex/wizz-exec-opus.toml +19 -19
  101. package/src/modules/wizz/subagents/codex/wizz-exec-review.toml +18 -17
  102. package/src/modules/wizz/subagents/codex/wizz-exec-sonnet.toml +18 -18
  103. package/src/modules/wizz/subagents/gemini/wizz-exec-haiku.md +17 -17
  104. package/src/modules/wizz/subagents/gemini/wizz-exec-opus.md +19 -19
  105. package/src/modules/wizz/subagents/gemini/wizz-exec-review.md +18 -17
  106. package/src/modules/wizz/subagents/gemini/wizz-exec-sonnet.md +18 -18
  107. package/src/modules/wizz/subagents/opencode/wizz-exec-haiku.md +17 -17
  108. package/src/modules/wizz/subagents/opencode/wizz-exec-opus.md +19 -19
  109. package/src/modules/wizz/subagents/opencode/wizz-exec-review.md +18 -17
  110. package/src/modules/wizz/subagents/opencode/wizz-exec-sonnet.md +18 -18
  111. package/src/modules/wizz/subagents/spec.yaml +84 -82
  112. package/src/modules/wizz/subagents/wizz-exec-haiku.md +17 -17
  113. package/src/modules/wizz/subagents/wizz-exec-opus.md +19 -19
  114. package/src/modules/wizz/subagents/wizz-exec-review.md +18 -17
  115. package/src/modules/wizz/subagents/wizz-exec-sonnet.md +18 -18
  116. package/src/skills-lib/cerebro/SKILL.md +61 -61
  117. package/src/skills-lib/cerebro/references/comandos-pesquisa-e-memoria.md +46 -46
  118. package/src/skills-lib/cerebro/references/comandos-rotina-e-captura.md +65 -65
  119. package/src/skills-lib/cerebro/references/comandos-sessao.md +74 -74
  120. package/src/skills-lib/ctc-align/SKILL.md +37 -37
  121. package/src/skills-lib/find-skills/SKILL.md +19 -19
  122. package/src/skills-lib/pesquisa-de-publico-do-piva/README.md +33 -33
  123. package/src/skills-lib/pesquisa-de-publico-do-piva/SKILL.md +42 -42
  124. package/src/skills-lib/pesquisa-de-publico-do-piva/prompts.md +20 -20
  125. package/src/skills-lib/references/premium-agency-rules.md +63 -63
  126. package/src/skills-lib/security-audit-pentest/SKILL.md +31 -31
  127. package/src/skills-lib/security-audit-pentest/references/stage-1-validacao-entrada.md +37 -37
  128. package/src/skills-lib/security-audit-pentest/references/stage-2-autorizacao.md +61 -61
  129. package/src/skills-lib/security-audit-pentest/references/stage-3-abuso-volume.md +37 -37
  130. package/src/skills-lib/security-audit-pentest/references/stage-4-vazamento-resposta.md +52 -52
  131. package/src/skills-lib/site-launch-kit/SKILL.md +42 -42
  132. package/src/skills-lib/site-launch-kit/references/01-cta-principal.md +20 -20
  133. package/src/skills-lib/site-launch-kit/references/02-barra-fixa-mobile.md +24 -24
  134. package/src/skills-lib/site-launch-kit/references/03-tempo-de-resposta.md +21 -21
  135. package/src/skills-lib/site-launch-kit/references/04-prova-social.md +22 -22
  136. package/src/skills-lib/site-launch-kit/references/05-faq-decisao.md +28 -28
  137. package/src/skills-lib/site-launch-kit/references/06-imagens-reais.md +27 -27
  138. package/src/skills-lib/site-launch-kit/references/07-endereco-como-chegar.md +25 -25
  139. package/src/skills-lib/site-launch-kit/references/08-titles.md +30 -30
  140. package/src/skills-lib/site-launch-kit/references/09-open-graph.md +23 -23
  141. package/src/skills-lib/site-launch-kit/references/10-breadcrumbs.md +23 -23
  142. package/src/skills-lib/site-launch-kit/references/11-alt-text.md +28 -28
  143. package/src/skills-lib/site-launch-kit/references/12-schema-local.md +22 -22
  144. package/src/skills-lib/site-launch-kit/references/13-robots-sitemap.md +26 -26
  145. package/src/skills-lib/site-launch-kit/references/14-privacidade-termos.md +27 -27
  146. package/src/skills-lib/site-launch-kit/references/15-medicao.md +23 -23
  147. package/src/skills-lib/wizz-ai-product-design/SKILL.md +70 -70
  148. package/src/skills-lib/wizz-auth-and-secrets/SKILL.md +78 -78
  149. package/src/skills-lib/wizz-caching-and-queues/SKILL.md +40 -40
  150. package/src/skills-lib/wizz-cloud-and-infra/SKILL.md +22 -22
  151. package/src/skills-lib/wizz-database-and-deps/SKILL.md +52 -52
  152. package/src/skills-lib/wizz-database-scaling/SKILL.md +31 -31
  153. package/src/skills-lib/wizz-desktop-security/SKILL.md +49 -49
  154. package/src/skills-lib/wizz-implementation-planner/SKILL.md +56 -56
  155. package/src/skills-lib/wizz-implementation-planner/references/folder-structure-and-dependencies.md +14 -14
  156. package/src/skills-lib/wizz-implementation-planner/references/implementation-phases.md +15 -15
  157. package/src/skills-lib/wizz-implementation-planner/references/implementation-types.md +9 -9
  158. package/src/skills-lib/wizz-implementation-planner/references/motion-path-implementation.md +19 -19
  159. package/src/skills-lib/wizz-implementation-planner/references/performance-plan.md +27 -27
  160. package/src/skills-lib/wizz-infrastructure/SKILL.md +21 -21
  161. package/src/skills-lib/wizz-inicio-de-projeto/SKILL.md +63 -63
  162. package/src/skills-lib/wizz-inicio-de-projeto/references/implementacao-api-forms.md +27 -27
  163. package/src/skills-lib/wizz-inicio-de-projeto/references/padroes-arquiteturais-e-pastas.md +31 -31
  164. package/src/skills-lib/wizz-inicio-de-projeto/references/seguranca-e-regras-codigo.md +21 -21
  165. package/src/skills-lib/wizz-launch-readiness/SKILL.md +61 -61
  166. package/src/skills-lib/wizz-launch-readiness/references/01-tecnico-build.md +16 -16
  167. package/src/skills-lib/wizz-launch-readiness/references/02-seguranca.md +16 -16
  168. package/src/skills-lib/wizz-launch-readiness/references/03-seo-descoberta.md +16 -16
  169. package/src/skills-lib/wizz-launch-readiness/references/04-analytics-medicao.md +15 -15
  170. package/src/skills-lib/wizz-launch-readiness/references/05-conteudo-prova-social.md +15 -15
  171. package/src/skills-lib/wizz-launch-readiness/references/06-legal-lgpd.md +15 -15
  172. package/src/skills-lib/wizz-launch-readiness/references/07-infra-deploy-rollback.md +16 -16
  173. package/src/skills-lib/wizz-launch-readiness/references/08-fusao-priorizacao.md +19 -19
  174. package/src/skills-lib/wizz-launch-readiness/references/09-persistencia-project-context.md +26 -26
  175. package/src/skills-lib/wizz-motion-3d-director/SKILL.md +70 -70
  176. package/src/skills-lib/wizz-motion-3d-director/references/image-to-video-workflow.md +34 -35
  177. package/src/skills-lib/wizz-motion-3d-director/references/motion-paths.md +70 -70
  178. package/src/skills-lib/wizz-motion-3d-director/references/performance-and-handoff.md +17 -17
  179. package/src/skills-lib/wizz-offer-forge/README.md +9 -9
  180. package/src/skills-lib/wizz-offer-forge/SKILL.md +64 -64
  181. package/src/skills-lib/wizz-offer-forge/references/empilhamento-valor.md +17 -17
  182. package/src/skills-lib/wizz-offer-forge/references/garantia-reversa.md +16 -16
  183. package/src/skills-lib/wizz-offer-forge/references/mecanismo-unico.md +19 -19
  184. package/src/skills-lib/wizz-offer-forge/references/ponte-trafego.md +17 -17
  185. package/src/skills-lib/wizz-premium-landing-ui-researcher/SKILL.md +36 -36
  186. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/audit-protocol.md +81 -82
  187. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/component-sources.md +105 -105
  188. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/core-goal.md +39 -39
  189. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/dashboard-and-portfolio-modes.md +49 -50
  190. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/handoffs.md +33 -34
  191. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/landing-page-strategy.md +141 -142
  192. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/mandatory-process.md +24 -24
  193. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/output-format-and-quality.md +73 -73
  194. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/prompt-templates.md +4 -4
  195. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/site-levels.md +282 -283
  196. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/source-first-protocol.md +39 -39
  197. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/source-links.md +8 -8
  198. package/src/skills-lib/wizz-premium-landing-ui-researcher/references/stack-and-visual-direction.md +63 -64
  199. package/src/skills-lib/wizz-router/SKILL.md +38 -38
  200. package/src/skills-lib/wizz-router/references/auditoria-360.md +12 -12
  201. package/src/skills-lib/wizz-router/references/routing-table-flat.md +80 -80
  202. package/src/skills-lib/wizz-tracking-audit/SKILL.md +48 -48
  203. package/src/skills-lib/wizz-tracking-audit/references/modo-diagnostico.md +43 -43
  204. package/src/skills-lib/wizz-tracking-audit/references/modo-implantacao.md +59 -59
  205. package/src/skills-lib/wizz-tracking-audit/references/utm-e-atribuicao.md +35 -35
  206. package/src/skills-lib/wizz-web-security/SKILL.md +35 -35
  207. package/src/skills-lib/wizz-web-security/references/checklist-deploy.md +50 -50
  208. package/src/skills-lib/wizz-web-security/references/headers-rate-limit-cors.md +33 -33
  209. package/src/skills-lib/wizz-web-security/references/owasp-top5-detalhado.md +36 -36
  210. package/tools/hooks/session-rules.js +14 -11
  211. package/tools/installer/core/resolved-customizations.js +58 -10
  212. package/tools/installer/core/resolved-schema.js +116 -18
@@ -1,125 +1,125 @@
1
- ## 4A. Criativos — produção com IA
1
+ ## 4A. Creatives — AI production
2
2
 
3
- > Shard da metodologia desta base. Índice: [`INDEX.md`](INDEX.md) · Sempre carregado junto: [`guardrails.md`](guardrails.md)
4
- > Onde a skill genérica contradisser este shard, **o shard vence**, e isso deve ser dito na resposta.
3
+ > Shard of this base's methodology. Index: [`INDEX.md`](INDEX.md) · Always loaded alongside: [`guardrails.md`](guardrails.md)
4
+ > Where the generic skill contradicts this shard, **the shard wins**, and this must be stated in the response.
5
5
 
6
- **O que tem aqui:** `4.6` realismo em vídeo com IA · `4.9` imagens e avatares realistas · `4.13` avatares de fala, continuação de cena e pipeline sem marca d'água · `4.14` pipeline de 20 min para TikTok · `4.15` banco de ferramentas gratuitas
7
- **Irmãos:** fundamentos em [`04-criativos.md`](04-criativos.md) · roteiro, moldes e swipe file em [`04b-criativos-formatos.md`](04b-criativos-formatos.md)
8
- **Atenção:** avatar de IA passando por pessoa real é tática bloqueada — ver [guardrails 21](guardrails.md).
6
+ **What's here:** `4.6` realism in AI video · `4.9` realistic images and avatars · `4.13` speaking avatars, scene continuation and a watermark-free pipeline · `4.14` 20-minute pipeline for TikTok · `4.15` bank of free tools
7
+ **Siblings:** fundamentals in [`04-criativos.md`](04-criativos.md) · script, templates and swipe file in [`04b-criativos-formatos.md`](04b-criativos-formatos.md)
8
+ **Attention:** an AI avatar passing as a real person is a blocked tactic — see [guardrails 21](guardrails.md).
9
9
 
10
- ### 4.6 Realismo em vídeo com IA
10
+ ### 4.6 Realism in AI video
11
11
 
12
- > ⚠️ Avatar realista de IA: ver [guardrails 21](guardrails.md) antes de apresentar avatar gerado como se fosse pessoa real em anúncio.
12
+ > ⚠️ Realistic AI avatar: see [guardrails 21](guardrails.md) before presenting a generated avatar as if it were a real person in an ad.
13
13
 
14
- Duas ferramentas, funções distintas: **Dream Face** para sincronia labial (avatar falando) e **Eleven Labs** para geração de voz.
14
+ Two tools, distinct functions: **Dream Face** for lip-sync (a speaking avatar) and **Eleven Labs** for voice generation.
15
15
 
16
- **As 3 regras de ouro do realismo** (falhar em uma quebra a ilusão inteira):
16
+ **The 3 golden rules of realism** (failing one breaks the whole illusion):
17
17
 
18
- 1. **Cenário natural.** Vídeo base realista, não pessoa parada de frente para a câmera.
19
- 2. **Voz combinando com a entonação** da pessoa no vídeo original.
20
- 3. **Gestos acompanhando exatamente o que está sendo dito.** Gesticulação descolada da fala é o erro mais visível.
18
+ 1. **Natural setting.** A realistic base video, not a person standing still facing the camera.
19
+ 2. **A voice matching the intonation** of the person in the original video.
20
+ 3. **Gestures exactly following what's being said.** Gesturing out of sync with the speech is the most visible mistake.
21
21
 
22
- **Operação:**
22
+ **Operation:**
23
23
 
24
- - Usar avatar pré-existente ou carregado no Dream Face dá lip sync mais natural do que subir só uma foto.
25
- - Versão gratuita do Dream Face limita a 30s; acima disso exige o plano Pro.
26
- - **Dividir a copy em trechos de 3 a 4 linhas** em vez de colar texto longo inteiro. Áudio fica mais estável.
27
- - Treinar a voz com áudio isolado e limpo (podcast, por exemplo), nunca com ruído de fundo.
28
- - Conferir pronúncia: erro de pronúncia é a falha que mais denuncia IA.
24
+ - Using a pre-existing avatar or one uploaded in Dream Face gives a more natural lip sync than uploading just a photo.
25
+ - Dream Face's free version caps at 30s; beyond that requires the Pro plan.
26
+ - **Split the copy into chunks of 3 to 4 lines** instead of pasting one long block of text. The audio stays more stable.
27
+ - Train the voice with isolated, clean audio (a podcast, for example), never with background noise.
28
+ - Check pronunciation: mispronunciation is the mistake that gives away AI the most.
29
29
 
30
- ### 4.9 Imagens e avatares realistas com IA — Google Flow
30
+ ### 4.9 Realistic images and avatars with AI — Google Flow
31
31
 
32
- > ⚠️ **Avatar de IA como pessoa real — confirmar antes de usar.** Meta e Instagram exigem que conta representando pessoa fictícia seja identificável como tal, e a regra varia por formato e por país (mais dura em Portugal e na UE, ver 4.8). O material de origem não trata disso. Avatar de IA como recurso visual declarado, sim; avatar de IA apresentado como pessoa real em anúncio, **não sem confirmar a política do mercado alvo**. Ver [guardrails 21](guardrails.md).
32
+ > ⚠️ **AI avatar as a real person — confirm before using.** Meta and Instagram require an account representing a fictitious person to be identifiable as such, and the rule varies by format and by country (stricter in Portugal and the EU, see 4.8). The source material doesn't address this. An AI avatar as a declared visual device, yes; an AI avatar presented as a real person in an ad, **not without confirming the target market's policy**. See [guardrails 21](guardrails.md).
33
33
 
34
- Complementa a 4.6 (que trata de vídeo falado com Dream Face + Eleven Labs). Aqui o objeto é **gerar a foto/avatar**, para perfil ou para criativo.
34
+ Complements 4.6 (which covers spoken video with Dream Face + Eleven Labs). Here the object is **generating the photo/avatar**, for a profile or for a creative.
35
35
 
36
- **Ferramenta:** **Google Flow** — gratuita, gera foto e vídeo direto no navegador. Modelo de imagem citado na aula: "NanoBandana 2".
36
+ **Tool:** **Google Flow** — free, generates photo and video directly in the browser. Image model cited in the lesson: "NanoBandana 2".
37
37
 
38
- **Configuração:**
38
+ **Setup:**
39
39
 
40
- - Proporção **3:4 para feed**, **9:16 para stories**.
41
- - Gerar **4 fotos por rodada** para ter de onde escolher.
40
+ - Aspect ratio **3:4 for feed**, **9:16 for stories**.
41
+ - Generate **4 photos per round** to have options to choose from.
42
42
 
43
- **Fluxo:**
43
+ **Flow:**
44
44
 
45
- 1. Usar o ChatGPT para descrever a imagem desejada em **JSON realista** (prompt estruturado, não frase solta).
46
- 2. Colar o JSON no Google Flow.
47
- 3. Se a consistência facial falhar (a IA não incorpora a foto de referência sozinha), usar o recurso manual **"add to prompt"** para forçar a referência.
45
+ 1. Use ChatGPT to describe the desired image in **realistic JSON** (a structured prompt, not a loose sentence).
46
+ 2. Paste the JSON into Google Flow.
47
+ 3. If facial consistency fails (the AI doesn't incorporate the reference photo on its own), use the manual **"add to prompt"** feature to force the reference.
48
48
 
49
- **Benchmark de qualidade citado:** o perfil "Deborah Nowalski" foi usado na aula como padrão de realismo a atingir.
49
+ **Quality benchmark cited:** the "Deborah Nowalski" profile was used in the lesson as the realism standard to reach.
50
50
 
51
- > Vale para as 3 regras de ouro da 4.6: cenário natural, voz combinando com a entonação e gesto acompanhando a fala. Foto realista com vídeo mal sincronizado continua quebrando a ilusão.
51
+ > The 3 golden rules from 4.6 still apply: natural setting, voice matching the intonation, and gestures following the speech. A realistic photo with a poorly synced video still breaks the illusion.
52
52
  >
53
- > 💡 **Prompt literal:** O prompt base em inglês para selfie realista com microexpressões, gestos naturais e iluminação suave foi fornecido na aula de 2026-08-25 e está registrado na íntegra na seção 4.13 deste shard.
53
+ > 💡 **Literal prompt:** the base English prompt for a realistic selfie with micro-expressions, natural gestures and soft lighting was provided in the 2026-08-25 lesson and is recorded in full in section 4.13 of this shard.
54
54
 
55
- ### 4.13 Avatares de Fala, Continuação de Cenas e Pipeline sem Marca d'Água
55
+ ### 4.13 Speaking Avatars, Scene Continuation and a Watermark-Free Pipeline
56
56
 
57
- Material da aula prática focada na criação de vídeos com avatares falantes ultra-realistas com ferramentas gratuitas, técnicas de consistência frame-a-frame e pós-produção:
57
+ Material from a hands-on lesson focused on creating videos with ultra-realistic speaking avatars using free tools, frame-to-frame consistency techniques and post-production:
58
58
 
59
- 1. **Stack Integrada de Ferramentas (100% Gratuita):**
60
- - **Google Flow:** Geração da imagem base do avatar em 4 variações a partir de prompt descritivo.
61
- - **DreamFace:** Lip-sync / sincronia labial, microexpressões faciais e gesticulação do avatar com base no áudio.
62
- - **Eleven Labs:** Geração de voz realista com entonação humana e sotaque adequado.
63
- - **CapCut:** Pós-produção — aceleração leve da velocidade da fala (para retirar a cadência arrastada/robótica comum da IA), cortes finos de silêncio e adição de ruído de fundo/tráfego sonoro ambiente para gerar imersão e naturalidade.
59
+ 1. **Integrated Tool Stack (100% Free):**
60
+ - **Google Flow:** Generates the avatar's base image in 4 variations from a descriptive prompt.
61
+ - **DreamFace:** Lip-sync, facial micro-expressions and avatar gesturing based on the audio.
62
+ - **Eleven Labs:** Generates realistic voice with human intonation and appropriate accent.
63
+ - **CapCut:** Post-production — lightly speeding up the speech pace (to remove the dragging/robotic cadence common in AI), fine cuts of silence, and adding background/ambient traffic noise to create immersion and naturalness.
64
64
 
65
- 2. **Truque de Download sem Marca d'Água (DevTools / Network):**
66
- - Na versão gratuita web do DreamFace, para não pagar pelo plano Pro nem ficar com marca d'água no criativo: abrir as ferramentas de desenvolvedor do navegador (`Inspecionar Elemento` / `F12` / `Ctrl+P`), acessar a aba **Network (Rede)**, filtrar por mídia/stream (`media` ou formato de vídeo mp4/webm) durante o preview e capturar/baixar a URL direta do arquivo de vídeo limpo sem a logo sobreposta.
65
+ 2. **Watermark-Free Download Trick (DevTools / Network):**
66
+ - In DreamFace's free web version, to avoid paying for the Pro plan or ending up with a watermark on the creative: open the browser's developer tools (`Inspect Element` / `F12` / `Ctrl+P`), go to the **Network** tab, filter by media/stream (`media` or mp4/webm video format) during the preview, and capture/download the direct URL of the clean video file without the overlaid logo.
67
67
 
68
- 3. **Ancoragem de Gestos na Primeira Frame (Evitar Distorções no Lip-Sync):**
69
- - Para avatares com gesticulação específica (ex: mãos no volante do carro, segurando copo/xícara ou segurando o celular), o gesto e a postura corporal **precisam estar presentes e definidos na primeira frame gerada**. Se o avatar iniciar neutro e tentar gesticular no meio da fala, a IA gera distorções laterais na face e quebra o encaixe do lip-sync.
68
+ 3. **Anchoring Gestures in the First Frame (Avoiding Lip-Sync Distortions):**
69
+ - For avatars with specific gesturing (e.g. hands on the steering wheel, holding a cup/mug, or holding a phone), the gesture and body posture **need to be present and set in the first generated frame**. If the avatar starts neutral and tries to gesture mid-speech, the AI generates lateral distortions on the face and breaks the lip-sync fit.
70
70
 
71
- 4. **Técnica de Continuação para Vídeos Longos (Frame-to-Frame Continuity):**
72
- - **O problema:** Limite de tempo de geração por clipe na IA gratuita (ex: 30s) e perda de consistência visual ao gerar múltiplos trechos soltos.
73
- - **A solução:** Salvar um print/export exato do **último frame** do vídeo anterior e usá-lo como **imagem inicial / imagem de referência** da próxima geração mantendo exatamente o mesmo prompt base. Isso conecta as cenas perfeitamente sem cortes bruscos, mantendo o avatar consistente e evitando que ele "reinicie" com gestos ou posições erradas.
71
+ 4. **Continuation Technique for Long Videos (Frame-to-Frame Continuity):**
72
+ - **The problem:** generation time limit per clip in the free AI (e.g. 30s) and loss of visual consistency when generating multiple separate segments.
73
+ - **The solution:** save an exact screenshot/export of the **last frame** of the previous video and use it as the **starting image / reference image** for the next generation while keeping exactly the same base prompt. This connects the scenes perfectly with no abrupt cuts, keeping the avatar consistent and preventing it from "resetting" with wrong gestures or positions.
74
74
 
75
- 5. **Prompt Base Operacional da Aula (Prompt Estruturado em Inglês):**
75
+ 5. **Operational Base Prompt from the Lesson (Structured Prompt in English):**
76
76
 
77
77
  ```text
78
78
  Generate a realistic vertical selfie video format. The character should speak naturally with perfect lip-sync to the audio. Capture an authentic, informal vibe with subtle hand tremors typical of holding a smartphone. Include natural micro-expressions, soft blinking, light head nods, and organic hand gestures emphasizing words. The mood should feel candid, friendly, and spontaneous. Background is a warm, softly lit everyday setting (like a living room or cozy cafe) remaining static with soft depth of field. Ultra-photorealistic 8k video quality.
79
79
  ```
80
80
 
81
- ### 4.14 Pipeline de 20 minutos — criativo de vídeo para TikTok
81
+ ### 4.14 20-minute pipeline — video creative for TikTok
82
82
 
83
- > ⚠️ Avatar de IA apresentado como pessoa real: ver [guardrails 21](guardrails.md). Vale também a regra de lip-sync: nunca reaproveitar take de avatar cuja boca não corresponde 1:1 ao áudio da peça.
83
+ > ⚠️ AI avatar presented as a real person: see [guardrails 21](guardrails.md). The lip-sync rule also applies: never reuse an avatar take whose mouth doesn't match the piece's audio 1:1.
84
84
 
85
- Mesma stack de §4.6, §4.9 e §4.13 — Google Flow, Eleven Labs, CapCut. O que muda aqui é a **ordem de operação e o tempo**, não a ferramenta.
85
+ Same stack as §4.6, §4.9 and §4.13 — Google Flow, Eleven Labs, CapCut. What changes here is the **order of operations and the timing**, not the tooling.
86
86
 
87
- **Preparar tudo antes de abrir qualquer ferramenta.** A fonte de origem monta um bloco de notas prévio com avatares, movimentos e cópias de áudio baseadas no prompt. Só depois disso abre Google Flow, Eleven Labs ou CapCut. É essa preparação que compra os 20 minutos, não a velocidade dentro de cada ferramenta.
87
+ **Prepare everything before opening any tool.** The source material builds a prior notes block with avatars, movements and audio copy based on the prompt. Only after that does it open Google Flow, Eleven Labs or CapCut. It's this preparation that buys the 20 minutes, not the speed inside each tool.
88
88
 
89
- **Fluxo:**
89
+ **Flow:**
90
90
 
91
- 1. Pedir ao Google Flow, via **prompt JSON**, o avatar em formato **selfie / falando para a câmera**, geração em **9:16**.
92
- 2. Gerar a voz e, no mesmo Eleven Labs, **adaptar o sotaque** para pt-PT ou pt-BR ("mude somente as nuances, os jeitos e as gírias").
93
- > Isso é adaptação de **sotaque no áudio**, e não substitui a **transcriação de texto** de §4.8 de [`04b-criativos-formatos.md`](04b-criativos-formatos.md). São duas operações diferentes; esta aula só cobre a primeira.
94
- 3. Sincronizar lip-sync e editar no CapCut.
95
- 4. Fechar a edição com legendas coloridas (mesma prática de §4.5 de [`04-criativos.md`](04-criativos.md)) e efeitos sonoros.
91
+ 1. Ask Google Flow, via a **JSON prompt**, for the avatar in **selfie / talking to the camera** format, generated in **9:16**.
92
+ 2. Generate the voice and, in the same Eleven Labs session, **adapt the accent** to pt-PT or pt-BR ("only change the nuances, the mannerisms and the slang").
93
+ > This is **accent adaptation in the audio**, and it doesn't replace the **text transcreation** from §4.8 of [`04b-criativos-formatos.md`](04b-criativos-formatos.md). They're two different operations; this lesson only covers the first one.
94
+ 3. Sync the lip-sync and edit in CapCut.
95
+ 4. Finish the edit with colorful captions (same practice as §4.5 of [`04-criativos.md`](04-criativos.md)) and sound effects.
96
96
 
97
- **Um cenário só, várias falas.** É o truque que torna o pipeline de 20 minutos viável: em vez de um cenário novo por vídeo, repete-se o mesmo cenário (exemplo da aula: uma cozinha) com falas diferentes, cortando com frequência e variando ângulo para manter o dinamismo visual.
97
+ **One setting, several lines.** This is the trick that makes the 20-minute pipeline viable: instead of a new setting per video, the same setting is reused (the lesson's example: a kitchen) with different lines, cutting frequently and varying the angle to keep visual dynamism.
98
98
 
99
- **Detalhes de qualidade citados na aula:**
99
+ **Quality details mentioned in the lesson:**
100
100
 
101
- - Ajustar a **iluminação** do avatar melhora a precisão do lip-sync gerado por IA.
102
- - **Transições sonoras tipo "riser"** reacendem a atenção do espectador ao longo do vídeo.
103
- - **B-roll de banco de imagens e áudio** entre os cortes quebra a monotonia do cenário único.
104
- - Exportar a **30 fps**. A fonte de origem é explícita: 60 fps deixa o arquivo mais pesado sem ganho.
101
+ - Adjusting the avatar's **lighting** improves the accuracy of the AI-generated lip-sync.
102
+ - **"Riser"-style sound transitions** re-spark the viewer's attention throughout the video.
103
+ - **B-roll from stock footage and audio** between cuts breaks the monotony of a single setting.
104
+ - Export at **30 fps**. The source material is explicit: 60 fps makes the file heavier with no gain.
105
105
 
106
- ### 4.15 Banco de ferramentas — alternativas gratuitas
106
+ ### 4.15 Tool bank — free alternatives
107
107
 
108
- > ⚠️ **Duas táticas desta aula não são adotadas.** Descarregar vídeo de terceiro do TikTok (com ou sem marca d'água) para rodar como criativo próprio, e usar imagem de pessoa de outro país para "testar aceitação" sem direito de uso. Motivo e alternativa em [guardrails 45](guardrails.md). O resto da aula — bancos gratuitos, alternativa de voz, TikTok como referência para ESTUDAR formato — continua valendo.
108
+ > ⚠️ **Two tactics from this lesson are not adopted.** Downloading someone else's TikTok video (with or without watermark) to run as your own creative, and using a photo of a person from another country to "test acceptance" without usage rights. Reason and alternative in [guardrails 45](guardrails.md). The rest of the lesson — free stock banks, a voice alternative, TikTok as a reference to STUDY format — still stands.
109
109
 
110
- A parte do TikTok que fica valendo é usar a plataforma para **observar e modelar formato** (o que está funcionando, como estão cortando, que ganchos usam), nunca para extrair o arquivo de outra pessoa e reaproveitar como próprio.
110
+ The part of TikTok that remains valid is using the platform to **observe and model format** (what's working, how they're cutting it, what hooks they use), never to extract someone else's file and reuse it as your own.
111
111
 
112
- > 💡 Os nomes abaixo vêm de **ata automática de aula, com transcrição danificada**. Onde a grafia é duvidosa, o nome está marcado como leitura provável e **não verificado**. Conferir antes de instalar ou assinar qualquer ferramenta.
112
+ > 💡 The names below come from an **automatic lesson transcript, with damaged transcription**. Where the spelling is doubtful, the name is flagged as a probable, **unverified** reading. Check before installing or subscribing to any tool.
113
113
 
114
- | Ferramenta | Para que serve | Nota |
114
+ | Tool | What it's for | Note |
115
115
  |---|---|---|
116
- | **MiniMax** (ata grafa "Minimax IO") | Geração de voz — alternativa gratuita ao Eleven Labs | Comparada na aula com o TurboScribe |
117
- | **TurboScribe** | Transcrição | Citada em comparação com o MiniMax |
118
- | **Magnific** (ata grafa "Magnifique") | Geração/tratamento de imagem | — |
119
- | **Pexels** | Banco gratuito de imagem e vídeo | — |
120
- | **TikTok** | Fonte de B-roll e referência para estudar formato | Só para observar/modelar — ver aviso acima, nunca para baixar e reaproveitar vídeo alheio |
121
- | "Coque Coque" na ata — provavelmente o navegador **Cốc Cốc**, que tem descarregador de vídeo embutido | Descarregar vídeo do TikTok sem marca d'água | **Nome não confirmado: verificar antes de instalar.** E o próprio uso está bloqueado — ver aviso acima |
116
+ | **MiniMax** (transcript spells it "Minimax IO") | Voice generation — free alternative to Eleven Labs | Compared in the lesson with TurboScribe |
117
+ | **TurboScribe** | Transcription | Cited in comparison with MiniMax |
118
+ | **Magnific** (transcript spells it "Magnifique") | Image generation/processing | — |
119
+ | **Pexels** | Free image and video stock bank | — |
120
+ | **TikTok** | Source of B-roll and reference for studying format | Only for observing/modeling — see warning above, never for downloading and reusing someone else's video |
121
+ | "Coque Coque" in the transcript — probably the **Cốc Cốc** browser, which has a built-in video downloader | Downloading TikTok video without a watermark | **Name not confirmed: verify before installing.** And the use itself is blocked — see warning above |
122
122
 
123
- **Não identificado:** a ata cita "Eddes" em comparação com o Eleven Labs, sem contexto suficiente para saber a que ferramenta se refere. Registrado aqui como pendente, não como recomendação.
123
+ **Not identified:** the transcript mentions "Eddes" in comparison with Eleven Labs, without enough context to know which tool it refers to. Recorded here as pending, not as a recommendation.
124
124
 
125
- **Pendente de esclarecimento:** "YouTube Russo", citado na ata para avatares realistas e formato de perguntas e respostas, não tem contexto suficiente na fonte para identificar do que se trata. Não incorporado até nova fonte esclarecer.
125
+ **Pending clarification:** "Russian YouTube," cited in the transcript for realistic avatars and Q&A format, doesn't have enough context in the source to identify what it refers to. Not incorporated until a new source clarifies it.