wizz-method 1.17.0 → 1.18.1

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 (112) hide show
  1. package/README.md +1 -1
  2. package/package.json +5 -2
  3. package/removals.txt +3 -0
  4. package/skills-registry.yaml +67 -29
  5. package/src/bmm-skills/1-analysis/wizz-agent-analyst/customize.toml +1 -1
  6. package/src/bmm-skills/1-analysis/wizz-set-feature/SKILL.md +41 -37
  7. package/src/bmm-skills/2-plan-workflows/wizz-agent-pm/customize.toml +1 -1
  8. package/src/bmm-skills/2-plan-workflows/wizz-agent-ux-designer/customize.toml +1 -1
  9. package/src/bmm-skills/3-solutioning/wizz-agent-architect/customize.toml +1 -1
  10. package/src/bmm-skills/4-implementation/wizz-agent-dev/customize.toml +1 -1
  11. package/src/core-skills/_shared/handoff-protocol.md +6 -4
  12. package/src/modules/lowticket/README.md +55 -0
  13. package/src/modules/lowticket/module.yaml +31 -0
  14. package/src/modules/lowticket/skills/lowticket-funil/SKILL.md +112 -0
  15. package/src/modules/lowticket/skills/lowticket-funil/references/copy-das-paginas.md +75 -0
  16. package/src/modules/lowticket/skills/lowticket-funil/references/mapa-do-funil.md +71 -0
  17. package/src/modules/lowticket/skills/lowticket-metodologia/CATALOGO.md +352 -0
  18. package/src/modules/lowticket/skills/lowticket-metodologia/SKILL.md +62 -0
  19. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/01-principios.md +12 -0
  20. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/02-diagnostico-funil.md +83 -0
  21. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/03-campanha-bidcap.md +95 -0
  22. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/04-criativos.md +66 -0
  23. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/04a-criativos-ia.md +79 -0
  24. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/04b-criativos-formatos.md +152 -0
  25. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/05-oferta.md +51 -0
  26. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/06-pagina-vendas.md +175 -0
  27. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/06a-instagram.md +138 -0
  28. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/07-funil-upsell.md +73 -0
  29. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/08-pesquisa-publico.md +14 -0
  30. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/09-especialista-coproducao.md +41 -0
  31. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/10-levantar-caixa.md +49 -0
  32. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/11-checklist-roi.md +36 -0
  33. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/12-mineracao-ofertas.md +63 -0
  34. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/12a-mineracao-veredito.md +78 -0
  35. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/12b-fabrica-de-ofertas.md +178 -0
  36. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/13-benchmarks-vsl.md +10 -0
  37. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/14-vocabulario.md +55 -0
  38. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/15-como-estender.md +35 -0
  39. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/INDEX.md +45 -0
  40. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/guardrails.md +33 -0
  41. package/src/modules/lowticket/skills/lowticket-metodologia/knowledge/pontos-em-aberto.md +42 -0
  42. package/src/modules/lowticket/skills/lowticket-metodologia/references/swipe-file.md +38 -0
  43. package/src/modules/lowticket/skills/lowticket-minerador/SKILL.md +115 -0
  44. package/src/modules/lowticket/skills/lowticket-minerador/references/rubrica.md +75 -0
  45. package/src/modules/lowticket/skills/lowticket-pagina/SKILL.md +106 -0
  46. package/src/modules/lowticket/skills/lowticket-pagina/references/metas-e-medicao.md +70 -0
  47. package/src/modules/lowticket/skills/lowticket-pagina/references/padroes-de-codigo.md +148 -0
  48. package/src/modules/lowticket/skills/lowticket-trafego/SKILL.md +88 -0
  49. package/src/modules/lowticket/skills/lowticket-trafego/references/formato-do-diagnostico.md +56 -0
  50. package/src/modules/lowticket/skills/lowticket-trafego/references/reguas.md +72 -0
  51. package/src/modules/wizz/README.md +1 -1
  52. package/src/modules/wizz/_shared/cerebro.md +35 -1
  53. package/src/modules/wizz/_shared/communication-rules.md +8 -1
  54. package/src/modules/wizz/_shared/token-economy.md +7 -10
  55. package/src/modules/wizz/agents/wizz-ads/customize.toml +1 -1
  56. package/src/modules/wizz/agents/wizz-copy/customize.toml +1 -1
  57. package/src/modules/wizz/agents/wizz-designer/SKILL.md +2 -0
  58. package/src/modules/wizz/agents/wizz-designer/customize.toml +1 -1
  59. package/src/modules/wizz/agents/wizz-growth/SKILL.md +2 -0
  60. package/src/modules/wizz/agents/wizz-growth/customize.toml +1 -1
  61. package/src/modules/wizz/agents/wizz-maestro/SKILL.md +7 -3
  62. package/src/modules/wizz/agents/wizz-maestro/customize.toml +1 -1
  63. package/src/modules/wizz/agents/wizz-memoria/SKILL.md +1 -1
  64. package/src/modules/wizz/agents/wizz-qa/customize.toml +1 -1
  65. package/src/modules/wizz/agents/wizz-seo/customize.toml +1 -1
  66. package/src/modules/wizz/agents/wizz-social/customize.toml +1 -1
  67. package/src/modules/wizz/overrides/wizz-agent-analyst.toml +2 -2
  68. package/src/modules/wizz/overrides/wizz-agent-architect.toml +2 -2
  69. package/src/modules/wizz/overrides/wizz-agent-dev.toml +1 -1
  70. package/src/modules/wizz/overrides/wizz-agent-pm.toml +1 -1
  71. package/src/modules/wizz/overrides/wizz-agent-tech-writer.toml +1 -1
  72. package/src/modules/wizz/overrides/wizz-agent-ux-designer.toml +1 -1
  73. package/src/skills-lib/analytics-tracking/SKILL.md +2 -0
  74. package/src/skills-lib/analytics-tracking/references/utm-taxonomy.md +92 -0
  75. package/src/skills-lib/cerebro/SKILL.md +20 -17
  76. package/src/skills-lib/cerebro/references/comandos-pesquisa-e-memoria.md +96 -0
  77. package/src/skills-lib/cerebro/references/comandos-rotina-e-captura.md +25 -6
  78. package/src/skills-lib/cerebro/references/comandos-sessao.md +61 -37
  79. package/src/skills-lib/find-skills/SKILL.md +0 -1
  80. package/src/skills-lib/impeccable/SKILL.md +20 -25
  81. package/src/skills-lib/impeccable/references/command-workflows.md +35 -0
  82. package/src/skills-lib/impeccable/references/design-rules.md +1 -1
  83. package/src/skills-lib/impeccable/references/pin-unpin-and-hooks.md +4 -14
  84. package/src/skills-lib/impeccable/references/routing-rules.md +8 -25
  85. package/src/skills-lib/premium-landing-ui-researcher/SKILL.md +6 -6
  86. package/src/skills-lib/premium-landing-ui-researcher/references/component-sources.md +12 -81
  87. package/src/skills-lib/premium-landing-ui-researcher/references/core-goal.md +2 -4
  88. package/src/skills-lib/premium-landing-ui-researcher/references/mandatory-process.md +6 -7
  89. package/src/skills-lib/premium-landing-ui-researcher/references/output-format-and-quality.md +3 -4
  90. package/src/skills-lib/premium-landing-ui-researcher/references/source-first-protocol.md +43 -124
  91. package/src/skills-lib/premium-landing-ui-researcher/references/source-links.md +0 -8
  92. package/src/skills-lib/tracking-audit/SKILL.md +78 -0
  93. package/src/skills-lib/tracking-audit/references/modo-diagnostico.md +72 -0
  94. package/src/skills-lib/tracking-audit/references/modo-implantacao.md +89 -0
  95. package/src/skills-lib/tracking-audit/references/utm-e-atribuicao.md +75 -0
  96. package/src/skills-lib/ui-component-curator/SKILL.md +13 -7
  97. package/src/skills-lib/ui-ux-pro-max/SKILL.md +18 -3
  98. package/src/skills-lib/ui-ux-pro-max/references/search-reference.md +3 -3
  99. package/src/skills-lib/ui-ux-pro-max/references/workflow-guide.md +20 -20
  100. package/src/skills-lib/ui-ux-pro-max/scripts/__pycache__/core.cpython-314.pyc +0 -0
  101. package/src/skills-lib/ui-ux-pro-max/scripts/__pycache__/design_system.cpython-314.pyc +0 -0
  102. package/src/skills-lib/ui-ux-pro-max/scripts/search.py +9 -3
  103. package/src/skills-lib/wizz-offer-forge/SKILL.md +27 -2
  104. package/src/skills-lib/wizz-offer-forge/references/plano-de-medicao.md +74 -0
  105. package/src/skills-lib/wizz-router/SKILL.md +3 -1
  106. package/src/skills-lib/wizz-router/references/routing-table-flat.md +3 -3
  107. package/tools/installer/commands/trace-report.js +1 -1
  108. package/tools/installer/modules/skills-lib.js +7 -1
  109. package/wizz-modules.yaml +17 -0
  110. package/src/skills-lib/cerebro/references/comandos-pesquisa-e-sync.md +0 -44
  111. package/src/skills-lib/graphify/.graphify_version +0 -1
  112. package/src/skills-lib/graphify/SKILL.md +0 -1199
@@ -0,0 +1,96 @@
1
+ # Comandos de Pesquisa e Memoria: /prospect, /memoria
2
+
3
+ Carregue este arquivo ao executar `/prospect` ou `/memoria`. Antes de tudo, releia a REGRA DE OURO e a seção Vault no SKILL.md principal — esses comandos dependem delas.
4
+
5
+ ## /prospect
6
+
7
+ **Objetivo:** pesquisar e registrar prospect.
8
+
9
+ **Passos:**
10
+ 1. Receber nome/empresa + objetivo (tudo de uma vez)
11
+ 2. Pesquisar via web search (setor, presença digital, dores, oportunidades)
12
+ 3. Write direto em `_prospects/YYYY-MM-DD-[slug].md`
13
+ 4. Resumo executivo para o usuário (não precisa estar no arquivo)
14
+
15
+ **Template `_prospects/YYYY-MM-DD-[slug].md`:**
16
+ ```markdown
17
+ # [Nome / Empresa]
18
+ > Data: [data] | Objetivo: [tipo] | Status: pesquisado
19
+
20
+ ## Perfil
21
+ - Setor / Tamanho / Produto / Público-alvo
22
+
23
+ ## Presença digital
24
+ - Site / Redes / Ads ativos
25
+
26
+ ## Oportunidade e ângulo de abordagem
27
+ [o que oferecer e como entrar]
28
+
29
+ ## Próximo passo
30
+ - [ ] [ação]
31
+ ```
32
+
33
+ ## /memoria
34
+
35
+ **Objetivo:** ler (e alimentar) a auto-memória do projeto a partir de **qualquer**
36
+ plataforma, não só do Claude Code.
37
+
38
+ A auto-memória guarda as duas linhas que não moram no vault: **armadilha de stack /
39
+ bug não-óbvio** e **preferência de trabalho / correção do usuário**. No Claude Code ela
40
+ carrega sozinha no início da sessão. Em Codex, OpenCode e Gemini não carrega nada, mas
41
+ o dado está lá: é um diretório comum de arquivos `.md` no disco local. Este comando é a
42
+ ponte de leitura. Não existe segunda cópia dos fatos — a fonte continua sendo uma só.
43
+
44
+ ### Passo 1 — resolver o diretório de memória
45
+
46
+ ```bash
47
+ PROJ_DIR="$(pwd)"
48
+ SLUG="$(printf '%s' "$PROJ_DIR" | sed 's/[/.]/-/g')"
49
+ MEM="$HOME/.claude/projects/$SLUG/memory"
50
+ # fallback: o slug histórico nem sempre normaliza espaço e ponto do mesmo jeito
51
+ [ -d "$MEM" ] || MEM="$(ls -d "$HOME"/.claude/projects/*"$(basename "$PROJ_DIR")"/memory 2>/dev/null | head -1)"
52
+ echo "$MEM"
53
+ ```
54
+
55
+ Diretório inexistente = projeto sem auto-memória. Siga sem travar; não é problema a corrigir.
56
+
57
+ ### Passo 2 — carregar só o índice
58
+
59
+ ```bash
60
+ cat "$MEM/MEMORY.md"
61
+ ```
62
+
63
+ O índice tem teto de 8 KB e é 1 linha por memória. **Nunca leia os arquivos individuais
64
+ em bloco.** Abra um arquivo só quando a linha do índice for relevante ao pedido da vez:
65
+
66
+ ```bash
67
+ grep -rln "termo" "$MEM" --include="*.md" | head -5 # depois Read só o que casar
68
+ ```
69
+
70
+ `_archive/` fica fora do índice de propósito. Só entre nele quando o índice não tiver a resposta.
71
+
72
+ ### Passo 3 — gravar (mesma pasta, mesmo formato)
73
+
74
+ Vale o Dever de Memória e o teto: **40 memórias e 8 KB de índice por projeto**. Antes de
75
+ criar, `grep` no destino; se o fato já existe, atualize o arquivo que existe.
76
+
77
+ ```markdown
78
+ ---
79
+ name: <slug-em-kebab-case>
80
+ description: <resumo de uma linha, é o que decide a relevância na recuperação>
81
+ metadata:
82
+ type: user | feedback | project | reference
83
+ ---
84
+
85
+ <o fato. Para feedback/project, siga com as linhas **Why:** e **How to apply:**.
86
+ Ligue memórias relacionadas com [[nome-da-outra]].>
87
+ ```
88
+
89
+ Depois de escrever o arquivo, acrescente 1 linha ao `MEMORY.md`:
90
+ `- [Título](arquivo.md) — gancho`
91
+
92
+ ### Limites honestos
93
+
94
+ - É **pull, não push**: fora do Claude Code nada carrega sozinho, o agente precisa rodar o comando.
95
+ - Vale só para agente rodando na **mesma máquina**. Agente remoto não enxerga este disco.
96
+ - O teto e a poda continuam valendo igual, venha a escrita de qual plataforma vier.
@@ -36,19 +36,38 @@ Carregue este arquivo ao executar `/dia`, `/dump`, `/decisao` ou `/conteudo`. An
36
36
 
37
37
  ## /decisao
38
38
 
39
- **Objetivo:** registrar decisão. Zero reads de arquivos existentes.
39
+ **Objetivo:** registrar decisão. 1 grep antes, nenhum Read.
40
40
 
41
41
  **Passos:**
42
42
  1. Receber descrição + alternativas + projeto (perguntar tudo de uma vez se não passado)
43
- 2. Write direto em `_decisions/YYYY-MM-DD-[slug].md` (template abaixo)
44
- 3. `grep -n "## Decisões recentes" "$VAULT/CEREBRO.md"` → linha
45
- 4. Edit para inserir referência wiki-link logo abaixo dessa linha
46
- 5. Se projeto: `grep -n "## Decisões" "$VAULT/projetos/$PROJ.md"` Edit 1 linha
43
+ 2. **Grep antes de gravar** (obrigatório, 1 bash call):
44
+
45
+ ```bash
46
+ grep -ril "<2 ou 3 palavras do tema>" "$VAULT/_decisions/" | head -5
47
+ ```
48
+
49
+ - Achou decisão sobre o mesmo tema: **não crie arquivo novo**. Abra o que existe e decida entre dois caminhos:
50
+ - a decisão nova **substitui** a antiga → marque a antiga com `status: superseded` e `supersedida_por: <slug novo>`, e crie a nova com `supersede: <slug antigo>`
51
+ - a decisão nova **detalha** a antiga → edite a antiga, não crie a segunda
52
+ - Não achou nada: siga para o passo 3.
53
+
54
+ 3. Write direto em `_decisions/YYYY-MM-DD-[slug].md` (template abaixo)
55
+ 4. `grep -n "## Decisões recentes" "$VAULT/CEREBRO.md"` → linha
56
+ 5. Edit para inserir referência wiki-link logo abaixo dessa linha
57
+ 6. Se há projeto: `grep -n "## Decisões" "$VAULT/projetos/$PROJ.md"` → Edit 1 linha
47
58
 
48
59
  **Template `_decisions/YYYY-MM-DD-[slug].md`:**
49
60
  ```markdown
61
+ ---
62
+ data: YYYY-MM-DD
63
+ projeto: [nome]
64
+ tema: [2 a 4 palavras-chave separadas por vírgula, é por elas que o grep acha]
65
+ status: ativa
66
+ supersede: [slug da decisão que esta substitui, ou omitir]
67
+ supersedida_por: [preenchido depois, quando outra decisão substituir esta]
68
+ ---
69
+
50
70
  # [Título]
51
- > Data: [data] | Projeto: [[projetos/nome]] | Status: ativa
52
71
 
53
72
  ## Decisão
54
73
  [1-2 linhas]
@@ -2,11 +2,30 @@
2
2
 
3
3
  Carregue este arquivo ao executar `/iniciar`, `/ver` ou `/salvar`. Antes de tudo, releia a REGRA DE OURO e a seção Vault no SKILL.md principal — esses comandos dependem delas.
4
4
 
5
+ ## O bloco Estado
6
+
7
+ Todo arquivo em `projetos/` começa com um bloco `## Estado` de no **máximo 12 linhas**, logo abaixo do título. Ele é sobrescrito a cada `/salvar` e é a única coisa que o `/ver` precisa ler.
8
+
9
+ ```markdown
10
+ ## Estado
11
+ - **Fase:** [em que ponto o projeto está, 1 linha]
12
+ - **Stack:** [1 linha]
13
+ - **Onde parou:** [1 linha]
14
+ - **Próximo passo:** [1 linha, a primeira coisa a fazer ao voltar]
15
+ - **Bloqueio:** [1 linha, ou "nenhum"]
16
+ - **Última sessão:** [YYYY-MM-DD] — [1 linha]
17
+ ```
18
+
19
+ Por que 12 linhas: o `/ver` vira 1 Read de 14 linhas em vez de um tail de 60. E o bloco fica no topo, onde qualquer humano abrindo a nota também lê primeiro.
20
+
21
+ O que **não** entra no bloco: histórico, decisão, aprendizado, lista longa de pendências. Histórico é a tabela `Sessões`; decisão é `_decisions/`; aprendizado é a auto-memória do agente; a lista completa de pendências é a seção `O que falta`.
22
+
5
23
  ## /iniciar
6
24
 
7
25
  **Objetivo:** configurar projeto novo. Só cria arquivos — não lê nada além do CEREBRO.md mínimo.
8
26
 
9
27
  **Passos:**
28
+
10
29
  1. Descobrir vault (ver seção Vault)
11
30
  2. `grep -c "$PROJ" "$VAULT/CEREBRO.md"` → verificar se projeto já existe (0 = novo)
12
31
  3. Se novo: entrevistar em 1 mensagem (organização, info essencial, estilo, modo)
@@ -15,21 +34,27 @@ Carregue este arquivo ao executar `/iniciar`, `/ver` ou `/salvar`. Antes de tudo
15
34
  6. Confirmar
16
35
 
17
36
  **Template `projetos/[nome].md`:**
37
+
18
38
  ```markdown
19
39
  # [Nome] — Estado Atual
20
40
  > Atualizado: [data]
21
41
 
42
+ ## Estado
43
+ - **Fase:** [fase]
44
+ - **Stack:** [stack]
45
+ - **Onde parou:** [1 linha]
46
+ - **Próximo passo:** [1 linha]
47
+ - **Bloqueio:** nenhum
48
+ - **Última sessão:** [data] — [1 linha]
49
+
22
50
  ## Preferências
23
51
  - Organização: [resposta]
24
52
  - Info essencial: [resposta]
25
53
  - Estilo: [resposta]
26
54
  - Modo: [registro / sugestivo]
27
55
 
28
- ## Stack
29
- [breve descrição]
30
-
31
- ## Onde parou
32
- -
56
+ ## Contexto
57
+ [o que o bloco Estado não cabe: stack detalhada, restrições, links]
33
58
 
34
59
  ## O que falta
35
60
  - [ ]
@@ -41,6 +66,7 @@ Carregue este arquivo ao executar `/iniciar`, `/ver` ou `/salvar`. Antes de tudo
41
66
  ```
42
67
 
43
68
  **Template bloco em CEREBRO.md:**
69
+
44
70
  ```markdown
45
71
  ### [Nome] [emoji]
46
72
  - **Stack:** [stack]
@@ -51,20 +77,14 @@ Carregue este arquivo ao executar `/iniciar`, `/ver` ou `/salvar`. Antes de tudo
51
77
 
52
78
  ## /ver
53
79
 
54
- **Objetivo:** mostrar estado atual rápido. Máximo: 1 Read.
80
+ **Objetivo:** mostrar estado atual rápido. Máximo: 1 Read de 14 linhas.
55
81
 
56
82
  **Passos:**
57
- 1. `wc -l "$VAULT/projetos/$PROJ.md"` → total de linhas
58
- 2. Read com `offset=(n-60)`, `limit=60` → pega Onde parou + O que falta + Sessões
59
- 3. Retornar em formato condensado:
60
83
 
61
- ```
62
- ## [Projeto] [data última sessão]
63
- Stack: [1 linha]
64
- Onde parou: [bullets]
65
- O que falta: [checkboxes]
66
- Última sessão: [1 linha]
67
- ```
84
+ 1. Read `projetos/[nome].md` com `limit=14` (o bloco Estado está no topo)
85
+ 2. Devolver o bloco quase como está, sem reescrever
86
+
87
+ **Arquivo antigo, sem bloco Estado no topo:** cai no caminho lento uma única vez — `wc -l` e Read das últimas 60 linhas — e ao devolver, ofereça criar o bloco. Aceito, o próximo `/ver` volta a custar 1 Read curto.
68
88
 
69
89
  ## /salvar
70
90
 
@@ -73,6 +93,7 @@ O que falta: [checkboxes]
73
93
  **Passos (executar em ordem, sem desvios):**
74
94
 
75
95
  **1. Localizar projeto e bloco no CEREBRO.md (1 bash call)**
96
+
76
97
  ```bash
77
98
  VAULT=~/Documents/projects/Obsidian\ Vault
78
99
  PROJ=construcao # inferir do diretório atual ou contexto
@@ -80,43 +101,46 @@ grep -n "### \|Última sessão\|Pendente" "$VAULT/CEREBRO.md" | grep -A2 -i "$PR
80
101
  wc -l "$VAULT/projetos/$PROJ.md"
81
102
  ```
82
103
 
83
- **2. Ler apenas o final do arquivo do projeto (1 Read)**
84
- - `offset = (total_linhas - 80)`, `limit = 80`
85
- - Isso captura: Hoje atual, Onde parou, O que falta, tabela Sessões
104
+ **2. Ler o topo e o fim do arquivo do projeto (2 Reads curtos)**
105
+
106
+ - topo: `limit=14` bloco Estado
107
+ - fim: `offset = (total_linhas - 40)`, `limit = 40` → O que falta e tabela Sessões
86
108
 
87
109
  **3. Construir as alterações na memória, depois aplicar (Edits atômicos)**
88
110
 
89
- Em `projetos/[nome].md`, sempre adicionar ACIMA da seção "Onde parou" existente:
111
+ Em `projetos/[nome].md`:
112
+
113
+ - **Sobrescrever o bloco `## Estado`** inteiro, mantendo os mesmos 6 campos e o teto de 12 linhas. Não empilhar bloco novo: o histórico é a tabela.
114
+ - Atualizar a seção `O que falta` (marcar o que saiu, acrescentar o que entrou).
115
+ - Acrescentar 1 linha ao fim da tabela `Sessões`:
116
+
90
117
  ```markdown
91
- ## Hoje ([data] [sessão])
92
- - [item 1]
93
- - [item 2]
118
+ | [data] | [resumo 1 linha] |
94
119
  ```
95
120
 
96
- Substituir "Onde parou" e "O que falta" com o estado novo.
97
-
98
- Adicionar linha na tabela Sessões (append na última linha da tabela).
121
+ Arquivo sem bloco `## Estado`: criar agora, logo abaixo do título, com o que a sessão apurou.
99
122
 
100
123
  **4. Atualizar bloco do projeto em CEREBRO.md (1 Edit)**
124
+
101
125
  - Usar grep do passo 1 para saber as linhas exatas
102
126
  - Edit cirúrgico apenas nas linhas "Última sessão" e "Pendente"
103
127
 
104
- **5. Atualizar CONTEXT.md (Edit cirúrgico campos alterados)**
105
- - Nunca reescrever o arquivo inteiro
106
- - Editar apenas: data no cabeçalho, pendências em "O que falta", commit hash se mudou
128
+ **5. Se houve decisão relevante:** criar arquivo em `_decisions/` (ver `comandos-rotina-e-captura.md` para o frontmatter e a regra de grep-antes-de-gravar).
129
+ Aprendizado técnico (armadilha de stack, bug não óbvio, pegadinha de ambiente) **não vai para o vault**: vai para a auto-memória do agente. No vault ninguém lia. No Claude Code ela carrega sozinha no início da sessão; em Codex, OpenCode e Gemini o caminho de leitura é o `/memoria` (ver `comandos-pesquisa-e-memoria.md`).
107
130
 
108
- **6. Append em `_index/sessions.md` (1 Edit ou Write se não existir)**
109
- ```markdown
110
- | [data] | [projeto] | [resumo 1 linha] |
111
- ```
112
-
113
- **7. Se houve decisão ou aprendizado relevante:** criar arquivo em `_decisions/` ou `_learnings/` (Write direto, sem Read prévio).
131
+ **6. Higiene do índice (compactação)**
114
132
 
115
- **8. Higiene do índice (compactação)**
116
133
  ```bash
117
134
  wc -l "$VAULT/CEREBRO.md"
118
135
  ```
136
+
119
137
  - Se > 150 linhas: mover o conteúdo mais antigo/menos essencial (projeto ✅ concluído ou ❌ descontinuado com histórico longo, ou entradas de "Decisões recentes" além das ~15 mais novas) para `_index/cerebro-archive.md`, deixando no lugar só 1 linha de referência `[[_index/cerebro-archive]]`. Nunca apagar, só mover.
120
138
  - Se ≤ 150 linhas: pular este passo.
121
139
 
122
- **9. Confirmar em 2 linhas** o que foi salvo.
140
+ ```bash
141
+ grep -c "^| " "$VAULT/projetos/$PROJ.md"
142
+ ```
143
+
144
+ - Tabela Sessões com mais de 15 linhas: mover as mais antigas para `_index/cerebro-archive.md`, sob `## Sessões antigas — [projeto]`, deixando as 15 mais novas no arquivo do projeto. Nunca apagar, só mover.
145
+
146
+ **7. Confirmar em 2 linhas** o que foi salvo.
@@ -164,7 +164,6 @@ claude mcp add <id> [-e VAR=valor ...] -- <command> [args...]
164
164
  # necessário):
165
165
  claude mcp add context7 -- npx -y @upstash/context7-mcp@3.2.2
166
166
  claude mcp add exa -e EXA_API_KEY=$EXA_API_KEY -- npx -y exa-mcp-server@3.2.1
167
- claude mcp add magic -e API_KEY=$MAGIC_API_KEY -- npx -y @21st-dev/magic@0.1.0
168
167
  claude mcp add supabase -e SUPABASE_ACCESS_TOKEN=$SUPABASE_ACCESS_TOKEN -- npx -y @supabase/mcp-server-supabase@0.8.2 --read-only
169
168
  ```
170
169
  Versões acima são as pinadas hoje em `skills-registry.yaml` — confira lá antes de copiar, pode ter mudado. Não sugira o MCP do Playwright: browser é sempre via CLI `agent-browser` neste framework, nunca Playwright.
@@ -1,30 +1,28 @@
1
1
  ---
2
2
  name: impeccable
3
- description: "Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks."
4
- argument-hint: "[{{command_hint}}] [target]"
3
+ description: "Use when the user wants to review, audit, polish, redesign or improve a frontend interface. Covers hierarchy, accessibility, responsive layout, typography, color, motion, UX copy and component consistency. Wizz's self-contained adaptation runs on project evidence and bundled references."
4
+ argument-hint: "[audit|critique|polish|shape|document|adapt|harden] [target]"
5
5
  user-invocable: true
6
- allowed-tools:
7
- - Bash(npx impeccable *)
8
6
  license: Apache 2.0
9
7
  ---
10
8
 
11
- Designs and iterates production-grade frontend interfaces. Real working code, committed design choices, exceptional craft.
9
+ # Impeccable Wizz adaptation
12
10
 
13
- ## Setup (first step, always run before anything else)
11
+ Design and review working interfaces using project evidence. This bundle contains instructions and design rules; it does not ship the upstream CLI, detector, context scripts or native engine. Do not invent commands or claim those checks ran.
14
12
 
15
- You MUST do these steps before proceeding:
13
+ ## Setup
16
14
 
17
- 1. Run `node {{scripts_path}}/context.mjs` once per session. If you've already seen its output in this conversation, do not re-run it. The script either prints the project's PRODUCT.md (and DESIGN.md when present) as a markdown block, or tells you it's missing. Follow whatever it prints. **If it reports `NO_PRODUCT_MD`, stop and follow `reference/init.md` before doing anything else.** If the output ends with an `UPDATE_AVAILABLE` directive, follow it (ask the user once about updating, then continue). It never blocks the current task.
18
- 2. If the user invoked a sub-command (`craft`, `shape`, `audit`, `polish`, ...), you MUST read `reference/<command>.md` next. Non-optional. The reference defines the command's flow; without it you will skip steps the user expects.
19
- 3. Familiarize yourself with any existing design system, conventions, and components in the code. Read at least one project file (CSS / tokens / theme / a representative component or page). **Required even when you've loaded a sub-command reference in step 2.** Don't reinvent the wheel; use what's there when it works, branch out when the UX wins.
20
- 4. Read the matching register reference. **This is non-optional; skipping it produces generic output.** If the project is marketing, a landing page, a campaign, long-form content, or a portfolio (design IS the product), read `reference/brand.md`. If it is app UI, admin, a dashboard, or a tool (design SERVES the product), read `reference/product.md`. Pick by first match: (1) task cue ("landing page" vs "dashboard"); (2) surface in focus (the page, file, or route being worked on); (3) `register` field in PRODUCT.md.
21
- 5. **If the project is brand-new (no existing CSS tokens / theme / committed brand colors found in step 3)**, run `node {{scripts_path}}/palette.mjs` to receive a brand seed color and composition guidance. This is the anchor for your primary brand color. Compose the rest of the palette (bg, surface, ink, accent, muted) around it per the script's instructions. Use OKLCH throughout. **Skip this step only if step 3 found committed brand colors in existing tokens; in that case identity-preservation wins.**
15
+ 1. Read the user's brief, existing PRODUCT.md/DESIGN.md when present, and at least one relevant UI source file (tokens, theme, component or page). Missing documents alone do not make an existing project greenfield.
16
+ 2. Preserve the established identity during refinement. For a requested redesign, choose a new direction while preserving product facts, functionality and user constraints. Explicit user choices take precedence over generic anti-pattern warnings.
17
+ 3. Choose the surface mode: **Persuade** (landing/marketing), **Operate** (app/dashboard), **Read** (docs/articles) or **Experience** (portfolio/gallery). A product can have surfaces in different modes.
18
+ 4. Map the requested action using [routing-rules](references/routing-rules.md). Read [command-workflows](references/command-workflows.md) for the relevant workflow and [design-rules](references/design-rules.md) before reviewing or changing UI.
19
+ 5. For new nontrivial components, invoke `skill:premium-landing-ui-researcher` or `skill:ui-component-curator` to obtain inspected sources. Do not replace source research with generic taste recommendations.
22
20
 
23
- ## Design guidance
21
+ ## Verification
24
22
 
25
- Produce ready-to-ship, production-grade code, not prototypes or starting points. Take no shortcuts unless the user asks for them (when in doubt, ask). Don't stop until arriving at a complete implementation (beautiful, responsive, fast, precise, bug-free, on brand). You take attention to detail seriously: every page, section or component crafted is battle tested using the tools available to you (browser screenshotting, computer use, etc). {{model}} is capable of extraordinary work. Don't hold back.
23
+ Build the authorized change, inspect the affected desktop/mobile states in one batch, fix the observed issues together and confirm once more. Additional passes need a specific unresolved defect. Verify keyboard/focus, responsive overflow, reduced-motion and relevant project checks. If the app cannot run, use current screenshot fixtures and code, and state the limitation.
26
24
 
27
- **Before writing or reviewing any UI code, load `references/design-rules.md`** the ruleset every craft/polish/audit/critique pass is checked against. Skipping it is the most common way this skill produces generic or AI-tell-heavy output.
25
+ Report findings with file/route, observed evidence, impact and proposed correction. Distinguish observed defects from taste preferences. Never claim an automatic detector, browser test or performance measurement without running it.
28
26
 
29
27
  ## Commands
30
28
 
@@ -54,17 +52,14 @@ Produce ready-to-ship, production-grade code, not prototypes or starting points.
54
52
  | `optimize [target]` | Fix | Diagnose and fix UI performance |
55
53
  | `live` | Iterate | Visual variant mode: pick elements in the browser, generate alternatives |
56
54
 
57
- Each command's flow lives at `reference/<command>.md` (e.g. `reference/craft.md`, `reference/live.md` — vendored, per Setup step 2). Plus three management commands: `pin <command>`, `unpin <command>`, and `hooks <on|off|status|...>` — see `references/pin-unpin-and-hooks.md`.
58
55
 
59
- **If the first word matches a command** (table above OR `pin` / `unpin` / `hooks`): load its reference file and follow its instructions. Everything after the command name is the target. **If no argument was given, or the intent doesn't obviously name a command**, load `references/routing-rules.md` for the full routing logic (context-aware menu, signal-based recommendations, intent mapping, fallback general invocation).
56
+ Command names above select the bundled [command-workflows](references/command-workflows.md); they are not shell commands. Management requests (`pin`, `unpin`, `hooks`) use [pin-unpin-and-hooks](references/pin-unpin-and-hooks.md). `teach` aliases `init`.
60
57
 
61
- `teach` is a deprecated alias for `init`: if the user types it, load [reference/init.md](reference/init.md) and proceed as if they ran `init`.
58
+ ## References
62
59
 
63
- ## Reference map load each file when needed
60
+ - [Design rules](references/design-rules.md): visual, interaction and anti-pattern checks.
61
+ - [Routing rules](references/routing-rules.md): map intent to the appropriate workflow.
62
+ - [Command workflows](references/command-workflows.md): executable steps using available project tools.
63
+ - [Management capabilities](references/pin-unpin-and-hooks.md): limits of this instruction-only bundle.
64
64
 
65
- - `references/design-rules.md` general + new-project rules, absolute bans, AI slop test. **Load before producing/reviewing UI code.**
66
- - `references/routing-rules.md` — full routing algorithm for no-argument or ambiguous invocations. **Load when you can't map the request to a table row.**
67
- - `references/pin-unpin-and-hooks.md` — the `pin`/`unpin`/`hooks` management flows. **Load when the user invokes one of those.**
68
- - `reference/<command>.md` (singular — e.g. `reference/craft.md`, `reference/brand.md`) — vendored per-command/per-register flows from the `impeccable` npm package, resolved by Setup steps 2 and 4. Not part of this repo.
69
-
70
- Zero content was cut — every rule, example, and routing detail lives verbatim in its `references/` file.
65
+ Upstream: [pbakaus/impeccable](https://github.com/pbakaus/impeccable). The current upstream skill 4.2.1 uses a native engine; this Wizz adaptation does not imply that engine is installed.
@@ -0,0 +1,35 @@
1
+ # Command workflows
2
+
3
+ Apply only the workflow matching the user's request. Use the existing project tools and evidence; these procedures do not require a separate CLI.
4
+
5
+ ## Shape and build
6
+
7
+ For `shape` or `craft`: inspect the brief and current UI; determine visitor task and surface mode; draft section/component structure and states; resolve missing material decisions; research nontrivial components through the appropriate Wizz research skill. Build when authorized, then run the verification pass described in SKILL.md.
8
+
9
+ ## Audit and critique
10
+
11
+ For `audit`: inspect keyboard/focus, labels, contrast, errors/loading/empty states, responsive overflow, motion preferences and relevant performance evidence. For `critique`: inspect hierarchy, comprehension, navigation, density, typography, brand fit and task completion. Report prioritized findings with exact file/route and evidence. Do not equate a preference with a defect, invent scores or apply fixes during a review-only request.
12
+
13
+ ## Refine and adjust
14
+
15
+ For `polish`, address the observed issues with the highest user impact. Other commands narrow the scope:
16
+
17
+ | Commands | Inspect and change |
18
+ |---|---|
19
+ | typeset, layout | Type hierarchy, readable line lengths, wrapping, spacing, alignment, responsive behavior |
20
+ | colorize, bolder, quieter | Color roles, contrast and intended emphasis within the approved direction |
21
+ | distill, clarify | Unnecessary UI/copy complexity, labels and next-action clarity; preserve factual claims |
22
+ | adapt, harden, onboard | Device states, errors/loading/empty states, localization, first-use guidance |
23
+ | animate, delight, overdrive | Purposeful interaction feedback, timing, reduced-motion, rendering cost |
24
+ | optimize | Measured or directly evidenced performance problems; verify the affected path |
25
+ | extract | Repeated tokens/patterns that merit shared primitives without changing behavior |
26
+
27
+ Inspect the target first, make the authorized edits, then verify those states. Large motion effects still require inspected sources and a fit decision.
28
+
29
+ ## Init and document
30
+
31
+ For `init`, gather known product, audience, purpose and constraints from project/user evidence; ask only for missing material facts. For `document`, extract the actual design system from code and current screenshots. Merge into existing PRODUCT.md/DESIGN.md without discarding unrelated decisions; mark assumptions.
32
+
33
+ ## Live
34
+
35
+ Inspect the affected interface using the available browser and current dev server. Implement scoped visual variants if requested, compare the relevant viewport/states, and keep the chosen variant. If a running app or browser is unavailable, provide a code/static assessment and state what remains unverified. Do not simulate an interactive overlay or claim a visual check occurred.
@@ -92,4 +92,4 @@ If someone could look at this interface and say "AI made that" without doubt, it
92
92
  **Category-reflex check.** Run at two altitudes; the second one catches what the first one misses.
93
93
 
94
94
  - **First-order:** if someone could guess the theme + palette from the category alone, it's the first training-data reflex. Rework the scene sentence and color strategy until the answer isn't obvious from the domain. <!-- rule:skill-slop-first-order-check -->
95
- - **Second-order:** if someone could guess the aesthetic family from category-plus-anti-references ("AI workflow tool that's not SaaS-cream → editorial-typographic", "fintech that's not navy-and-gold → terminal-native dark mode"), it's the trap one tier deeper. The first reflex was avoided; the second wasn't. Rework until both answers are not obvious. The brand register's [reflex-reject aesthetic lanes](reference/brand.md) list catches the currently-saturated families. <!-- rule:skill-slop-second-order-check -->
95
+ - **Second-order:** if someone could guess the aesthetic family from category-plus-anti-references ("AI workflow tool that's not SaaS-cream → editorial-typographic", "fintech that's not navy-and-gold → terminal-native dark mode"), it's the trap one tier deeper. The first reflex was avoided; the second wasn't. Rework until both answers are not obvious. Ground the direction in the user's brief and inspected references instead of swapping one generic aesthetic for another. <!-- rule:skill-slop-second-order-check -->
@@ -1,17 +1,7 @@
1
- # Pin/unpin and hooks management commands
1
+ # Pin, unpin and hooks
2
2
 
3
- Load this file when the user invokes `pin`, `unpin`, or `hooks` (with any argument). Covers: creating/removing standalone command shortcuts, and managing the design detector hook that auto-runs after direct UI file edits.
3
+ The Wizz instruction-only adaptation does not ship the upstream management runtime. `pin`, `unpin` and `hooks` are therefore not executable through this bundle.
4
4
 
5
- ## Pin / Unpin
5
+ If asked to manage them, first inspect whether the project separately installed the official Impeccable runtime. If present, consult its installed help and current official documentation and use only commands it actually supports. If absent, explain the missing capability and prepare an installation plan if requested. Do not install another runtime automatically during UI work.
6
6
 
7
- **Pin** creates a standalone shortcut so `{{command_prefix}}<command>` invokes `{{command_prefix}}impeccable <command>` directly. **Unpin** removes it. The script writes to every harness directory present in the project.
8
-
9
- ```bash
10
- node {{scripts_path}}/pin.mjs <pin|unpin> <command>
11
- ```
12
-
13
- Valid `<command>` is any command from the table above. Report the script's result concisely. Confirm the new shortcut on success, relay stderr verbatim on error.
14
-
15
- ## Hooks
16
-
17
- `{{command_prefix}}impeccable hooks <on|off|status|ignore-rule|ignore-file|ignore-value|reset>` manages the design detector hook for this project. The hook auto-runs the detector after direct UI file edits and surfaces findings as system reminders. Full flow is in [reference/hooks.md](reference/hooks.md); load it when the user invokes `{{command_prefix}}impeccable hooks` with any argument.
7
+ UI audit and polish remain available through the bundled [command-workflows](command-workflows.md). Never report a hook or detector as active based solely on these instructions.
@@ -1,28 +1,11 @@
1
- # Routing rules — how to pick a command
1
+ # Routing rules
2
2
 
3
- Load this file whenever the skill is invoked without an explicit sub-command, or when the user's intent doesn't obviously name one of the commands in the table. Covers: the no-argument menu logic (reading context-signals.mjs and detect.mjs, picking the 2-3 highest-value next commands), first-word command matching, intent-to-command mapping, and the fallback general design invocation path.
3
+ Use the user's requested action and target. A clearly implied action is enough to start; do not ask them to choose a command they already described.
4
4
 
5
- ### Routing rules
5
+ - Review or diagnose: `audit` for technical defects; `critique` for visual/UX reasoning. Report findings without editing unless authorized.
6
+ - Fix or refine existing UI: `polish`, or the specific adjustment command. Preserve existing identity and behavior outside scope.
7
+ - New page or redesign: `shape`, then the authorized build; use the source-research skills before nontrivial UI code.
8
+ - Capture existing context: `document` for design evidence, `init` for product context. Missing PRODUCT.md does not block a narrow fix.
9
+ - No task or target: inspect available project context and recommend up to three useful actions with evidence; ask for the missing objective.
6
10
 
7
- 1. **No argument**: the user is asking "what should I do?" Make the menu context-aware instead of static. Setup has already run `context.mjs`; if that reported `NO_PRODUCT_MD` you are already in init (setup), so finish that and skip this. Otherwise run `node {{scripts_path}}/context-signals.mjs` once and read its JSON, then lead with the **2-3 highest-value next commands**, each with a one-line reason pulled from the signals, followed by the full menu (the table above, grouped by category). **Never auto-run a command; the recommendation is a suggestion the user confirms.**
8
-
9
- Reason over the signals; there is no score to obey:
10
- - `setup.hasDesign` false while `setup.hasCode` true → `document` (capture the visual system).
11
- - `critique.latest` is `null` → the project has never been critiqued; for a set-up project with a real surface, offering `/impeccable critique <surface>` is a strong default.
12
- - `critique.latest` with a low `score` or non-zero `p0` / `p1` → `polish` (it reads that snapshot as its backlog), or re-run `critique` if the snapshot looks stale.
13
- - `git.changedFiles` pointing at one surface → scope `audit` or `polish` to those files specifically, naming them.
14
- - `devServer.running` true → `live` is available for in-browser iteration; if false, don't lead with `live`.
15
- - Otherwise group by intent exactly as init's "Recommend starting points" step does (build new / improve what's there / iterate visually), tailored to `setup.register`.
16
-
17
- **If `scan.targets` is non-empty, run `node {{scripts_path}}/detect.mjs --json <scan.targets joined by spaces>` once** (the bundled detector over local files: no network, no npx). `scan.via` tells you what they are: `git-changes` (the markup/style files in your dirty tree, the most relevant set), `source-dir` (e.g. `src`, `app`), `html`, or `root`. Fold the hits into your picks: many quality / contrast hits → `audit` or `polish`; a specific slop family → the matching command (gradient text or eyebrows → `quieter` / `typeset`, flat or gray palette → `colorize`, and so on). It's a real, current signal that beats guessing. If detect errors or the tree is large and slow, skip it and recommend the user run `audit` themselves; never block the suggestion on it.
18
-
19
- Keep it to 2-3 pointed picks with the exact command to type. The menu stays the fallback; the recommendation is the lede.
20
- 2. **First word matches a command** (table above OR `pin` / `unpin` / `hooks`): load its reference file and follow its instructions. Everything after the command name is the target.
21
- 3. **First word doesn't match, but the intent clearly maps to one command** (e.g. "fix the spacing" → `layout`, "rewrite this error message" → `clarify`, "the colors feel flat" → `colorize`): load that command's reference and proceed as if invoked. If two commands could fit, ask once which.
22
- 4. **No clear command match**: general design invocation. Apply the setup steps, the General rules, and the loaded register reference, using the full argument as context.
23
-
24
- Setup (context gathering, register) is already loaded by then; sub-commands don't re-invoke `{{command_prefix}}impeccable`.
25
-
26
- If the first word is `craft`, setup still runs first, but [reference/craft.md](reference/craft.md) owns the rest of the flow. If setup invokes `init` as a blocker, finish init, refresh context, then resume the original command and target.
27
-
28
- `teach` is a deprecated alias for `init`: if the user types it, load [reference/init.md](reference/init.md) and proceed as if they ran `init`.
11
+ Read [command-workflows](command-workflows.md) for the selected action. Reuse context from the current handoff; do not re-invoke router or maestro. Do not invoke absent detector/context scripts.
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: premium-landing-ui-researcher
3
- description: Pesquisar animações, componentes, referências visuais e padrões de conversão para criar landing pages premium em React, Next.js, Tailwind, shadcn/ui, Framer Motion, Three.js e React Three Fiber. Use quando o pedido envolver analisar projeto existente; classificar nível de complexidade do site (básico a 3D high-end/Signature); escolher componentes/animações; melhorar UI genérica; criar landing page completa, transformar oferta em página estratégica, dashboard SaaS, site de autoridade/portfolio (agência, estúdio, consultoria, marca pessoal, lead passivo), case studies/selected work editoriais, ou experiência 3D cinematográfica para marcas premium; buscar referências em fontes premium (React Bits, Cult UI, Watermelon UI, Skiper UI, 21st.dev via Magic MCP/CLI, outras em references/component-sources.md); ou escolher motion engine (GSAP, anime.js, Framer Motion, Three.js/R3F) para scroll storytelling.
3
+ description: Pesquisar animações, componentes, referências visuais e padrões de conversão para criar landing pages premium em React, Next.js, Tailwind, shadcn/ui, Framer Motion, Three.js e React Three Fiber. Use quando o pedido envolver analisar projeto existente; classificar nível de complexidade do site (básico a 3D high-end/Signature); escolher componentes/animações; melhorar UI genérica; criar landing page completa, transformar oferta em página estratégica, dashboard SaaS, site de autoridade/portfolio (agência, estúdio, consultoria, marca pessoal, lead passivo), case studies/selected work editoriais, ou experiência 3D cinematográfica para marcas premium; buscar referências em fontes premium (React Bits, Cult UI, Watermelon UI, Skiper UI, Componentry, outras em references/component-sources.md); ou escolher motion engine (GSAP, anime.js, Framer Motion, Three.js/R3F) para scroll storytelling.
4
4
  ---
5
5
 
6
6
  # Premium Landing UI Researcher
@@ -9,9 +9,9 @@ Estrategista autônomo de landing pages premium, UI SaaS e experiências visuais
9
9
 
10
10
  ## Gate 1: Source-First (sempre, antes de qualquer código de UI)
11
11
 
12
- Esta skill existe porque escrever shaders, animações, hovers e componentes do zero NÃO é o caminho. O caminho é curar componentes, animações e shaders maduros de fontes profissionais (`modelos lp/` do usuário, React Bits, Cult UI, Ali Imam, Watermelon, StyleUI, Skiper UI e, como fonte PAGA complementar, 21st.dev via Magic MCP e 21st CLI) e adaptar à marca.
12
+ Esta skill existe porque escrever shaders, animações, hovers e componentes do zero NÃO é o caminho. O caminho é curar componentes, animações e shaders maduros de fontes profissionais (`modelos lp/` do usuário, React Bits, Cult UI, Ali Imam, Watermelon, StyleUI, Skiper UI, Componentry e registries públicos) e adaptar à marca.
13
13
 
14
- Regra absoluta: inspecione fontes reais, ofereça opções ao usuário, adapte à marca. Nunca recrie o que já existe maduro. Se uma fonte estiver indisponível (MCP offline, sem rede, sem permissão pra clone), declare isso explicitamente ao usuário antes de cair pro fallback de criar do zero. Nunca cair pro fallback silenciosamente. O mandato completo (anti-patterns e required pattern) está no topo de [source-first-protocol](references/source-first-protocol.md).
14
+ Regra absoluta: inspecione fontes reais, registre evidências e recomende opções, adapte à marca. Nunca recrie o que já existe maduro. Se uma fonte estiver indisponível, registre a limitação e pesquise outra fonte pública ou local antes de justificar uma implementação própria. Nunca cair pro fallback silenciosamente. O mandato completo (anti-patterns e required pattern) está no topo de [source-first-protocol](references/source-first-protocol.md).
15
15
 
16
16
  ## Gate 2: classificar o nível do site (sempre, antes de recomendar componentes)
17
17
 
@@ -31,7 +31,7 @@ Classificar o projeto em um dos 5 níveis (regras, motion permitido/proibido e b
31
31
  2. Classificar o nível do site (Gate 2).
32
32
  3. Definir direção visual e stack.
33
33
  4. Decidir modos extras: dashboard SaaS e/ou Portfolio / Authority Mode.
34
- 5. Checkpoints de fontes: inventário interno, Source-First Protocol completo e confirmação do usuário sobre as fontes escolhidas (Gate 1). Nunca pular silenciosamente.
34
+ 5. Checkpoints de fontes: inventário interno, Source-First Protocol completo e escolha das fontes dentro do escopo autorizado (Gate 1). Nunca pular silenciosamente.
35
35
  6. Se nível 4 ou 5: handoff pro `motion-3d-director` antes de implementar.
36
36
  7. Escrever copy completa e estrutura da página.
37
37
  8. Plano de implementação (handoff pro `implementation-planner` quando aplicável).
@@ -47,9 +47,9 @@ Classificar o projeto em um dos 5 níveis (regras, motion permitido/proibido e b
47
47
  | Handoffs pro motion-3d-director e implementation-planner, regra final do ladder | [handoffs](references/handoffs.md) |
48
48
  | SaaS Dashboard Mode e Portfolio / Authority Site Mode | [dashboard-and-portfolio-modes](references/dashboard-and-portfolio-modes.md) |
49
49
  | Processo obrigatório de 12 passos e checkpoint de honestidade | [mandatory-process](references/mandatory-process.md) |
50
- | Source-First Mandate completo + protocolo em 5 fases (inventário, repos em cache, Magic MCP, 21st CLI, confirmação; 21st = fonte paga complementar) | [source-first-protocol](references/source-first-protocol.md) |
50
+ | Protocolo em 5 fases (inventário, busca pública, cache, evidências, adaptação) | [source-first-protocol](references/source-first-protocol.md) |
51
51
  | Audit Protocol: Pass 1 Taste, Pass 2 Impeccable, Pass 3 Cross-check, Pass 4 A11y/Perf | [audit-protocol](references/audit-protocol.md) |
52
- | Fontes de componentes (React Bits, Cult UI, Ali Imam, Watermelon, StyleUI, Skiper UI, Bklit UI, 21st.dev + 21st CLI), animation engines (GSAP, anime.js), fontes de referência e inspiração visual, Clone Policy, Paid Source Policy | [component-sources](references/component-sources.md) |
52
+ | Fontes de componentes (React Bits, Cult UI, Ali Imam, Watermelon, StyleUI, Skiper UI, Bklit UI, Componentry), animation engines (GSAP, anime.js), fontes de referência e inspiração visual, Clone Policy, Paid Source Policy | [component-sources](references/component-sources.md) |
53
53
  | Stack default, direção visual, paletas, tipografia e regras de seleção de animação | [stack-and-visual-direction](references/stack-and-visual-direction.md) |
54
54
  | Estrutura obrigatória da landing, case studies/portfolio, copywriting, conversão e CTA externo/WhatsApp | [landing-page-strategy](references/landing-page-strategy.md) |
55
55
  | Prompts base (landing completa e hero 3D com scroll) | [prompt-templates](references/prompt-templates.md) |