create-genia-os 2.1.1 → 2.2.0

package/template/.genia/skills/documents/docx.md

@@ -1,153 +1,153 @@
-# Skill: /docx
-
-## Metadata
-- **Nome**: Word Document Processing
-- **Comando**: /docx
-- **Agente**: @dev
-- **Categoria**: documents
-- **Versao**: 2.0
-
-## Descricao
-Criacao, edicao e analise de documentos Word com suporte a tracked changes, comentarios, formatacao e extracao de texto.
-
-## Quando Usar
-- Criar novos documentos Word
-- Modificar/editar conteudo
-- Trabalhar com tracked changes
-- Adicionar comentarios
-- Extrair texto de documentos
-
-## Arvore de Decisao
-
-### Ler/Analisar
-→ Usar "Extracao de texto" ou "Acesso XML raw"
-
-### Criar Novo Documento
-→ Usar **docx-js** (JavaScript)
-
-### Editar Documento Existente
-- Documento proprio + mudancas simples → "Edicao OOXML basica"
-- Documento de terceiros → **Workflow de Redlining**
-- Docs juridicos/academicos/empresariais → **Workflow de Redlining**
-
-## Extracao de Texto
-```bash
-# Converter para markdown com tracked changes
-pandoc --track-changes=all documento.docx -o output.md
-```
-
-## Acesso XML Raw
-
-### Desempacotar arquivo
-```bash
-python ooxml/scripts/unpack.py <arquivo.docx> <diretorio>
-```
-
-### Estrutura de arquivos
-- `word/document.xml` - Conteudo principal
-- `word/comments.xml` - Comentarios
-- `word/media/` - Imagens e midia
-- Tracked changes: `<w:ins>` (insercoes) e `<w:del>` (delecoes)
-
-## Criar Novo Documento (docx-js)
-
-```javascript
-import { Document, Paragraph, TextRun, Packer } from 'docx';
-
-const doc = new Document({
-  sections: [{
-    properties: {},
-    children: [
-      new Paragraph({
-        children: [
-          new TextRun({ text: "Titulo", bold: true, size: 32 }),
-        ],
-      }),
-      new Paragraph({
-        children: [
-          new TextRun("Conteudo do documento..."),
-        ],
-      }),
-    ],
-  }],
-});
-
-// Exportar
-const buffer = await Packer.toBuffer(doc);
-fs.writeFileSync("documento.docx", buffer);
-```
-
-## Workflow de Redlining
-
-### 1. Obter markdown
-```bash
-pandoc --track-changes=all arquivo.docx -o atual.md
-```
-
-### 2. Identificar mudancas
-- Agrupar em batches de 3-10 mudancas
-- Metodos de localizacao: secao/heading, paragrafos numerados, grep patterns
-
-### 3. Ler documentacao e desempacotar
-```bash
-python ooxml/scripts/unpack.py arquivo.docx diretorio
-```
-
-### 4. Implementar mudancas em batches
-Usar `get_node` para encontrar nos, implementar mudancas, `doc.save()`
-
-### 5. Reempacotar
-```bash
-python ooxml/scripts/pack.py diretorio documento-revisado.docx
-```
-
-### 6. Verificacao final
-```bash
-pandoc --track-changes=all documento-revisado.docx -o verificacao.md
-```
-
-## Principio: Edicoes Minimas e Precisas
-
-### ERRADO - Substitui sentenca inteira
-```xml
-<w:del><w:delText>O prazo e 30 dias.</w:delText></w:del>
-<w:ins><w:t>O prazo e 60 dias.</w:t></w:ins>
-```
-
-### CORRETO - Marca apenas o que mudou
-```xml
-<w:r><w:t>O prazo e </w:t></w:r>
-<w:del><w:delText>30</w:delText></w:del>
-<w:ins><w:t>60</w:t></w:ins>
-<w:r><w:t> dias.</w:t></w:r>
-```
-
-## Converter para Imagens
-```bash
-# DOCX → PDF
-soffice --headless --convert-to pdf documento.docx
-
-# PDF → JPEG
-pdftoppm -jpeg -r 150 documento.pdf pagina
-```
-
-## Dependencias
-```bash
-# Python
-pip install defusedxml
-
-# Node
-npm install docx
-
-# Sistema
-sudo apt-get install pandoc libreoffice poppler-utils
-```
-
-## Tasks Relacionadas
-- task:criar-contrato
-- task:revisar-documento
-- task:gerar-relatorio-word
-
-## Workflows
-- workflow:revisao-documentos
-- workflow:geracao-contratos
+# Skill: /docx
+
+## Metadata
+- **Nome**: Word Document Processing
+- **Comando**: /docx
+- **Agente**: @dev
+- **Categoria**: documents
+- **Versao**: 2.0
+
+## Descricao
+Criacao, edicao e analise de documentos Word com suporte a tracked changes, comentarios, formatacao e extracao de texto.
+
+## Quando Usar
+- Criar novos documentos Word
+- Modificar/editar conteudo
+- Trabalhar com tracked changes
+- Adicionar comentarios
+- Extrair texto de documentos
+
+## Arvore de Decisao
+
+### Ler/Analisar
+→ Usar "Extracao de texto" ou "Acesso XML raw"
+
+### Criar Novo Documento
+→ Usar **docx-js** (JavaScript)
+
+### Editar Documento Existente
+- Documento proprio + mudancas simples → "Edicao OOXML basica"
+- Documento de terceiros → **Workflow de Redlining**
+- Docs juridicos/academicos/empresariais → **Workflow de Redlining**
+
+## Extracao de Texto
+```bash
+# Converter para markdown com tracked changes
+pandoc --track-changes=all documento.docx -o output.md
+```
+
+## Acesso XML Raw
+
+### Desempacotar arquivo
+```bash
+python ooxml/scripts/unpack.py <arquivo.docx> <diretorio>
+```
+
+### Estrutura de arquivos
+- `word/document.xml` - Conteudo principal
+- `word/comments.xml` - Comentarios
+- `word/media/` - Imagens e midia
+- Tracked changes: `<w:ins>` (insercoes) e `<w:del>` (delecoes)
+
+## Criar Novo Documento (docx-js)
+
+```javascript
+import { Document, Paragraph, TextRun, Packer } from 'docx';
+
+const doc = new Document({
+  sections: [{
+    properties: {},
+    children: [
+      new Paragraph({
+        children: [
+          new TextRun({ text: "Titulo", bold: true, size: 32 }),
+        ],
+      }),
+      new Paragraph({
+        children: [
+          new TextRun("Conteudo do documento..."),
+        ],
+      }),
+    ],
+  }],
+});
+
+// Exportar
+const buffer = await Packer.toBuffer(doc);
+fs.writeFileSync("documento.docx", buffer);
+```
+
+## Workflow de Redlining
+
+### 1. Obter markdown
+```bash
+pandoc --track-changes=all arquivo.docx -o atual.md
+```
+
+### 2. Identificar mudancas
+- Agrupar em batches de 3-10 mudancas
+- Metodos de localizacao: secao/heading, paragrafos numerados, grep patterns
+
+### 3. Ler documentacao e desempacotar
+```bash
+python ooxml/scripts/unpack.py arquivo.docx diretorio
+```
+
+### 4. Implementar mudancas em batches
+Usar `get_node` para encontrar nos, implementar mudancas, `doc.save()`
+
+### 5. Reempacotar
+```bash
+python ooxml/scripts/pack.py diretorio documento-revisado.docx
+```
+
+### 6. Verificacao final
+```bash
+pandoc --track-changes=all documento-revisado.docx -o verificacao.md
+```
+
+## Principio: Edicoes Minimas e Precisas
+
+### ERRADO - Substitui sentenca inteira
+```xml
+<w:del><w:delText>O prazo e 30 dias.</w:delText></w:del>
+<w:ins><w:t>O prazo e 60 dias.</w:t></w:ins>
+```
+
+### CORRETO - Marca apenas o que mudou
+```xml
+<w:r><w:t>O prazo e </w:t></w:r>
+<w:del><w:delText>30</w:delText></w:del>
+<w:ins><w:t>60</w:t></w:ins>
+<w:r><w:t> dias.</w:t></w:r>
+```
+
+## Converter para Imagens
+```bash
+# DOCX → PDF
+soffice --headless --convert-to pdf documento.docx
+
+# PDF → JPEG
+pdftoppm -jpeg -r 150 documento.pdf pagina
+```
+
+## Dependencias
+```bash
+# Python
+pip install defusedxml
+
+# Node
+npm install docx
+
+# Sistema
+sudo apt-get install pandoc libreoffice poppler-utils
+```
+
+## Tasks Relacionadas
+- task:criar-contrato
+- task:revisar-documento
+- task:gerar-relatorio-word
+
+## Workflows
+- workflow:revisao-documentos
+- workflow:geracao-contratos

package/template/.genia/skills/documents/pdf.md

@@ -1,134 +1,134 @@
-# Skill: /pdf
-
-## Metadata
-- **Nome**: PDF Processing
-- **Comando**: /pdf
-- **Agente**: @dev
-- **Categoria**: documents
-- **Versao**: 2.0
-
-## Descricao
-Toolkit completo para manipulacao de PDFs: extrair texto e tabelas, criar novos PDFs, mesclar/dividir documentos e preencher formularios.
-
-## Quando Usar
-- Extrair texto de PDFs
-- Extrair tabelas para Excel/CSV
-- Mesclar multiplos PDFs
-- Dividir PDF em paginas
-- Criar novos PDFs
-- Preencher formularios PDF
-- Adicionar marca d'agua
-- OCR em PDFs escaneados
-
-## Bibliotecas Python
-
-### pypdf - Operacoes Basicas
-```python
-from pypdf import PdfReader, PdfWriter
-
-# Ler PDF
-reader = PdfReader("documento.pdf")
-print(f"Paginas: {len(reader.pages)}")
-
-# Extrair texto
-text = ""
-for page in reader.pages:
-    text += page.extract_text()
-```
-
-### Mesclar PDFs
-```python
-from pypdf import PdfWriter, PdfReader
-
-writer = PdfWriter()
-for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
-    reader = PdfReader(pdf_file)
-    for page in reader.pages:
-        writer.add_page(page)
-
-with open("mesclado.pdf", "wb") as output:
-    writer.write(output)
-```
-
-### Dividir PDF
-```python
-reader = PdfReader("input.pdf")
-for i, page in enumerate(reader.pages):
-    writer = PdfWriter()
-    writer.add_page(page)
-    with open(f"pagina_{i+1}.pdf", "wb") as output:
-        writer.write(output)
-```
-
-### pdfplumber - Extrair Tabelas
-```python
-import pdfplumber
-import pandas as pd
-
-with pdfplumber.open("documento.pdf") as pdf:
-    all_tables = []
-    for page in pdf.pages:
-        tables = page.extract_tables()
-        for table in tables:
-            if table:
-                df = pd.DataFrame(table[1:], columns=table[0])
-                all_tables.append(df)
-
-if all_tables:
-    combined_df = pd.concat(all_tables, ignore_index=True)
-    combined_df.to_excel("tabelas.xlsx", index=False)
-```
-
-### reportlab - Criar PDFs
-```python
-from reportlab.lib.pagesizes import letter
-from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
-from reportlab.lib.styles import getSampleStyleSheet
-
-doc = SimpleDocTemplate("relatorio.pdf", pagesize=letter)
-styles = getSampleStyleSheet()
-story = []
-
-story.append(Paragraph("Titulo", styles['Title']))
-story.append(Spacer(1, 12))
-story.append(Paragraph("Conteudo aqui...", styles['Normal']))
-
-doc.build(story)
-```
-
-## Comandos CLI
-
-### pdftotext (poppler-utils)
-```bash
-pdftotext input.pdf output.txt
-pdftotext -layout input.pdf output.txt  # Preserva layout
-```
-
-### qpdf
-```bash
-qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf  # Mesclar
-qpdf input.pdf --pages . 1-5 -- pages1-5.pdf  # Extrair paginas
-```
-
-## Quick Reference
-
-| Tarefa | Biblioteca | Codigo |
-|--------|------------|--------|
-| Mesclar PDFs | pypdf | `writer.add_page(page)` |
-| Extrair texto | pdfplumber | `page.extract_text()` |
-| Extrair tabelas | pdfplumber | `page.extract_tables()` |
-| Criar PDFs | reportlab | Canvas ou Platypus |
-| OCR | pytesseract | Converter para imagem primeiro |
-| Formularios | pypdf/pdf-lib | Ver forms.md |
-
-## Dependencias
-```bash
-pip install pypdf pdfplumber reportlab pytesseract pdf2image
-```
-
-## Tasks Relacionadas
-- task:extrair-dados-pdf
-- task:gerar-relatorio-pdf
-
-## Workflows
-- workflow:processar-documentos
+# Skill: /pdf
+
+## Metadata
+- **Nome**: PDF Processing
+- **Comando**: /pdf
+- **Agente**: @dev
+- **Categoria**: documents
+- **Versao**: 2.0
+
+## Descricao
+Toolkit completo para manipulacao de PDFs: extrair texto e tabelas, criar novos PDFs, mesclar/dividir documentos e preencher formularios.
+
+## Quando Usar
+- Extrair texto de PDFs
+- Extrair tabelas para Excel/CSV
+- Mesclar multiplos PDFs
+- Dividir PDF em paginas
+- Criar novos PDFs
+- Preencher formularios PDF
+- Adicionar marca d'agua
+- OCR em PDFs escaneados
+
+## Bibliotecas Python
+
+### pypdf - Operacoes Basicas
+```python
+from pypdf import PdfReader, PdfWriter
+
+# Ler PDF
+reader = PdfReader("documento.pdf")
+print(f"Paginas: {len(reader.pages)}")
+
+# Extrair texto
+text = ""
+for page in reader.pages:
+    text += page.extract_text()
+```
+
+### Mesclar PDFs
+```python
+from pypdf import PdfWriter, PdfReader
+
+writer = PdfWriter()
+for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
+    reader = PdfReader(pdf_file)
+    for page in reader.pages:
+        writer.add_page(page)
+
+with open("mesclado.pdf", "wb") as output:
+    writer.write(output)
+```
+
+### Dividir PDF
+```python
+reader = PdfReader("input.pdf")
+for i, page in enumerate(reader.pages):
+    writer = PdfWriter()
+    writer.add_page(page)
+    with open(f"pagina_{i+1}.pdf", "wb") as output:
+        writer.write(output)
+```
+
+### pdfplumber - Extrair Tabelas
+```python
+import pdfplumber
+import pandas as pd
+
+with pdfplumber.open("documento.pdf") as pdf:
+    all_tables = []
+    for page in pdf.pages:
+        tables = page.extract_tables()
+        for table in tables:
+            if table:
+                df = pd.DataFrame(table[1:], columns=table[0])
+                all_tables.append(df)
+
+if all_tables:
+    combined_df = pd.concat(all_tables, ignore_index=True)
+    combined_df.to_excel("tabelas.xlsx", index=False)
+```
+
+### reportlab - Criar PDFs
+```python
+from reportlab.lib.pagesizes import letter
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
+from reportlab.lib.styles import getSampleStyleSheet
+
+doc = SimpleDocTemplate("relatorio.pdf", pagesize=letter)
+styles = getSampleStyleSheet()
+story = []
+
+story.append(Paragraph("Titulo", styles['Title']))
+story.append(Spacer(1, 12))
+story.append(Paragraph("Conteudo aqui...", styles['Normal']))
+
+doc.build(story)
+```
+
+## Comandos CLI
+
+### pdftotext (poppler-utils)
+```bash
+pdftotext input.pdf output.txt
+pdftotext -layout input.pdf output.txt  # Preserva layout
+```
+
+### qpdf
+```bash
+qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf  # Mesclar
+qpdf input.pdf --pages . 1-5 -- pages1-5.pdf  # Extrair paginas
+```
+
+## Quick Reference
+
+| Tarefa | Biblioteca | Codigo |
+|--------|------------|--------|
+| Mesclar PDFs | pypdf | `writer.add_page(page)` |
+| Extrair texto | pdfplumber | `page.extract_text()` |
+| Extrair tabelas | pdfplumber | `page.extract_tables()` |
+| Criar PDFs | reportlab | Canvas ou Platypus |
+| OCR | pytesseract | Converter para imagem primeiro |
+| Formularios | pypdf/pdf-lib | Ver forms.md |
+
+## Dependencias
+```bash
+pip install pypdf pdfplumber reportlab pytesseract pdf2image
+```
+
+## Tasks Relacionadas
+- task:extrair-dados-pdf
+- task:gerar-relatorio-pdf
+
+## Workflows
+- workflow:processar-documentos