Document Generation & Processing Skill
This skill provides comprehensive capabilities for creating, editing, and extracting content from office documents. It is designed to be used by agents requiring document manipulation capabilities.
Capabilities
1. Document Generation
- Word (.docx): Generate professional reports with headings, paragraphs, bullet points, and tables.
- PowerPoint (.pptx): Create slide decks with titles, content, and consistent layouts.
- Excel (.xlsx): Create spreadsheets with data and basic formatting.
- PDF (.pdf): Generate PDF documents from text content.
2. Document Processing
- Content Extraction: Extract text and structure from uploaded PDF, Word, PowerPoint, and Excel files.
- Format Conversion: Convert between compatible formats.
Usage
This skill exposes a set of Python scripts located in the scripts/ directory.
Python API
from app.skills.common.document_skill.scripts.word_generator import WordGenerator
from app.skills.common.document_skill.scripts.ppt_generator import PPTGenerator
from app.skills.common.document_skill.scripts.excel_generator import excel_generator
from app.skills.common.document_skill.scripts.office_processor import OfficeProcessor
# Example: Generate a Word Document
word_gen = WordGenerator(output_dir="path/to/output")
file_path = word_gen.generate(markdown_content, "filename")
# Example: Extract content
processor = OfficeProcessor()
content = processor.process("path/to/file.pdf")Dependencies
- python-docx
- python-pptx
- openpyxl
- reportlab (for PDF)
- pypdf (for PDF extraction)
Directory Structure
scripts/: Implementation logic.templates/: (Optional) Document templates.