word-analysis

npx skills add OpenSenseNova/SenseNova-Skills --skill word-analysis --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# Word Analysis — .docx / .doc ## Environment ```python from docx import Document import os # python-docx is available; for .doc (old format) convert via libreoffice first def load_doc(path): """Load .docx directly; convert .doc to .docx first if needed.""" if path.lower().endswith('.doc'): import subprocess out_dir = os.path.dirname(path) subprocess.run( ['libreoffice', '--headless', '--convert-to', 'docx', '--outdir', out_dir, path], check=True, capture_output=True ) path = path.rsplit('.', 1)[0] + '.docx' return Document(path) ``` --- ## Core Method 1: Full Text Extraction ```python def extract_full_text(doc_path): """Extract all text: paragraphs + table cells, in document order.""" doc = load_doc(doc_path) lines = [] # Iterate paragraphs and tables in body order from docx.oxml.ns import qn for block in doc.element.body: tag = block.tag.split('}')[-1] if tag == 'p': # Paragraph from docx.text.paragraph import Paragraph para = Paragraph(block, doc) text = para.text.strip() if text: lines.append(text) elif tag == 'tbl': # Table from docx.table import Table tbl = Table(block, doc) for row in tbl.rows: row_text = '\t'.join(cell.text.strip() for cell in row.cells) if row_text.strip()