file-analyst

name	file-analyst
description	Analyze local files via scripts/file_analyst.py. Actions — summarize/contract/datasheet/extract/stats for PDF/DOCX/CSV/XLSX/TXT/JSON/MD; ocr/ocr_translate for images (jpg/png/webp/bmp/tiff) AND scanned PDFs (Tesseract 5.x); pdf_to_md for PDF→Markdown conversion (MarkItDown). Examples — 'summarize --path report.pdf', 'contract --path lease.pdf', 'datasheet --path tpa3255.pdf', 'ocr --path scan.jpg', 'ocr_translate --path image.png --to he', 'pdf_to_md --path report.pdf'. Trigger when asked to read, summarize, extract data from files, analyze a lease/rental contract (use 'contract'), analyze a technical datasheet / IC spec sheet (use 'datasheet'), read text from an image (use 'ocr'), or translate text inside an image (use 'ocr_translate'). CRITICAL: NEVER pass a file path that was not explicitly confirmed by a prior tool output (look for 'saved to' in tool output). Invented file paths will fail. Only use paths that were created by a tool or provided by the user.
metadata	{"clawdbot":{"emoji":"📄","commands":["summarize","extract","convert","stats","check","extract_tables","chart","contract","datasheet","analyze","ocr","ocr_translate","ocr_pdf","redact","batch","pdf_to_md"],"arg_template":"scripts/file_analyst.py {command} {args}","timeout":90,"requires":{"bins":["python"],"python_libs":["PyPDF2","pdfplumber","pdfminer.six","python-docx","openpyxl","pandas","pytesseract","Pillow","deep-translator","pymupdf"]},"install":[{"id":"pip-files","kind":"pip","packages":["PyPDF2","pdfplumber","pdfminer.six","python-docx","openpyxl","pandas","pytesseract","Pillow","deep-translator","pymupdf"],"label":"Install file analysis dependencies (baseline)"},{"id":"pip-ml-extras","kind":"pip","optional":true,"packages":["markitdown"],"label":"Optional ML extras (MarkItDown for PDF→Markdown)"}],"commands_schema":{"summarize":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"extract":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"convert":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"stats":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"check":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"extract_tables":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"chart":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"contract":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"datasheet":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"analyze":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"ocr":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"ocr_translate":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"ocr_pdf":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"redact":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"pdf_to_md":{"properties":{"path":{"type":"string","description":"Path to the file to analyze"},"output":{"type":"string","description":"Output file path (optional)"}},"required":["path"]},"batch":{"properties":{"dir":{"type":"string","description":"Directory to batch process"},"pattern":{"type":"string","default":"*"},"batch_action":{"type":"string","default":"summarize"}},"required":["dir"]}}}}

File Analyst

Read and summarize documents, spreadsheets, and text files locally.

Quick start

# 📄 טקסט ומסמכים
python {baseDir}/scripts/file_analyst.py summarize --path ~/Documents/report.pdf
python {baseDir}/scripts/file_analyst.py summarize --path ~/Documents/report.pdf --pages 5
python {baseDir}/scripts/file_analyst.py extract --path ~/Data/sales.csv --query "top 5 products by revenue"
python {baseDir}/scripts/file_analyst.py convert --path ~/Notes/meeting.docx --format markdown
python {baseDir}/scripts/file_analyst.py stats --path ~/Logs/access.json
python {baseDir}/scripts/file_analyst.py check --path ~/Documents/report.pdf  # בדיקת שלמות קובץ

# 📊 נתונים וטבלאות
python {baseDir}/scripts/file_analyst.py extract_tables --path ~/Data/financial.pdf --output tables.csv
python {baseDir}/scripts/file_analyst.py chart --path ~/Data/sales.csv --x-col date --y-cols revenue,profit --kind line

# 📋 חוזים ומסמכים משפטיים
python {baseDir}/scripts/file_analyst.py contract --path ~/Contracts/lease.pdf        # חוזה שכירות
python {baseDir}/scripts/file_analyst.py contract --path ~/Contracts/job_offer.pdf   # חוזה עבודה
python {baseDir}/scripts/file_analyst.py contract --path ~/Contracts/car_sale.pdf    # חוזה רכב
python {baseDir}/scripts/file_analyst.py contract --path ~/Contracts/nda.pdf         # הסכם סודיות

# 🔧 ניתוח טכני (Datasheets)
python {baseDir}/scripts/file_analyst.py datasheet --path ~/Docs/tpa3255.pdf
python {baseDir}/scripts/file_analyst.py datasheet --path ~/Docs/amplifier.pdf

# 🔍 OCR - חילוץ טקסט מתמונות ו-PDF סרוקים
python {baseDir}/scripts/file_analyst.py ocr --path ~/Pictures/scan.jpg
python {baseDir}/scripts/file_analyst.py ocr --path ~/Pictures/scan.jpg --ocr-engine tesseract
python {baseDir}/scripts/file_analyst.py ocr --path ~/Documents/scanned.pdf
python {baseDir}/scripts/file_analyst.py ocr_pdf --path ~/Documents/scanned.pdf --output extracted.txt
python {baseDir}/scripts/file_analyst.py ocr_translate --path ~/Pictures/sign.png --to he
python {baseDir}/scripts/file_analyst.py ocr_translate --path ~/Pictures/menu.jpg --to en --output menu_en.txt

# 📝 PDF → Markdown (MarkItDown only; --md-engine deprecated)
python {baseDir}/scripts/file_analyst.py pdf_to_md --path ~/Documents/report.pdf

# 🛡️ Redaction — מחיקה פיזית של תוכן ב-PDF (PyMuPDF).
# --pattern הוא regex; כל התאמה מקבלת redact_annot + apply_redactions —

python {baseDir}/scripts/file_analyst.py redact --path ~/Contracts/contract.pdf --pattern  --output redacted.pdf


python {baseDir}/scripts/file_analyst.py batch -- ~/Downloads --pattern  --batch-action summarize
python {baseDir}/scripts/file_analyst.py batch -- ~/Documents/Contracts --pattern  --batch-action contract