About this skill

Problem context

PDFs often act as isolated information sources in automation pipelines: the body may be flowing text or a scanned image, tables need to be normalized into CSV or Excel, and files may still require merging, splitting, watermarking, or metadata edits. Manual handling is costly and can easily disturb layout, page order, or permission-related details.

Capabilities and workflow

The skill is organized around PDF parsing and output:

Text extraction: Uses pdfplumber to obtain plain text or position-aware structured text, which helps locate fields.
Table recognition: Combines camelot-py and pdfplumber to extract PDF tables into structured data, with CSV / Excel-friendly output.
OCR recognition: Uses pytesseract to handle scanned documents and image-based PDFs, supporting multilingual text extraction.
Format conversion: Uses pdf2image to convert PDFs into images and provides intermediate results for downstream workflows targeting Word or Excel.
Page and security operations: Uses PyPDF2 to merge, split, rotate, delete, encrypt, or decrypt pages, and can also add watermarks or digital signatures.
Metadata: Reads and modifies document properties to support archiving and traceability.

Boundaries and cautions

OCR requires an external Tesseract environment; complex layouts, cross-page tables, encrypted files, or low-quality scans may still affect recognition accuracy. Digital signatures and encryption are document-security operations, so file ownership and permission requirements should be clarified before use.

Screenshots

Use Cases

When processing scanned procurement contracts, run OCR to extract key clauses and merge them into one searchable PDF.
When organizing supplier quote PDFs, use table recognition to export price tables to CSV for reconciliation in Excel.
Before archiving monthly financial reports, batch-delete draft pages, rotate landscape pages, and add confidentiality watermarks.
Read bid document metadata and update author, title, and creation date to keep archive information consistent.

Best For

Legal assistants handling contract archives who need to extract clauses from scans and add confidentiality watermarks.
Financial analysts reconciling supplier data who need to turn PDF quote tables into CSV or Excel.
Office automation engineers maintaining document libraries who need to merge, split, encrypt, and edit PDF metadata.
Overseas operations staff handling multilingual scans who need OCR text extraction for later translation.