Fill PDF forms and process documents with Python-based CLI scripts.
npx skills add https://github.com/tfriedel/claude-office-skills --skill pdf-tfriedel
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/tfriedel/claude-office-skills/tree/main/public/pdf Command: npx skills add https://github.com/tfriedel/claude-office-skills --skill pdf-tfriedel
This Skill liberates you from the repetitive and often frustrating manual tasks associated with PDF documents, such as filling out forms, extracting information, or merging/splitting files. It streamlines document workflows, saving significant time and reducing human error.
from pypdf import PdfReader
reader = PdfReader("document.pdf") print(f"Pages: {len(reader.pages)}")
text = "" for page in reader.pages: text += page.extract_text() print(text)
High-intent search queries and answers about installing and using this skill.
Automated form filling extracts fillable field metadata from PDFs, then programmatically populates those fields with your data using libraries like pypdf and reportlab. This eliminates manual data entry across batches of forms, whether fillable or scanned, and outputs completed PDFs ready for storage or processing.
Yes. This Skill performs OCR on scanned PDFs using pytesseract and pdf2image to convert image-based pages into machine-readable text and structured tables, then extracts that data programmatically. This transforms unstructured scanned documents into usable information for databases or reports.
Batch PDF manipulation merges multiple documents, splits large files into individual pages, rotates pages, and extracts metadata using pypdf and reportlab. This approach handles high-volume document workflows programmatically, reducing manual file handling and enabling automated distribution or archival.
No. This Skill detects fillable fields automatically and applies the appropriate filling method—programmatic for fillable forms, annotation-based for non-fillable ones. A single workflow processes mixed form types without manual intervention.
Yes. PDF generation creates new documents from scratch with custom text, layouts, and styling using reportlab. Combined with form filling and data extraction, this enables end-to-end automation: ingest source data, process it, and output formatted reports or completed forms.
Complex layouts and encrypted PDFs may require additional validation of bounding boxes and field coordinates to ensure accurate filling and extraction. The Skill handles standard PDFs reliably; edge cases with unusual encoding or heavy encryption may need preprocessing or manual validation steps.
ticruz38Export categorized expenses to IRS-ready CSV and PDF formats.
frumu-aiConvert PDF, CSV, Excel, and TXT instrument files to ASM JSON or CSV.
Project-N-E-K-OAutomate PDF manipulation and data extraction using Python libraries.
eesha000009-devExtracts text, tables, and form data from PDF documents.
