skills.rest
Fergana-Labs
Fergana-LabsOFFICIAL
Explore all skills by this author →
GitHub

pdf

Extract text, tables, and metadata from PDF documents.

27|3|Updated Nov 6, 2025
Search Tags:#data extraction#pdf#form filling#split#merge#document automation#OCR
One-click install
npx skills add https://github.com/Fergana-Labs/claude_agent_desktop --skill pdf-fergana-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/Fergana-Labs/claude_agent_desktop/tree/main/plugins/skills/pdf
Command: npx skills add https://github.com/Fergana-Labs/claude_agent_desktop --skill pdf-fergana-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pytesseract, pdf2image, Pillow, poppler-utils, qpdf, libreoffice, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Tedious manual PDF form filling, time-consuming data extraction, and complex document manipulation often lead to errors and wasted effort. This Skill streamlines these processes, allowing you to manage PDFs at scale with ease.

Core Features & Use Cases

  • Intelligent Form Filling: Automatically complete both fillable and non-fillable PDF forms, saving hours of repetitive data entry and ensuring consistency.
  • Advanced Data Extraction: Precisely extract text, structured tables, and metadata from any PDF, transforming unstructured data into actionable insights.
  • Comprehensive Document Manipulation: Seamlessly merge, split, rotate, and create new PDF documents, streamlining your entire document workflow.
  • Use Case: You receive 50 scanned expense reports monthly. Use this Skill to automatically OCR each PDF, extract the vendor name, date, and total amount, and then compile this data into a structured spreadsheet for accounting, all without manual intervention.

Quick Start

I have a PDF form named 'application.pdf'. It has fillable fields. Extract all the form field information into a JSON file so I can see what fields are available.

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text and tables from PDF files automatically?▼

Text and table extraction from PDFs uses libraries like pdfplumber to parse structured content and pytesseract for OCR on scanned documents, converting unstructured pages into actionable data you can export to spreadsheets or databases.

Can I automatically fill out fillable PDF forms with data?▼

Yes, fillable PDF form automation detects form fields, validates them, and populates them programmatically using pypdf and reportlab, enabling batch processing of forms without manual data entry.

How do I detect and extract metadata from PDF form fields?▼

Form field detection extracts field names, types, and bounding box coordinates from PDFs, giving you a structured inventory of available fields you can map to your data source for automated population.

What's the best way to OCR scanned PDFs and extract vendor information?▼

Scanned PDF OCR uses pytesseract with pdf2image and Pillow to convert image content to text, then extract structured data like vendor names and amounts for downstream processing and accounting automation.

Can I merge, split, and rotate PDF documents in batch workflows?▼

Document manipulation—merging, splitting, and rotating PDFs—is handled through pypdf and qpdf, allowing you to reorganize multi-page documents at scale for streamlined workflows without manual file handling.

Do I need external tools like LibreOffice to handle complex PDF operations?▼

Complex operations leverage poppler-utils and LibreOffice for advanced rendering and conversion tasks, extending capability beyond Python libraries alone for edge cases in document generation and format transformation.

Related Skills

Explore More Content & Communication Skills→
TasiTechTasiTech
9

pdf

Extract text, tables, and form fields from PDF files.

Community
Advanced
nirholasnirholas
443

account-backup

Export X/Twitter account data into a downloadable JSON file.

Community
Intermediate
rovannirovanni
1

PDF Form Filler

Fill PDF forms and extract field values and metadata programmatically.

Community
Intermediate
andebet07-ossandebet07-oss

pdf

Automates PDF text extraction, table extraction, OCR, and form filling.

Community
Advanced