pdf

Extract text, merge documents, and process forms from PDFs using Python libraries.

Updated Mar 7, 2026
One-click install
npx skills add https://github.com/OpenElementsLabs/claude-base --skill pdf-openelementslabs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/OpenElementsLabs/claude-base/tree/main/claude-project-base/skills/pdf
Command: npx skills add https://github.com/OpenElementsLabs/claude-base --skill pdf-openelementslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image.

What problem does it solve?

PDFs are ubiquitous in professional workflows, but extracting text, merging documents, filling forms, and applying OCR can be tedious and error-prone when done manually.

Core Features & Use Cases

  • Text extraction and OCR for both native and scanned PDFs
  • Merge, split, and repackage multi-page documents
  • Fillable and non-fillable form handling, including annotation-based output
  • Convert PDFs to structured text, CSV, or image outputs for indexing and archiving
  • Real-world scenario: automate invoice processing by extracting line items and totals and exporting to downstream systems

Quick Start

Extract text from a PDF and return it as plain text.

Frequently Asked Questions about pdf

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

FAQPage Schema
How do I extract text from scanned PDFs using OCR in Python?

Extract text from scanned PDFs using OCR by rendering pages to images with pdf2image, then applying recognition to digitize content into usable structured outputs. This automation handles both native and scanned PDF documents without manual intervention, converting them to plain text or CSV formats for indexing and archiving.

Can I automate PDF form filling and merge multiple documents end-to-end?

Automate PDF form filling and merge multiple documents end-to-end using pypdf and pdfplumber to manipulate fillable and non-fillable forms, package multi-page documents, and apply annotation-based output. This handles administrative workflows by turning PDFs into structured outputs for downstream systems.

What's the best way to parse line items and totals from invoices in PDF format?

Parse line items and totals from invoices in PDF format by using pdfplumber to extract structured text and tables, converting them to CSV outputs for downstream indexing. This automates invoice processing workflows by exporting extracted data directly to external systems without manual data entry.

Do I need Python libraries like pypdf and pdfplumber to process PDFs?

Yes, you need Python libraries like pypdf, pdfplumber, and pdf2image to parse, manipulate, and render PDF content for extraction, merging, and OCR. These dependencies are required to automate end-to-end document handling and convert PDFs into usable textual and structured outputs.

Does pdfplumber support converting PDFs to structured text and image outputs for archiving?

Yes, pdfplumber supports converting PDFs to structured text, CSV, and image outputs for archiving and indexing. Combined with pdf2image for rendering and pypdf for manipulation, it transforms diverse document types into digitized, searchable formats suitable for archival indexing workflows.

Why does PDF text extraction return garbled output for certain scanned documents?

PDF text extraction returns garbled output for scanned documents when they contain images rather than embedded text. Using pdf2image to render pages and applying OCR resolves this by digitizing image-based content into structured textual outputs, ensuring accurate data extraction across diverse document types.