pdf

Extract text, tables, and images from PDF documents and perform transformations.

Updated May 5, 2026

Search Tags:#ocr #pdf #form filling #text extraction #pdf manipulation #table extraction #annotation placement

Ready to run

npx skills add https://github.com/XCmiaow/cc-deploy --skill pdf-xcmiaow

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/XCmiaow/cc-deploy/tree/main/skills/pdf
Command: npx skills add https://github.com/XCmiaow/cc-deploy --skill pdf-xcmiaow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, pytesseract, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the manual burden of reading, extracting, and editing PDF documents by providing repeatable workflows for text/tables extraction and form handling.

Core Features & Use Cases

Text and Table Extraction: Extract readable text and tables from PDFs for downstream analysis.
PDF Transformations: Merge, split, rotate pages, and modify document content in a structured way.
Form Handling (Fillable + Non-fillable): Detect fillable fields; otherwise place annotations using coordinate-driven placement, including for scanned/OCR workflows.

Quick Start

Tell the assistant to extract text and tables from a file named report.pdf and return the extracted results for your next step.

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 a PDF for downstream analysis?▼

Extract text and tables from a PDF by using parsing libraries to read document content and return structured outputs. This handles readable text and table extraction for immediate downstream analysis.

What is the best way to automate fillable PDF form filling?▼

Automate fillable PDF form filling by detecting interactive fields and applying transformations using PDF parsing libraries. This detects fillable fields automatically and populates them for reliable form handling workflows.

How do I place annotations on non-fillable or scanned PDFs?▼

Place annotations on non-fillable PDFs using coordinate-driven placement and validate bounding boxes. For scanned PDFs, convert pages to images and apply OCR before performing annotation workflows.

Does PDF OCR work with scanned documents that need image conversion?▼

Yes, PDF OCR works with scanned documents by converting pages to images using image conversion libraries, then applying optical character recognition. This extracts readable text from scanned PDF documents.

What are the limitations of coordinate-driven annotation placement in PDFs?▼

Coordinate-driven annotation placement in PDFs requires validating bounding boxes to ensure reliable positioning. Without proper coordinate validation, annotations may misalign, especially across scanned PDFs.