pdf

Extracts text, tables, and images from PDFs and handles forms with OCR support.

23|2|Updated May 27, 2026
One-click install
npx skills add https://github.com/zhouguoqing/QianYuan.AIAgenticFramework --skill pdf-zhouguoqing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/zhouguoqing/QianYuan.AIAgenticFramework/tree/main/.agents/skills/pdf
Command: npx skills add https://github.com/zhouguoqing/QianYuan.AIAgenticFramework --skill pdf-zhouguoqing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, pypdfium2, and includes scripts (resource) components.

What problem does it solve?

PDFs often contain valuable information trapped in unstructured text, tables, and forms, making extraction and digitization tedious and error-prone.

Core Features & Use Cases

  • Text extraction from PDFs (including OCR for scanned pages)
  • Form handling: fillable and non-fillable forms, annotations, and data capture
  • Data extraction and basic document processing (tables, images, metadata)
  • Use Case: process invoices, reports, or research documents by extracting key fields and exporting to CSV/JSON

Quick Start

Use this skill to extract text from a PDF and automatically fill or annotate forms with your data.

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 data processing?

Automating PDF text and table extraction pulls unstructured content into editable data. This skill parses text, tables, and images from documents, including scanned pages via OCR, enabling streamlined data capture for invoices and research workflows.

Can I fill out both fillable and non-fillable PDF forms automatically?

Automated form filling supports both fillable and non-fillable PDF forms. The skill handles annotations, coordinate-based field handling, and data capture to populate forms with your extracted data, including robust validation and error reporting.

Does this PDF processing approach support batch processing for administrative workflows?

Batch PDF processing supports administrative, legal, and research workflows by automating data extraction and form digitization across multiple documents. It captures key fields from invoices or reports and exports the structured results to CSV or JSON formats.

What's the best way to digitize scanned PDF documents using OCR?

Digitizing scanned PDF documents via OCR converts image-based text into editable data. This skill applies OCR to scanned pages, extracting text and images to streamline document workflows and enable data capture from non-fillable sources.

How do I export extracted PDF data to structured formats like CSV or JSON?

Exporting extracted PDF data to CSV or JSON transforms unstructured text and tables into structured formats. The skill processes invoices or reports by extracting key fields and exporting the captured data for downstream analysis and integration.

Why does PDF table parsing fail on certain non-fillable forms, and how is it handled?

PDF table parsing fails on non-fillable forms when text is image-based or lacks structural markers. This skill addresses these limitations by applying OCR for scanned pages and using coordinate-based field handling with robust validation and error reporting.