pdf

Fill PDF forms and extract text and table data.

564|70|Updated Jan 25, 2026

Search Tags:#data extraction #pdf #form filling #document automation #annotation #pdf processing

Ready to run

npx skills add https://github.com/ynulihao/AgentSkillOS --skill pdf-ynulihao

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/pdf
Command: npx skills add https://github.com/ynulihao/AgentSkillOS --skill pdf-ynulihao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of filling out PDF forms and extracting data from PDF documents, saving significant manual effort and time.

Core Features & Use Cases

Fillable Form Filling: Programmatically populate fields in PDFs that have interactive form elements.
Non-Fillable Form Filling: Add text annotations to PDFs that lack fillable fields, based on visual analysis and defined bounding boxes.
Data Extraction: Extract text content and structured tables from PDF documents.
Use Case: Automatically process a batch of scanned application forms by extracting applicant information and filling in standardized fields, converting them into a structured dataset.

Quick Start

Use the pdf skill to fill out the form in 'application.pdf' with the provided 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 table data from PDF documents?▼

To extract text and table data from PDF documents, this Skill uses pdfplumber and pdf2image to parse structured content and retrieve tabular information. It automates text extraction from standard PDFs and uses pytesseract for scanned documents.

Can I programmatically fill non-fillable PDF forms without interactive fields?▼

You can fill non-fillable PDF forms by adding text annotations based on visual analysis and defined bounding boxes. This approach requires precise coordinate mapping and validation to accurately place data onto the document.

How do I automate filling interactive PDF forms?▼

Automating interactive PDF form filling is achieved by programmatically extracting data and applying it to specified form fields. The Skill leverages pypdf to identify and populate interactive elements directly within the document.

Does PDF form automation work for batch processing scanned applications?▼

PDF form automation works for batch processing scanned applications by extracting applicant information using OCR and filling standardized fields. It converts unstructured scanned inputs into a structured, automated dataset output.

What is the best way to handle data extraction from scanned PDF forms?▼

The best way to handle data extraction from scanned PDF forms is using OCR via pytesseract. The Skill converts PDF pages to images with pdf2image, then applies OCR to extract text from non-digital documents for downstream processing.

Do I need precise coordinate mapping for non-fillable PDF document automation?▼

Precise coordinate mapping is required for non-fillable PDF document automation because these documents lack interactive fields. The Skill validates bounding boxes to ensure text annotations are accurately positioned on the page.