skills.rest
polyuiislab
polyuiislabCOMMUNITY
Explore all skills by this author →
GitHub

pdf

Extract text, tables, images, and form data from PDF documents.

1.2k|53|Updated Dec 24, 2025
Search Tags:#automation#ocr#pdf#pypdf#form-filling#table-extraction#pdf-processing
One-click install
npx skills add https://github.com/polyuiislab/infiAgent --skill pdf-polyuiislab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/polyuiislab/infiAgent/tree/main/skills/pdf
Command: npx skills add https://github.com/polyuiislab/infiAgent --skill pdf-polyuiislab

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Many workflows require manual extraction, annotation, or filling of PDF documents which is slow, error-prone, and difficult to scale; this Skill centralizes PDF operations so users can reliably extract text, tables, images, and complete forms without manual editing.

Core Features & Use Cases

  • Form filling: Fill both native fillable fields and add annotations for non-fillable forms using coordinate-based placement and validation.
  • Data extraction: Extract plain text, layout-preserved text, and structured tables for downstream analysis or CSV export.
  • OCR and image workflows: Convert scanned pages to images and run OCR when text streams are unavailable; extract embedded images and figures.
  • File operations: Merge, split, rotate, encrypt/decrypt, watermark, and batch-process PDFs for archival or processing pipelines.

Quick Start

Extract all text and tables from invoice-q3.pdf and produce a combined CSV of the results.

Frequently Asked Questions about pdf

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

FAQPage Schema
How do I extract tables and text from PDF documents for CSV export?▼

You can extract plain text, layout-preserved text, and structured tables from PDFs using pdfplumber, enabling direct CSV export and downstream analysis without manual data entry.

Can I fill both fillable and non-fillable PDF forms using Python?▼

Yes, you can fill PDF forms by detecting native fillable fields and applying coordinate-based annotations for non-fillable forms, validated through pypdf to ensure accurate placement across documents.

Does this approach support OCR conversion for scanned PDFs?▼

Yes, OCR conversion for scanned PDFs is supported. It converts scanned pages to images using pdf2image and pillow, running OCR as a fallback when text streams are unavailable for text extraction.

What is the best way to merge, split, and watermark PDF files in bulk?▼

The best way to merge, split, and watermark PDF files in bulk is by batching file operations through pypdf, automating archival and processing pipelines reliably without manual editing.

How do I extract embedded images from a PDF file?▼

To extract embedded images from a PDF file, the Skill processes document pages and figures using pillow, isolating embedded images for separate export and downstream image workflows.

Why does PDF text extraction fail on certain scanned documents?▼

PDF text extraction fails on scanned documents when text streams are unavailable. The Skill handles this by converting pages to images with pdf2image and applying OCR fallback to capture text.

Related Skills

Explore More Data & Analytics Skills→
wangx7wangx7

pdf

Extract text and tables from digital and scanned PDFs with OCR.

Community
Intermediate
oalanicolasoalanicolas
54

pdf

Automate PDF extraction, merging, splitting, and form handling via Python libraries.

Community
Advanced
dthuy62dthuy62

ck:pdf

Extract text, tables, and metadata from PDF documents.

Community
Advanced
paxlabs-incpaxlabs-inc
7

ocr-and-documents

Extract text, tables, and images from PDFs and scanned documents.

Community
Intermediate