skills.rest
garochee33
garochee33COMMUNITY
Explore all skills by this author →
WebsiteGitHub

pdf

Extract text, tables, images, and form fields from PDF files.

3|Updated Apr 18, 2026
Search Tags:#ocr#document processing#pdf#encryption#form filling#text extraction#table extraction
One-click install
npx skills add https://github.com/garochee33/DSH --skill pdf-garochee33
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/garochee33/DSH/tree/main/kb/claude/skills/pdf
Command: npx skills add https://github.com/garochee33/DSH --skill pdf-garochee33

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of working with PDFs by helping you read, extract, transform, merge, split, rotate, annotate, secure, and generate documents without manual rework.

Core Features & Use Cases

  • Text and table extraction: Pull readable content and structured tables from PDFs for analysis, reuse, or archival workflows.
  • PDF transformation: Merge files, split pages, rotate documents, add watermarks, and create new PDFs from scratch.
  • Form handling: Fill fillable forms, determine how to handle non-fillable forms, and place text annotations accurately using coordinate-based workflows.
  • Security and recovery tasks: Encrypt or decrypt PDFs, handle scanned documents with OCR, and use validation helpers to verify outputs.
  • Use case: A team can take incoming signed PDFs, extract the needed data, fill a standard form, and produce a finalized document package in one workflow.

Quick Start

Ask the pdf skill to extract text from a PDF, identify whether it is fillable, and fill the form or annotate it as needed.

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 file for data analysis?▼

PDF text and table extraction parses binary files to pull readable content and structured rows using libraries like pdfplumber and pypdfium2. This allows you to convert static document content into actionable data for reuse, analysis, or archival workflows.

Can I fill out a non-fillable PDF form using coordinate-based placement?▼

Non-fillable PDF forms require coordinate-aware text annotation rather than standard field completion. The workflow determines whether a document has fillable fields, then places text annotations accurately using coordinate-based workflows with validation helpers to verify the final output.

What's the best way to merge, split, and encrypt PDF documents in one workflow?▼

Merging, splitting, and encrypting PDF documents is handled through a single transformation workflow using pypdf. You can combine multiple files, separate specific pages, and apply encryption or decryption security measures to produce a finalized document package.

Does this PDF processing approach support OCR for scanned documents?▼

OCR for scanned PDF documents is supported to recover text from image-based files. The process uses command-line tools and Python libraries like pdf2image and pillow to handle scanned document recovery and convert images into readable, actionable data.

How do I generate a new PDF from scratch or add watermarks to existing files?▼

Generating new PDFs and adding watermarks utilizes the reportlab library alongside transformation scripts. You can create documents from scratch, apply watermark overlays to existing pages, and rotate documents within an automated document processing pipeline.

Related Skills

Explore More Software Engineering Skills→
Avi977Avi977

pdf

Automate PDF text extraction, merging, splitting, rotation, watermarking, form filling, and OCR.

Community
Advanced
Pans0020Pans0020

markdown-exporter

Convert Markdown content into DOCX, PPTX, XLSX, PDF, HTML, IPYNB, MD, CSV, JSON/JSONL, XML, and extracted code files.

Community
Advanced
verrio1verrio1

Pdf

Extract text and tables from PDFs and fill forms using Python libraries.

Community
Advanced
guccangguccang
3

ocr-and-documents

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

Community
Advanced