skills.rest
zhboner
zhbonerCOMMUNITY
Explore all skills by this author →
GitHub

pdf

Extract text and tables, render pages, and fill PDF forms with validated coordinates.

Updated Apr 6, 2026
Search Tags:#ocr#pdf#form filling#text extraction#document automation#annotations#bounding boxes
One-click install
npx skills add https://github.com/zhboner/Agent-Skills --skill pdf-zhboner
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/zhboner/Agent-Skills/tree/main/Global-skills/anthropics-skills-pdf
Command: npx skills add https://github.com/zhboner/Agent-Skills --skill pdf-zhboner

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the manual effort of working with PDFs by letting you extract content, manipulate pages, and fill forms with validated, coordinate-based placement.

Core Features & Use Cases

  • PDF text, table, and structure extraction to turn document content into usable text and field-aware layouts.
  • PDF form handling including both fillable forms (field-value based) and non-fillable forms (label/line/checkbox detection with coordinate-driven annotations).
  • PDF conversions and page operations such as rendering pages to images for OCR/visual workflows, plus common transformations like splitting/rotating/merging (as supported by the included workflow guidance).
  • Use Case: You receive a scanned, non-fillable application form as a PDF and need to place answers into the correct fields reliably, with validation of bounding boxes before writing the output.

Quick Start

Tell the Skill to fill the PDF form from your provided field values, and it will generate a filled output PDF after validating the target field areas.

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 document?▼

PDF text and table extraction automates the retrieval of document content by identifying structural layouts. This transforms static PDFs into usable text and field-aware layouts for downstream data processing workflows.

How do I fill a non-fillable PDF form using coordinates?▼

Filling a non-fillable PDF form uses coordinate-based placement of annotations over detected labels, lines, and checkboxes. It validates target bounding boxes before writing answers to ensure correct field placement in the output.

Can I convert PDF pages to images for OCR workflows?▼

Yes, converting PDF pages to images renders visual representations of each page for OCR workflows. This transformation prepares scanned documents for optical character recognition and visual field detection.

Does this PDF form filling approach support structured JSON inputs?▼

Yes, PDF form population requires structured inputs in JSON for form fields. This ensures deterministic script execution and accurate mapping of field values to corresponding fillable or non-fillable PDF areas.

What is the best way to automate placing annotations on scanned PDF forms?▼

Automating PDF annotations involves detecting labels, checkboxes, and lines, then validating their bounding boxes. This coordinate-driven approach guarantees correct placement of answers into target fields of the produced output.

What are the limitations of coordinate-based PDF form filling?▼

Coordinate-based PDF form filling requires strict validation of bounding boxes to prevent misplaced annotations. You must ensure deterministic script execution and accurate label detection, as incorrect coordinates will cause errors in the output.

Related Skills

Explore More Software Engineering Skills→
lanejlanej
40

python

Manage Python projects with uv for dependencies, environments, versions, and scripts.

Community
Intermediate
rkz91rkz91
264

pdf

Extract text and tables from PDFs using Python libraries.

Community
Intermediate
blueskies1818blueskies1818
1

ocr-and-documents

Convert PDFs, scanned documents, and images into searchable text via OCR.

Community
Advanced
1479089714790897
7

pdf

Extract text, tables, and images from PDF documents.

Community
Advanced