pdf

Name: pdf
Availability: InStock
Author: liuharry1

Extract text, fill forms, and manipulate pages in PDFs.

4|Updated Mar 14, 2026

Search Tags:#automation #pdf #document-processing #batch-processing #text-extraction #form-filling

Ready to run

npx skills add https://github.com/LiuHarry1/ai_coding_agent_intro --skill pdf-liuharry1

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/LiuHarry1/ai_coding_agent_intro/tree/main/.ai-agent/skills/pdf
Command: npx skills add https://github.com/LiuHarry1/ai_coding_agent_intro --skill pdf-liuharry1

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates PDF processing tasks such as extracting text from pages, filling forms, merging or splitting documents, and annotating PDFs, reducing manual data handling and repetitive tasks.

Core Features & Use Cases

Automate text extraction and table data capture from PDFs for reporting and archival.
Handle forms end-to-end, including filling native and non-fillable fields with validated coordinates.
Merge, split, rotate pages, and apply annotations or watermarks for batch document workflows.
Use case: processing hundreds of invoices to extract totals and vendor details, then generating a consolidated report.

Quick Start

Process a sample PDF to extract text, fill forms, and export a merged document.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I automate PDF text extraction and table data capture for batch processing?▼

Automate PDF text extraction by using pdfplumber to parse pages and capture table data, generating structured outputs for reporting and archival without manual data entry.

Can I fill non-fillable PDF forms using coordinate-based definitions?▼

Fill non-fillable PDF forms by applying validated coordinate-based field definitions to position text accurately, handling both native and scanned document formats reliably.

Does this PDF processing approach work with scanned documents?▼

PDF processing works with scanned documents by leveraging pdf2image and Pillow to render page images, enabling text extraction and form filling for digitized administrative archives.

What's the best way to merge, split, and rotate PDF pages in bulk?▼

Merge, split, and rotate PDF pages in bulk by applying pypdf for page manipulation across batch document workflows, appending annotations or watermarks to standardize outputs.

Do I need Python libraries installed to extract invoice totals and vendor details?▼

Extracting invoice totals and vendor details requires Python libraries including pypdf, pdfplumber, pdf2image, and Pillow to process both native and scanned PDFs accurately.

Why does PDF form filling fail on scanned documents without validation utilities?▼

PDF form filling on scanned documents fails without validation utilities because pixel-based layouts lack native field definitions, requiring coordinate-based mapping and image rendering to ensure reliable results.