pdf-processor

Name: pdf-processor
Availability: InStock
Author: Orthogonal

Extract text, tables, and structured data from PDF documents.

12|4|Updated Feb 12, 2026

Search Tags:#automation #pdf #structured-output #document-processing #data-extraction #text-extraction #table-extraction

Ready to run

npx skills add https://github.com/orthogonal-sh/skills --skill pdf-processor-orthogonal-sh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf-processor
Source: https://github.com/orthogonal-sh/skills/tree/main/skills/orthogonal-pdf-processor
Command: npx skills add https://github.com/orthogonal-sh/skills --skill pdf-processor-orthogonal-sh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

PDFs can contain unstructured text and tables that are hard to reuse. This Skill automates extracting text, tables, and other structured data from PDFs, enabling rapid data reuse.

Core Features & Use Cases

Extract text and tables from PDFs into structured formats (JSON, CSV, or Markdown).
Preserve table structures and metadata for analysis and reporting.
Use Case: Convert a batch of invoices or reports into structured data for analytics.

Quick Start

Provide a PDF URL or file path and request extraction of text and tables to obtain structured output.

Frequently Asked Questions about pdf-processor

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

FAQPage Schema

How do I extract tables and text from PDF documents into structured data?▼

To extract tables and text from PDF documents into structured data, you provide a PDF URL or file path to initiate automated parsing. The process uses table recognition and validation to deliver clean outputs in formats like JSON, CSV, or Markdown.

Can I convert a batch of PDF invoices into JSON or CSV for analytics?▼

Yes, you can convert a batch of PDF invoices into JSON or CSV for analytics. The extraction process preserves table structures and metadata, enabling rapid data reuse and structured output for reporting purposes.

Does structured data extraction work with scanned PDFs and research papers?▼

Structured data extraction works with scanned PDFs and research papers. The process applies end-to-end extraction using PDF parsing and table recognition to handle unstructured text and tables, turning them into validated structured formats.

What is the best way to automate table extraction from PDF reports?▼

The best way to automate table extraction from PDF reports is using an end-to-end extraction Skill that applies table recognition and validation. This preserves table structures and metadata for analysis, outputting clean structured data.

What are the limitations of PDF parsing for structured output?▼

Limitations of PDF parsing for structured output involve handling complex unstructured text and tables that are hard to reuse. While parsing and table recognition validate outputs, heavily degraded scanned documents may impact extraction accuracy.