document-parsing

Extract structured JSON data from PDFs, images, and office files.

2|Updated Jun 26, 2026
One-click install
npx skills add https://github.com/sxd007/investigation-ontology --skill document-parsing-sxd007
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: document-parsing
Source: https://github.com/sxd007/investigation-ontology/tree/main/skills/document-parsing
Command: npx skills add https://github.com/sxd007/investigation-ontology --skill document-parsing-sxd007

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of converting unstructured raw documents like PDFs, scans, and images into reliable, structured JSON data that is ready for audit and analysis.

Core Features & Use Cases

  • Multi-Format Parsing: Automatically routes documents (invoices, contracts, bank statements) to the appropriate extraction path, whether via OCR or direct AI reading.
  • Versioned Auditing: Maintains a strict append-only versioning system for parsed results, ensuring every change is traceable and reviewable.
  • Quality Assurance: Performs field-level confidence scoring and triggers human review workflows when data quality falls below defined thresholds.

Quick Start

Use the document-parsing skill to analyze the raw document located in the current case directory and generate a structured JSON output.

Frequently Asked Questions about document-parsing

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

FAQPage Schema
How do I extract structured data from PDFs and images for audit workflows?

To extract structured data from PDFs and images for audit workflows, this skill routes raw documents through OCR or direct AI analysis to generate reliable, structured JSON output. It supports diverse formats including invoices, contracts, and bank statements.

What is the best way to parse invoices and bank statements into JSON?

The best way to parse invoices and bank statements into JSON is using automated document routing that directs raw files to the appropriate extraction path. It ensures data integrity through field-level confidence scoring and triggers human review when quality falls below defined thresholds.

Does document parsing support versioned output for traceable investigations?

Yes, document parsing supports versioned output for traceable investigations by maintaining a strict append-only versioning system. This ensures every change to the parsed structured data is traceable and reviewable.

How does confidence scoring work during unstructured document extraction?

Confidence scoring during unstructured document extraction works by performing field-level quality assessments on the parsed data. It automatically triggers integrated human review workflows when data quality falls below defined thresholds.

Can I use OCR to process scanned office files into structured formats?

Yes, you can use OCR to process scanned office files into structured formats. The system automatically routes raw documents, including scans and images, to the appropriate extraction path based on the file type.