docparse

Parse PDF, DOCX, PPTX, and XLSX files to extract text and spatial bounding boxes.

10|1|Updated Jun 29, 2026
One-click install
npx skills add https://github.com/mishahanin/heading-os --skill docparse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: docparse
Source: https://github.com/mishahanin/heading-os/tree/main/.claude/skills/docparse
Command: npx skills add https://github.com/mishahanin/heading-os --skill docparse

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the problem of verifying information in complex documents by providing exact, spatially-grounded citations that trace facts directly to their source location on a page.

Core Features & Use Cases

  • Visual Citations: Automatically generates reports that highlight the exact location of cited facts on source document images.
  • Multi-Format Support: Parses PDF, DOCX, PPTX, and XLSX files with spatial awareness.
  • Use Case: Use this when you need to audit a contract or financial report and require proof of where specific claims or data points originate within the source files.

Quick Start

Run the docparse skill on the quarterly-report.pdf file to answer questions about revenue and generate a visual citation report.

Frequently Asked Questions about docparse

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

FAQPage Schema
How do I extract data from a PDF with spatial bounding boxes for verifiable citations?

To extract data from a PDF with spatial bounding boxes, use a parsing skill that maps text to exact source locations. This generates verifiable citation reports by highlighting the precise coordinates of facts within the document.

What is spatial parsing for document analysis and how does it work?

Spatial parsing for document analysis is a technique that extracts text alongside its physical coordinates on a page. It works by mapping query answers to exact source locations, facilitating evidence-based analysis and verifiable citations.

Can I parse PPTX and XLSX files to track facts back to their original page location?

Yes, you can parse PPTX and XLSX files to track facts to their original location. The process supports multi-format parsing with spatial awareness, mapping extracted text and data points to precise bounding boxes within the source files.

Do I need Python to generate visual citations from DOCX documents?

Yes, you need Python installed to generate visual citations from DOCX documents. The spatial coordinate mapping and document parsing required to produce verifiable citation reports rely on a Python-based environment.

What is the best way to audit a financial report and prove where specific claims originate?

The best way to audit a financial report and prove claim origins is using spatially-grounded document analysis. It automatically generates reports that highlight the exact location of cited facts on source document images for verification.

What are the limitations of using spatial parsing for complex document analysis?

A limitation of spatial parsing for document analysis is its dependency on Python-based document parsing. It requires proper formatting within PDF, DOCX, PPTX, or XLSX files to accurately map spatial coordinates and generate verifiable reports.