document-parse

Parse PDFs, DOCX, PPTX, XLSX, and images into text or structured JSON.

2|2|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/mxzinke/atlas --skill document-parse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: document-parse
Source: https://github.com/mxzinke/atlas/tree/main/app/defaults/skills/document-parse
Command: npx skills add https://github.com/mxzinke/atlas --skill document-parse

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Parse unstructured documents to extract text and create structured outputs.

Core Features & Use Cases

  • Parse a single file (PDF, DOCX, PPTX, images) to text or structured JSON.
  • Batch parse directories to process many documents efficiently.
  • Generate page screenshots for visual inspection or layout extraction.
  • Reuse config for repeated tasks with LiteParse.
  • Supports common input formats and OCR options.

Quick Start

Parse a document with LiteParse to extract text and optionally generate structured output or screenshots.

Frequently Asked Questions about document-parse

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

FAQPage Schema
How do I extract text from a PDF or DOCX file locally?

To extract text from a PDF or DOCX locally, use LiteParse to parse unstructured documents. It processes single files or entire directories and outputs extracted text or structured JSON.

Can I batch parse a directory of images and PDFs for text extraction?

Yes, you can batch parse a directory of images and PDFs for text extraction. The Skill applies OCR options to process multiple documents efficiently and generate structured outputs.

Does document parsing support generating page screenshots for visual inspection?

Document parsing supports generating page screenshots for visual inspection. You can extract layout information and capture page images directly from PDFs, DOCX, and PPTX files.

Do I need LiteParse to perform local OCR on unstructured documents?

Yes, you need LiteParse to perform local OCR on unstructured documents. It acts as the required local processing engine to apply OCR options and extract text from images.

What is the best way to convert unstructured PDFs to structured JSON?

The best way to convert unstructured PDFs to structured JSON is by applying local OCR parsing. This Skill extracts text from specified page ranges and formats the output into structured data.

Can I select specific page ranges when parsing a document?

Yes, you can select specific page ranges when parsing a document. The Skill supports page-range selection to target extraction, allowing you to isolate content and save processing time.