skills.rest
dfpalhano
dfpalhanoCOMMUNITY
Explore all skills by this author →
GitHub

upstage-document-parse

Parse PDFs, images, DOCX, PPTX, and XLSX via the Upstage Document Parse API.

Updated Feb 26, 2026
Search Tags:#ocr#data extraction#pdf#document parsing#image to text#upstage
One-click install
npx skills add https://github.com/dfpalhano/openclaw-workspace --skill upstage-document-parse
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: upstage-document-parse
Source: https://github.com/dfpalhano/openclaw-workspace/tree/main/skills/upstage-document-parse
Command: npx skills add https://github.com/dfpalhano/openclaw-workspace --skill upstage-document-parse

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the extraction of text, tables, figures, and layout information from various document formats, saving users time and effort in manual data processing.

Core Features & Use Cases

  • Multi-format Document Parsing: Supports PDF, images (PNG, JPG, etc.), DOCX, PPTX, XLSX, and HWP.
  • Structured Data Extraction: Extracts text, tables, and figures with bounding boxes.
  • Use Case: Convert a complex PDF report into a structured Markdown or HTML format for easier analysis and integration into other systems.

Quick Start

Use the upstage-document-parse skill to extract markdown from the attached file 'report.pdf'.

Frequently Asked Questions about upstage-document-parse

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

FAQPage Schema
How do I extract text and tables from a PDF document?▼

To extract text and tables from a PDF, this Skill uses the Upstage Document Parse API to parse files and output structured Markdown or HTML. It retrieves text, tables, figures, and layout elements complete with bounding boxes.

Can I parse images and DOCX files for data extraction?▼

Yes, you can parse images and DOCX files for data extraction. The tool supports multi-format document parsing including PDF, PNG, DOCX, PPTX, and XLSX, converting them into structured text or HTML output.

Do I need an API key to parse documents?▼

Yes, you need an API key to parse documents. The operation requires setting the UPSTAGE_API_KEY environment variable and having the curl command-line tool available in your execution environment.

Does document parsing retain layout elements and bounding boxes?▼

Yes, document parsing retains layout elements and bounding boxes. The extraction process captures structural layout information including text, tables, and figures, mapping their exact locations within the original document.

What is the best way to convert a complex PDF report to Markdown?▼

The best way to convert a complex PDF report to Markdown is using this Skill to automate the extraction of text, tables, and figures. It processes the document and outputs structured Markdown for analysis and system integration.

Related Skills

Explore More Data & Analytics Skills→
tanyagraytanyagray

bitbucket-setup

Install and configure the Bitbucket CLI for Bitbucket Cloud workflows.

Community
Intermediate
xberg-ioxberg-io
26

extracting-metadata

Extract titles, descriptions, language, and Open Graph tags from HTML documents.

Official
Intermediate
BinSquareBinSquare
305

pdf

Extract text, tables, and forms from PDF documents using Python libraries.

Community
Advanced
EGAdamsEGAdams

Receipt Scanner Master

Parse receipt images and PDFs into structured line-item data.

Community
Advanced