docstrange

Convert PDFs and images to Markdown, JSON, CSV, or HTML with confidence scores.

1|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/xukrutdonut/openclaw-skills --skill docstrange
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: docstrange
Source: https://github.com/xukrutdonut/openclaw-skills/tree/main/docstrange
Command: npx skills add https://github.com/xukrutdonut/openclaw-skills --skill docstrange

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

DocStrange automates extraction of structured content from documents: converting PDFs, images, and other file types to Markdown, JSON, CSV, or HTML with confidence scoring. It reduces manual data-entry effort and OCR workload.

Core Features & Use Cases

  • Markdown extraction: convert documents to clean Markdown with embedded structure.
  • JSON data extraction: extract fields with confidence scores for validation.
  • Table extraction: export tables as CSV for analytics.
  • Use Case: When processing hundreds of invoices, DocStrange extracts key fields like invoice_number, date, and total_amount into a CSV for accounting.

Quick Start

Process your first document by providing a file to the DocStrange API; returns Markdown content, with optional JSON or CSV in a single request.

Frequently Asked Questions about docstrange

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

FAQPage Schema
How do I extract data from PDF invoices into CSV or JSON?

To extract data from PDF invoices into CSV or JSON, you can use an automated document extraction tool to capture fields like invoice numbers and totals. This process converts uploaded files or URLs into structured formats with confidence scores for validation.

What is the best way to convert PDF documents to Markdown format?

Converting PDF documents to Markdown is best handled by automated extraction tools that transform files into clean Markdown with embedded structure. This approach reduces manual data-entry effort and OCR workload while preserving document formatting.

Can I use an OCR API to extract tables from images and export them as CSV?

Yes, you can use an OCR API to extract tables from images and export them as CSV for analytics. This automated extraction process handles OCR-heavy workflows and outputs structured table data from uploaded image files.

Do I need an API key to automate structured data extraction from contracts?

Yes, an API key is required to automate structured data extraction from contracts. The extraction API processes uploaded contract files or URLs and returns structured data with optional metadata and bounding boxes.

Does automated document extraction support multiple output formats in a single request?

Automated document extraction supports requesting multiple output formats in a single API request. You can retrieve Markdown content alongside JSON or CSV outputs, with options for fields selection and confidence scores.