A high-performance OCR skill for extracting text, tables, and structured data from documents using Azure Document Intelligence.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install azure-doc-ocr
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install azure-doc-ocr using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Azure Document Intelligence OCR?
The Azure Document Intelligence OCR skill provides a robust interface for the Azure Document Intelligence REST API v4.0. As a key component of Openclaw Skills, it enables developers to transform scanned PDFs, images, and handwritten documents into machine-readable formats. Whether you are dealing with complex forms, invoices, or simple text, this skill offers the precision needed for modern AI-driven document workflows.
By integrating this skill, users can leverage prebuilt models specifically trained for various document types. It goes beyond simple character recognition by understanding document structure, which is essential for developers building intelligent automation pipelines within the Openclaw Skills ecosystem.
Azure Document Intelligence OCR Use Cases
- Extracting line items, vendor details, and totals from invoices and receipts for financial automation.
- Converting scanned tables and multi-column reports into structured Markdown for documentation.
- Digitizing handwritten notes and historical records with high accuracy.
- Automating identity verification processes through ID and passport data extraction.
- Processing large batches of diverse documents in a single workflow using Openclaw Skills.
How Azure Document Intelligence OCR Works
- The process begins when a user provides a local document path or a direct URL to the script.
- The skill authenticates with the configured Azure service using specific environment variables.
- Based on the document type, a prebuilt model (like layout, invoice, or read) is selected to optimize extraction accuracy.
- The Azure Document Intelligence service analyzes the file, identifying text blocks, tables, and key-value pairs.
- As part of the Openclaw Skills framework, the script formats the extracted data into text, Markdown, or JSON for the final output.
Azure Document Intelligence OCR Setup
To begin using this skill within the Openclaw Skills environment, first configure your Azure credentials:
export AZURE_DOC_INTEL_ENDPOINT="https://your-resource.cognitiveservices.azure.com"
export AZURE_DOC_INTEL_KEY="your-api-key"
For a single file extraction with structured layout, use:
python scripts/ocr_extract.py document.pdf --model prebuilt-layout --format markdown
To process an entire directory of images or PDFs:
python scripts/batch_ocr.py ./documents/ --workers 4
Azure Document Intelligence OCR Data Schema & Taxonomy
The skill organizes data based on the selected output format and model to ensure compatibility with various data pipelines:
| Component | Description |
|---|---|
| Supported Files | PDF (scanned/digital), PNG, JPG, JPEG, TIFF, BMP |
| Model Options | prebuilt-read, prebuilt-layout, prebuilt-invoice, prebuilt-idDocument, prebuilt-businessCard |
| Output Formats | Plain text (concatenated), Markdown (structured tables/headers), JSON (raw API data) |
| Metadata | The JSON output includes confidence scores, bounding box coordinates, and page metadata |
Azure Document Intelligence OCR Advanced Features
- Handwriting Recognition: Seamlessly extracts handwritten text alongside printed content in the same document.
- Concurrent Batch Processing: Utilize the batch script with multiple worker threads to handle high-volume document repositories quickly.
- Selective Page Extraction: Optimize API usage by targeting specific page ranges within large PDF files.
- Global Language Support: Includes full support for CJK (Chinese, Japanese, Korean) characters and other international languages.
- Layout Analysis: Preserves the visual structure of documents, including complex tables and nested forms, when used with Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
C# Developer
A specialist skill for building modern .NET 8+ applications, cloud-native APIs, and Blazor web apps with senior-level architecture patterns.
C++ Pro
A senior-level engineering skill for developing high-performance, memory-safe applications using modern C++20/23 standards.
Code Documenter
An AI-powered documentation specialist that generates standardized docstrings, comprehensive API specifications, and full developer portals.
Cloud Architect
A senior-level AI skill for designing, migrating, and optimizing multi-cloud infrastructures across AWS, Azure, and GCP.
OKX DEX Market Price API Skill
A specialized skill for fetching real-time, authenticated token price data from the OKX DEX Market Price API v6 across multiple blockchains.
Crypto & Stock Market Data (Node.js)
A high-performance Node.js toolkit for fetching real-time and historical financial data for cryptocurrencies and global stocks without external dependencies.
Featured*
