Extract structured text, tables, and document hierarchy from PDFs and images using Azure advanced layout analysis engine.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install azure-content-layout
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-content-layout 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 Content Layout Analyzer?
The Azure Content Layout skill leverages Azure Content Understanding to transform unstructured documents into developer-friendly formats. It serves as a bridge between complex file types like PDFs or Office documents and AI-ready data, providing both clean Markdown for LLM consumption and granular JSON for programmatic analysis. By integrating this into your Openclaw Skills library, you can automate document processing pipelines with high-fidelity layout preservation and robust OCR capabilities.
Azure Content Layout Analyzer Use Cases
- Automating OCR for scanned PDF documents and images.
- Converting complex technical manuals into Markdown for AI RAG pipelines.
- Extracting multi-column tables and hierarchical sections from financial reports.
- Processing mixed-media documents containing both text and figures for automated data entry.
How Azure Content Layout Analyzer Works
- The user provides a document URL or pipes a local file via stdin to the analyzer script.
- The skill sends an asynchronous request to the Azure Content Understanding API endpoint using the configured credentials.
- The system polls the operation status until the document analysis is complete.
- The skill processes the raw API response to generate both GitHub Flavored Markdown and structured JSON data.
- The final output is saved or displayed, preserving document elements like tables, headings, and selection marks.
Azure Content Layout Analyzer Setup
To use this tool within your Openclaw Skills environment, set the following environment variables:
export AZURE_CU_ENDPOINT="https://YOUR_RESOURCE.services.ai.azure.com/"
export AZURE_CU_API_KEY="YOUR_KEY_HERE"
# Optional: Defaults to 2025-05-01-preview
export AZURE_CU_API_VERSION="2025-11-01"
Run the analysis script using Node.js:
node scripts/analyze.mjs --url "https://example.com/document.pdf" --markdown output.md
Azure Content Layout Analyzer Data Schema & Taxonomy
The skill organizes extracted content into two primary formats. The Markdown output preserves document flow, while the JSON output provides spatial and semantic metadata:
| Element | Data Details | Output Type |
|---|---|---|
| Pages | Dimensions, word counts, and line data | JSON |
| Tables | Complex layouts with row and column spans | HTML (in Markdown) |
| Paragraphs | Text blocks with bounding regions and semantic roles | Markdown/JSON |
| Figures | Detected images and charts with coordinates | JSON |
| Sections | Hierarchical document structure (H1-H6) | Markdown |
Azure Content Layout Analyzer Advanced Features
- Support for multi-page documents up to 2,000 pages for enterprise-scale processing.
- Specialized detection of selection marks including checked and unchecked boxes.
- Flexible API versioning to switch between preview features and stable GA releases.
- Asynchronous polling logic optimized to handle processing times ranging from 5 to 60 seconds.
- Extensive file format support including Office documents (DOCX, XLSX, PPTX) and various image types.
SKILL.md
Loading
Related Openclaw Skills
Helium
A comprehensive integration for managing Helium's decentralized wireless networks, LoRaWAN devices, and data processing flows.
Web Search (Serper API)
A real-time web search skill for AI agents that leverages the Serper API to provide Google Search results without regional access restrictions.
WeChat Article Scraper
A powerful utility to extract WeChat Official Account articles and transform them into clean, portable Markdown files with local image support.
Income Tracker
A comprehensive financial management tool for freelancers and creators to track multi-source income with automated currency conversion and visual analytics.
PRD Writer
A professional assistant designed to transform raw product ideas and user stories into comprehensive, structured Product Requirements Documents.
Qidian Reader
A smart novel recommendation engine that uses browser automation to navigate Qidian's rankings and suggest books based on user preferences.
Featured*
