An intelligent document processing skill powered by the MinerU API for high-precision OCR and layout analysis of scanned PDFs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install smart-pdf-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 smart-pdf-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 Smart PDF OCR?
Smart PDF OCR is a professional-grade text extraction tool designed to handle the most challenging document digitization tasks. By leveraging the mineru-open-api, this Openclaw Skills integration allows users to convert scanned PDFs, image-based documents, and photographs into searchable and structured text. It is specifically optimized for complex document structures, including academic papers with intricate layouts, mathematical formulas, and detailed tables, making it an essential asset for automated data entry and research workflows.
The skill provides a flexible approach to OCR, offering both a rapid flash-extract mode for smaller files and a high-precision VLM-based extraction for documents requiring deep semantic understanding. Supporting over 50 languages, it ensures global compatibility for diverse document types ranging from legal contracts to historical archives.
Smart PDF OCR Use Cases
- Digitizing physical archives and paper-based historical records into searchable text.
- Extracting structured data from scanned invoices, receipts, and financial statements.
- Converting academic papers and technical journals with complex formulas and multi-column layouts into Markdown.
- Automating the processing of legal contracts and government forms in various languages.
- Transforming photographed documents and whiteboard notes into digital text assets.
How Smart PDF OCR Works
- The skill evaluates the input PDF file size and page count to determine the most efficient extraction path.
- For documents under 10MB or 20 pages, it triggers the flash-extract workflow for rapid results without token consumption.
- For complex or larger documents, it utilizes the full MinerU extraction pipeline with optional VLM (Vision Language Model) support.
- It identifies and processes specific layout elements like tables and formulas based on user-defined flags.
- The extracted text is processed according to the specified language script (e.g., Latin, CJK, Arabic).
- All processed data is organized and stored in a structured local directory for easy access and integration.
Smart PDF OCR Setup
To utilize this skill, you must install the mineru-open-api CLI globally on your system. Run the following command in your terminal:
npm install -g mineru-open-api
Ensure that your environment is configured to allow the Openclaw Skills agent to execute shell commands for interacting with the MinerU API.
Smart PDF OCR Data Schema & Taxonomy
The skill organizes its output using a standardized directory structure to ensure data integrity and easy retrieval:
| Path Component | Description |
|---|---|
~/MinerU-Skill/ |
The root directory for all OCR-related outputs. |
<name>_<hash>/ |
A unique sub-folder created for every specific extraction task to prevent data collisions. |
output/ |
The final destination for extracted text, images, and structured data files. |
--language |
Metadata flag used to define the script type (e.g., ch, en, japan, latin). |
Smart PDF OCR Advanced Features
- Flash-extract mode for zero-token, high-speed processing of smaller PDF files.
- VLM (Vision Language Model) integration for superior layout recognition in academic and technical documents.
- Pipeline model support for no-hallucination guarantees, critical for legal and financial data extraction.
- Comprehensive multi-language support covering over 50 scripts including Cyrillic, Devanagari, and Arabic.
- Intelligent automated output path generation using unique hashes for streamlined document management.
SKILL.md
Loading
Related Openclaw Skills
Code Explore
A specialized skill for inspecting and mapping the structure, logic, and data flow of local codebases without modifying files.
Code-Write
A precision-focused skill for AI agents to implement or modify code in local projects while strictly adhering to existing project styles and handling edge cases.
Code Architect
Code Architect generates minimal, actionable implementation plans and architectural designs optimized for your existing local codebase.
Code Orchestrator
An intelligent task router that coordinates specialized AI agents to handle complex coding lifecycles from exploration to deployment.
Context Usage Checker
A smart utility to monitor, visualize, and manage your AI session's token consumption and remaining context window.
AI PDF Converter
A high-performance AI document processing tool that converts PDFs into structured formats like Markdown, HTML, and DOCX using intelligent layout analysis.
Featured*
