A high-performance OCR and document extraction tool utilizing Vision Language Models for complex layouts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ocr-pro
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 ocr-pro 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 Ocr Pro?
Ocr Pro is a professional-grade extraction skill designed for Openclaw Skills, leveraging the powerful MinerU engine developed by OpenDataLab. It provides state-of-the-art text recognition for PDFs and various image formats, handling even the most challenging layouts including multi-column text, tables, and embedded formulas. By utilizing Vision Language Models (VLM), it moves beyond traditional optical character recognition to provide structural understanding of documents, making it an essential tool for digitizing complex archives or enterprise-level document processing within any AI agent workflow.
Ocr Pro Use Cases
- Digitizing scanned PDF documents with high structural accuracy for Openclaw Skills users.
- Extracting data from complex multi-column reports and academic papers where standard OCR fails.
- Converting images of tables or mathematical formulas into machine-readable formats.
- Automating data entry from screenshots and mixed-media documents in professional environments.
- Bulk processing of legacy paper documents into structured digital formats for archival.
How Ocr Pro Works
- The user initiates an extraction command via the CLI or an agent integrated with the Openclaw Skills ecosystem.
- The input file, which can be a local path or a URL, is passed to the MinerU engine.
- The engine applies advanced VLM algorithms to analyze the document layout, identifying text blocks, tables, and figures.
- Optional language hints (such as English or Chinese) are applied to refine the recognition process.
- The processed content is output as structured text to the terminal or saved as a specific file format like .docx to a designated directory.
Ocr Pro Setup
To integrate this skill into your Openclaw Skills environment, install the MinerU CLI using npm or Go:
npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
Authentication is required for extraction features. Obtain a token from the MinerU website and configure it locally:
export MINERU_TOKEN="your-token"
Ocr Pro Data Schema & Taxonomy
Ocr Pro handles a wide variety of input and output configurations to suit professional workflows within Openclaw Skills.
| Feature | Details |
|---|---|
| Supported Inputs | .pdf, .png, .jpg, .jpeg, .jp2, .webp, .gif, .bmp |
| Output Formats | Standard Output (text), Docx (binary), Markdown |
| Language Support | Default 'ch' (Chinese), supports 'en' (English) via hints |
| Advanced Flags | --ocr for text recognition, --model vlm for complex layouts |
Ocr Pro Advanced Features
- VLM-powered recognition for understanding complex visual document hierarchies and mixed-media content.
- Flexible page range selection to target specific sections of large documents.
- Direct URL support allowing for seamless cloud-based document processing without manual downloads.
- Automated table and formula extraction that preserves data integrity for technical and scientific documents.
- High-speed processing optimized for enterprise digitization projects using Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
PDF Analysis
A powerful document intelligence skill for extracting structured content, tables, and formulas from PDFs using MinerU.
Paper Parser
An advanced academic document processor that converts research PDFs into structured Markdown with LaTeX formulas and preserved table layouts.
OpenClaw Bash Safety Validator Primer
A comprehensive security guide and technical primer designed to harden Openclaw Skills against autonomous shell execution risks and injection attacks.
Context Death Spiral Prevention: OpenClaw Compaction Primer
A technical architectural primer designed to help developers identify and prevent reasoning degradation in OpenClaw agents through robust context compaction strategies.
Douyin Orchestrator
An automated workflow engine that downloads, transcribes, and analyzes Douyin videos and notes into structured knowledge.
Douyin Content Analyzer
An AI-driven content analysis module that transforms raw Whisper transcriptions into structured, professional reports with key point extraction.
METADATA
Featured*
