A high-performance OCR skill that converts scanned PDFs and photographed documents into machine-readable text without requiring an API key.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ocr-document
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-document 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 Document Extraction?
The OCR Document skill is a specialized tool within the Openclaw Skills ecosystem designed to bridge the gap between physical media and digital data. By leveraging the MinerU Open API, it enables AI agents to process non-selectable text from scanned documents, handwritten notes, and image files.
This skill is particularly valuable for developers and researchers who need a friction-less way to ingest data from legacy documents. It eliminates the overhead of manual transcription by providing a direct pipeline for optical character recognition across multiple file formats and sources.
OCR Document Extraction Use Cases
- Processing scanned PDF reports that lack a selectable text layer.
- Converting photos of whiteboard notes or handwritten documents into structured text.
- Extracting text from online image resources directly via URL without manual downloads.
- Improving AI context by feeding it the contents of legacy physical documentation.
How OCR Document Extraction Works
- The user provides a local file path or a URL pointing to a document or image.
- The skill invokes the mineru-open-api flash-extract command to handle the request.
- The document is uploaded to the MinerU cloud API for real-time processing.
- Optical character recognition algorithms identify and extract text based on the specified language hint.
- The processed text is returned to the agent or saved to a designated output directory.
OCR Document Extraction Setup
You can install the necessary dependencies for this Openclaw Skills component using your preferred package manager:
# Install via npm
npm install -g mineru-open-api
# Or install via uv
uv tool install mineru-open-api
# Or install via Go (Linux/macOS)
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api
OCR Document Extraction Data Schema & Taxonomy
The skill manages inputs and outputs according to the following specifications:
| Feature | Details |
|---|---|
| Supported Formats | PDF, PNG, JPG, WebP, BMP, TIFF |
| Size Limits | Maximum 10MB per file |
| Page Limits | Up to 20 pages per document |
| Default Language | Chinese (ch), configurable to English (en) |
| Storage | Files are processed in real-time and not stored post-extraction |
OCR Document Extraction Advanced Features
- Direct URL Support: OCR documents hosted online without local staging.
- Language Hinting: Use the --language flag to optimize extraction accuracy for specific dialects.
- Zero-Auth Workflow: Access powerful extraction capabilities without the need for API keys or user registration.
- Output Management: Automatically save extraction results to specific directories using the -o flag.
SKILL.md
Loading
Related Openclaw Skills
Vector Databases (Deep Workflow)
A professional deep-dive workflow for selecting, optimizing, and operating vector databases for high-performance AI applications.
CLIProxy + OpenClaw
A bridge that transforms subscription-based CLI and OAuth accounts into a unified, OpenAI-compatible API layer for seamless integration with AI agents.
Agent Browser
A high-performance Rust-based headless browser CLI designed for AI agents to interact with the web via structured commands.
Strategic Decision Making
A high-stakes executive-mode skill for diagnosing complex problems and designing definitive strategies with four distinct rigor modes.
Dusk Ascension
A specialized image generation skill that produces ethereal product hero shots using a 1990s high-fashion analog film aesthetic.
rapiddns
A powerful command-line interface for rapid DNS reconnaissance and subdomain enumeration leveraging the RapidDNS API.
METADATA
Featured*
