A high-performance OCR tool for extracting text from various image formats using the Tesseract engine.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-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 image-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 Image OCR?
Image OCR is a specialized utility designed to bridge the gap between visual data and text-based processing. By leveraging the industry-standard Tesseract OCR engine, this skill allows users to transform screenshots, scanned documents, and image files into editable text. It is a vital asset within the Openclaw Skills library for developers who need to automate data extraction from non-textual sources.
The skill is built for speed and accuracy, supporting a wide array of common image formats. Whether you are processing a single receipt or batching thousands of documents, this tool provides a clean CLI interface to get the job done efficiently.
Image OCR Use Cases
- Digitizing physical documents, invoices, or business cards into searchable text.
- Extracting code or error messages from screenshots during debugging sessions.
- Automating data entry workflows by piping image text into other Openclaw Skills.
- Processing archival TIFF or BMP files for modern database indexing.
How Image OCR Works
- The user provides the file path of the image to be processed (e.g., PNG, JPEG, TIFF, or BMP).
- Optionally, a language parameter is passed to refine the character recognition accuracy.
- The skill invokes the system's Tesseract binary to analyze the image's layout and characters.
- The recognized text is returned as a standardized string output for immediate use in the terminal or by an AI agent.
Image OCR Setup
To use this skill, you must have the Tesseract OCR engine installed on your local machine. Use the following command for DNF-based systems:
sudo dnf install tesseract
Once the binary is available in your path, you can use the Openclaw Skills interface to trigger the OCR process.
Image OCR Data Schema & Taxonomy
The skill processes image files and outputs plain text. The following table describes the input and output structure:
| Attribute | Type | Description |
|---|---|---|
| Input File | Path | Supported formats: .png, .jpg, .jpeg, .tiff, .bmp |
| Language Flag | String | Optional (e.g., --lang eng) to specify the OCR training data |
| Result | String | The raw text extracted from the image |
| Metadata | JSON | Returns tool-specific metadata through the Openclaw Skills framework |
Image OCR Advanced Features
- Multi-format support including legacy formats like BMP and TIFF.
- Language-specific processing to handle international documents with high precision.
- Seamless integration into bash scripts and automated agentic workflows.
- Lightweight footprint by utilizing existing system-level OCR binaries.
SKILL.md
Loading
Related Openclaw Skills
Git Helper
A specialized AI skill designed to simplify and automate common Git version control operations through optimized command wrappers.
Geo IP
A streamlined utility to retrieve city, region, country, and ISP information for any IP address using the ipinfo.io API.
File Search
A high-performance utility for finding files by name and searching code content using the power of fd and ripgrep.
Email Send Skill
A lightweight utility for sending emails via SMTP using msmtp without the need for a full mail client.
Log Tail
A specialized utility for streaming, filtering, and monitoring systemd journal logs directly from the command line.
Media Player
A specialized skill for triggering and controlling local audio and video playback using the mpv engine through simple commands.
Featured*
