A powerful OCR tool for AI agents to extract multi-language text from images using the JisuAPI service.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install generalrecognition
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 generalrecognition 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 General Text Recognition OCR?
The General Text Recognition OCR skill enables AI agents to perform high-accuracy Optical Character Recognition (OCR) on images. By integrating with the professional JisuAPI data platform, this skill allows developers to convert visual information from screenshots or photographs into actionable text. It is a core component of the Openclaw Skills library, designed to facilitate multimodal interactions where an agent needs to read and interpret visual data in various languages including Chinese, English, Japanese, and more.
General Text Recognition OCR Use Cases
- Extracting text from user-uploaded screenshots for immediate data processing.
- Automating the transcription of physical documents and business cards into digital formats.
- Enabling AI agents to read and translate text found within image files.
- Assisting in research by converting non-selectable text from images into searchable data.
How General Text Recognition OCR Works
- The AI agent identifies a request to recognize text from an image or local file path.
- The agent executes the Python script, passing the image data as a JSON parameter.
- The skill reads the local image file and automatically converts it to a base64-encoded string if needed.
- A request is sent to the JisuAPI endpoint using the configured JISU_API_KEY.
- The OCR engine processes the image and returns a list of recognized text strings.
- The skill outputs a cleaned JSON result containing the text array for the agent to summarize or analyze.
General Text Recognition OCR Setup
To begin using this skill, you must register at JisuAPI and obtain an AppKey. Configure your environment as follows:
# Linux / macOS
export JISU_API_KEY="your_appkey_here"
# Windows PowerShell
$env:JISU_API_KEY="your_appkey_here"
Ensure you have python3 installed and the skill files located in skills/generalrecognition/.
General Text Recognition OCR Data Schema & Taxonomy
The skill accepts a JSON input and returns structured text data.
| Parameter | Type | Required | Description |
|---|---|---|---|
| path | string | Optional | Local image path (supports JPG/PNG) |
| pic | string | Optional | Pure base64 image string (no prefix) |
| type | string | No | Language type: cnen (default), en, fr, jp, ru, etc. |
Example Output:
{
"result": [
"Extracted line 1",
"Extracted line 2"
]
}
General Text Recognition OCR Advanced Features
- Multi-language support covering 9+ major languages for global application.
- Intelligent file handling that automatically manages base64 conversion for local paths.
- Alias support for input parameters (path, image, or file) to increase agent flexibility.
- Robust error handling with specific codes for image size limits and format errors within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
WordPal
WordPal is an embedded AI English learning companion that uses the FSRS algorithm and personalized memory to help users master vocabulary through interactive chat.
Juejin Hot Trend
A specialized tool for extracting technical summaries, engagement metrics, and emerging trends from the Juejin developer community.
Zhaopin Hot Trend Analyst
A specialized tool for extracting and analyzing public job listings and company profiles from Zhaopin to identify recruitment trends.
IdealSpot
An advanced location intelligence skill for analyzing demographics, consumer behavior, and traffic data to optimize physical business locations.
Parser
A high-performance utility for parsing and transforming JSON, CSV, XML, and log files into structured data.
Perplexity Search
A sophisticated research skill integrating Perplexity Sonar models to provide citation-backed web answers and deep analytical reports.
METADATA
Featured*
