A professional OCR skill that extracts text data from identification documents like ID cards, passports, and driver's licenses into structured JSON.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install idcardrecognition
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 idcardrecognition 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 ID Card Recognition OCR?
The ID Card Recognition OCR skill is a robust tool designed to integrate high-accuracy Optical Character Recognition (OCR) into your automated workflows. By leveraging the JisuAPI platform, this skill allows AI agents to identify and extract critical information from a wide range of official documents, including Chinese second-generation ID cards, passports, and driver's licenses. It is an essential component for developers building Openclaw Skills that require reliable document processing and identity verification.
This skill transforms visual information into actionable data, returning fields such as name, gender, nationality, birth date, and identification numbers. It supports both local file paths and base64-encoded image strings, making it flexible for various deployment environments and front-end integrations.
ID Card Recognition OCR Use Cases
- Automating identity verification by extracting names and ID numbers from user-uploaded photos.
- Streamlining registration processes for travel and transit by digitizing passports and HK/Macau passes.
- Processing automotive insurance claims by automatically reading driver's licenses and vehicle registrations.
- Reducing manual data entry errors in financial or administrative systems through direct OCR extraction.
How ID Card Recognition OCR Works
- The AI agent receives an image file path or a base64 string representing an identification document.
- The skill identifies the specific document type to assign the correct typeid (e.g., 2 for a front-facing Chinese ID card).
- The image data is sent to the JisuAPI recognition endpoint via a secure Python script.
- The JisuAPI service processes the image and returns a structured JSON object containing the recognized text fields.
- The skill parses the result and provides the structured data back to the Openclaw Skills agent for natural language summarization or database entry.
ID Card Recognition OCR Setup
To use this skill, you must obtain an API key from JisuAPI and configure it in your environment.
# For Linux / macOS
export JISU_API_KEY="your_appkey_here"
# For Windows PowerShell
$env:JISU_API_KEY="your_appkey_here"
You can then run the script directly via the command line:
python3 skills/idcardrecognition/idcardrecognition.py '{"path":"my_id_card.jpg","typeid":2}'
ID Card Recognition OCR Data Schema & Taxonomy
| Field | Type | Description |
|---|---|---|
name |
string | The full legal name recognized on the document. |
number |
string | The unique identification number or document ID. |
address |
string | The residential or registered address listed. |
birth |
string | Date of birth in YYYY-MM-DD format. |
typeid |
integer | Mandatory ID representing the document type (e.g., Passport, License). |
portrait |
string | Base64 encoded string of the cropped portrait photo. |
ID Card Recognition OCR Advanced Features
- Support for multi-document recognition including military IDs, residency permits, and household registers.
- Built-in image pre-processing that converts local files to base64 automatically before transmission.
- Granular error reporting for common issues such as file size limits, invalid formats, or recognition failures.
- Capability to handle raw base64 inputs directly for high-performance Openclaw Skills integrations.
SKILL.md
Loading
Related Openclaw Skills
Yuque Skill for AI Agents
A powerful integration that enables AI agents to interact with Yuque knowledge bases for document management and content operations.
MoDora PDF Analysis Skill
A specialized skill for analyzing PDF documents through a remote MoDora HTTP service using secure, environment-based credential management.
Handoff Protocol V2
A high-efficiency state transfer protocol designed to freeze, encapsulate, and resume AI agent workflows across different sessions.
Interzoid
Interzoid provides comprehensive global data verification, standardization, and enrichment services to improve data quality for AI agents and applications.
Self-Improvement Agent Skill
A sophisticated logging and feedback framework that enables AI coding agents to capture errors and user corrections for continuous autonomous improvement.
Baidu Map Hot Trend
An automation skill for Baidu Maps designed to extract point-of-interest data, compare transit routes, and manage geographic coordinates.
METADATA
Featured*
