A high-performance API skill for detecting, decoding, and classifying QR codes and barcodes from images or URLs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install qrcode-decode
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 qrcode-decode 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 QR Code Detection & Decoding?
This Openclaw Skills component allows AI agents and developers to programmatically read QR codes and barcodes. By providing an image URL or a base64-encoded string, the skill identifies the code's position, decodes the content, and automatically classifies the data type—such as WiFi configurations, vCards, or standard URLs. It is built to integrate seamlessly into automated workflows that require visual data extraction without manual intervention.
Leveraging this skill within your Openclaw Skills environment enables high-speed image processing for vision-based tasks. Whether you are building a tool for mobile receipt processing or a desktop agent that reads QR codes from screenshots, this utility provides the structured data needed to bridge the gap between visual media and actionable text data.
QR Code Detection & Decoding Use Cases
- Extracting data from screenshots or photo uploads in real-time within Openclaw Skills.
- Processing image URLs during automated web scraping or research tasks.
- Automating the classification of QR code types like WiFi settings, contact details, or geolocation.
- Batch-processing multiple images for high-volume data extraction in professional workflows.
How QR Code Detection & Decoding Works
- The user provides an image input through the Openclaw Skills interface via a direct URL or base64 encoding.
- The system sends a POST request to the specialized detection endpoint.
- The backend scans the image to identify 2D codes like QR Codes or DataMatrix structures.
- The skill decodes the embedded content and determines metadata such as type, bounding box coordinates, and confidence levels.
- A structured JSON response is returned to the agent, allowing for immediate programmatic use of the extracted information.
QR Code Detection & Decoding Setup
To utilize this skill within Openclaw Skills, you can interact with the API via simple curl commands. No heavy local installation is required.
# Extract QR content from a remote URL
curl -s -X POST https://data.cli.im/x-deepscan/vision/detect \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com/photo-with-qrcode.jpg"}'
# Extract from a local file using base64 encoding
curl -s -X POST https://data.cli.im/x-deepscan/vision/detect \
-H "Content-Type: application/json" \
-d "{\"image\": \"$(base64 -i photo.jpg)\"}"
QR Code Detection & Decoding Data Schema & Taxonomy
The skill returns a structured response that helps Openclaw Skills understand exactly where and what the data is.
| Field | Type | Description |
|---|---|---|
| content | string | The decoded string from the QR code |
| format | string | Type of code detected (e.g., QR Code, DataMatrix) |
| content_type | string | Auto-classified type (url, wifi, vcard, email, phone, etc.) |
| bbox | object | Bounding box coordinates (x1, y1, x2, y2) for visual localization |
| confidence | float | Accuracy score between 0 and 1 |
Content types are automatically detected based on the data prefix, such as WIFI: for network configurations or BEGIN:VCARD for contact information.
QR Code Detection & Decoding Advanced Features
- Batch processing support allowing up to 10 images or URLs in a single Openclaw Skills request.
- Intelligent content type classification that maps raw strings to usable categories like GEO, SMS, or URL.
- High-precision bounding box (bbox) data for applications requiring visual highlighting or cropping.
- Robust error handling for invalid base64 data, SSRF protection for URLs, and rate-limiting alerts.
- Support for a wide range of image formats including JPEG, PNG, GIF, WebP, and BMP.
SKILL.md
Loading
Related Openclaw Skills
JRJ News & Financial Report Search
A professional financial data skill providing real-time A-Share market news and brokerage research report summaries through authoritative sources.
Balance Sheet Generator
An automated financial tool for generating standardized balance sheets from profit statements and transaction ledgers.
Feishu Agent Config Helper
A specialized configuration assistant that streamlines the integration process between Feishu messaging robots and OpenClaw agents.
Cron Cost Guard
A specialized auditing tool designed to prevent silent token budget burns and model conflicts in AI agent cron configurations.
ComfyUI Triple Upscaler
A professional automation tool for generating high-quality triple-pass image upscaling workflows in ComfyUI.
Financial Statement Generator
An automated tool to transform transaction detail logs into standardized, formatted profit statements.
Featured*
