The Scanner skill transforms standard document photos into clean, straightened, and professional-looking scanned pages through automatic edge detection and perspective correction.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install scanner
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 scanner 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 Scanner?
Scanner is a specialized technical skill designed to bridge the gap between casual mobile photography and professional document archiving. By leveraging the jscanify engine and OpenCV.js, this Openclaw Skills extension allows developers to automate the process of deskewing, cropping, and cleaning up images of receipts, forms, and papers. It focuses on a browser-first approach, ensuring that high-quality document processing can be integrated into web workflows without the heavy overhead of native dependencies.
The primary value of this skill lies in its ability to handle complex geometric transformations automatically. It identifies document boundaries even at steep angles and re-projects them into a flat, top-down view. This makes the resulting images significantly more legible for humans and far more accurate for downstream processes like OCR or digital archiving.
Scanner Use Cases
- Converting smartphone photos of paper receipts into flat, cropped digital records.
- Automatically correcting the perspective of skewed document photos for better readability.
- Preparing physical forms and handwritten notes for archival or OCR processing.
- Cleaning up document borders to remove busy backgrounds or desktop clutter from images.
- Standardizing document dimensions for digital storage and sharing.
How Scanner Works
- The skill initializes the jscanify engine, prioritizing a browser-based or CDN-loaded environment for maximum efficiency.
- Boundary detection is performed on the raw input image to locate the four corners of the document.
- The skill evaluates the edge detection quality; if contrast is too low, it applies subtle filters to improve boundary visibility.
- A perspective transformation is applied to warp the identified document area into a standardized rectangular frame.
- The final processed image is exported as a separate file, preserving the original photo for data integrity.
Scanner Setup
To integrate this functionality into your project, install the primary dependency via npm:
npm install jscanify
For a quick local preview without global installations, you can serve a simple HTML file containing the required CDN scripts:
npx serve .
Ensure your HTML includes the following scripts for OpenCV and the scanning engine:
<script src="https://docs.opencv.org/4.7.0/opencv.js" async></script>
<script src="https://cdn.jsdelivr.net/gh/ColonelParrot/jscanify@master/src/jscanify.min.js"></script>
Scanner Data Schema & Taxonomy
The Scanner skill follows a strict data handling protocol to ensure no data loss and clear categorization of processed assets:
| Data Type | Handling Method | Purpose |
|---|---|---|
| Input Image | Read-only / Immutable | Preserves the original evidence or source photo. |
| Edge Preview | Temporary Canvas | Generates a highlightPaper visualization for manual verification. |
| Scanned Export | New File Generation | Saves the perspective-corrected result (e.g., 1600x2200px). |
| Metadata | JSON Object | Tracks versioning and OS compatibility via Openclaw Skills standards. |
Scanner Advanced Features
- Multi-agent support when paired with the documents and files skills for automated archiving.
- Dynamic resolution scaling for extraction (e.g., custom 1600x2200 output presets).
- Low-friction CDN integration for zero-install browser environments.
- Automated edge highlighting for real-time visual feedback in user interfaces.
- Intelligent fallback to manual-corner workflows when automated detection fails.
SKILL.md
Loading
Related Openclaw Skills
QR Code Skill
A versatile tool for creating scannable QR codes from text and extracting data from existing QR code images.
Neta Routing & Index
A central navigation and routing hub for managing Neta sub-skills across creative, community, and character-driven workflows.
Super Trend Analysis
A comprehensive technical analysis engine that synthesizes multiple indicators to provide automated market trend scores and visualization reports.
Vinted
A comprehensive AI agent skill designed to automate and professionalize Vinted marketplace operations for buyers and resellers.
l (List)
A high-efficiency alias skill designed to list files, directories, active processes, and system states instantly.
Style Learner
Style Learner analyzes technical and creative documents to extract structural, linguistic, and formatting patterns into reusable style guides.
Featured*
