Daily Scan converts document photos into searchable PDFs with automated OCR-based naming and local retrieval capabilities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install daily-scan
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 daily-scan 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 Daily Scan?
Daily Scan is a specialized utility within the Openclaw Skills ecosystem designed to bridge the gap between physical documents and digital searchable records. By leveraging a local Tesseract OCR engine, it processes document photos to create high-quality, text-searchable PDF files without the need for cloud-based processing, ensuring your data remains private and secure.
The skill excels at automating the administrative overhead of document management. It handles image cleanup—including rotation and contrast enhancement—and intelligently generates filenames based on the document's own headline text. Whether you are archiving a single receipt or compiling multi-page reports, this tool provides a structured, professional workflow for local document digitization.
Daily Scan Use Cases
- Archiving physical receipts and invoices into a searchable month-by-month local storage system.
- Converting multi-page paper contracts into unified, OCR-enhanced PDF files for legal record-keeping.
- Quick retrieval of historical scans using keyword searches or specific dates within the Openclaw Skills environment.
- Improving the readability of low-quality document photos through automated contrast and orientation adjustments.
How Daily Scan Works
- The skill identifies the user intent through specific triggers such as scan, scan multi, or scan find.
- Attached images are collected and pre-processed for document-style cleanup, including straightening and contrast optimization.
- The local Tesseract OCR engine scans the document, supporting both Korean and English text detection.
- A stable filename is automatically generated using a YYYY-MM-DD format combined with extracted headline text from the document top.
- A searchable PDF is created and stored in a structured year/month directory within the local filesystem.
- For retrieval requests, the skill searches the existing archive by date, headline, or OCR keywords to return the relevant file path and title.
Daily Scan Setup
To use Daily Scan effectively, ensure your environment has the required local dependencies installed. This skill relies on Tesseract for OCR and specific Python libraries for image processing within the Openclaw Skills framework.
# Install Tesseract OCR (Example for macOS/Linux)
brew install tesseract # macOS
sudo apt install tesseract-ocr # Linux
# Install required Python packages
pip install opencv-python Pillow reportlab ocrmypdf
Ensure that the bundled helper scripts provided in the scripts/ directory are callable by your host agent.
Daily Scan Data Schema & Taxonomy
Daily Scan organizes data using a time-based hierarchy to ensure scalability and ease of navigation:
- Base Directory:
daily-scan-storage/ - Folder Structure:
YYYY-MM/(e.g.,2023-10/) - Filename Convention:
YYYY-MM-DD-{headline-text}.pdf
| Metadata Component | Source | Description |
|---|---|---|
| Filename | OCR + Date | Generated from the top 2-3 lines of detected text |
| Search Index | OCR Layer | Full-text content stored within the searchable PDF |
| Source Image | Input File | The original photo is preserved alongside the processed result |
Daily Scan Advanced Features
- Multi-page concatenation: Automatically merge multiple sequential photos into a single PDF document.
- Privacy-centric processing: All OCR and PDF generation happens locally, adhering to the security standards of Openclaw Skills.
- Semantic search: Retrieve documents not just by filename, but by the actual text content extracted during the OCR phase.
- Flexible engine support: Includes experimental support for PaddleOCR as an alternative to the stable Tesseract path.
SKILL.md
Loading
Related Openclaw Skills
Gate News Community Scan
A real-time community sentiment analysis tool that monitors X/Twitter discussions and social metrics for crypto assets.
EDID Parser
A comprehensive diagnostic utility for parsing, validating, and analyzing Extended Display Identification Data (EDID) on Linux systems.
Gate Info Risk Check
An AI-powered security auditor for real-time crypto contract risk detection and honeypot prevention.
Gate-Info Token On-Chain Analysis
A specialized tool for deep-diving into cryptocurrency on-chain metrics including holder concentration, transaction flows, and network activity.
Text Art Generator
Generate classic ASCII art and vibrant emoji pixel art for social media, documentation, and creative messaging.
Seedance vs Sora Comparison
A precision comparison tool designed to help creators decide between Seedance and Sora for professional AI video production.
Featured*
