A sophisticated tool for converting visual and web-based documents into structured, tagged Markdown notes that automatically sync to your Obsidian vault.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-breaker
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 image-breaker 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 Image Breaker?
Image Breaker is a robust content extraction utility designed to bridge the gap between raw data sources and organized personal knowledge management. By leveraging advanced vision and web scraping capabilities, this skill allows users to process screenshots, PDFs, and URLs into high-quality, formatted Markdown notes. It is a core component within the Openclaw Skills ecosystem, enabling developers, researchers, and biohackers to capture information from diverse formats without the need for manual transcription.
The skill goes beyond simple OCR by intelligently structuring content into logical sections, such as tables for numerical data and bulleted key points. This ensures that every piece of information extracted is actionable, searchable, and ready for long-term storage in a digital garden or research repository.
Image Breaker Use Cases
- Converting Labcorp or bloodwork PDF results into structured data tables for health tracking.
- Turning screenshots of technical documentation or research papers into searchable Markdown notes.
- Processing web URLs to extract key takeaways and reference ranges into a personal knowledge base.
- Automating the ingestion of business documents or marketing materials into specific project directories.
- Archiving academic papers by DOI for cross-referencing within an Obsidian vault.
How Image Breaker Works
- Extract: The skill utilizes web_fetch for URLs or advanced image analysis tools for screenshots and PDFs to pull raw text and visual data.
- Structure: It parses the raw content into a standardized Markdown template, organizing it into an overview, key points, and detailed subsections.
- Metadata: The system automatically assigns up to three relevant tags (e.g., research, longevity, protocols) and generates YAML frontmatter for easy indexing.
- Save: The resulting file is saved to a designated local workspace directory, intelligently selected based on the content type.
- Sync: It triggers a synchronization script to ensure the new note is immediately available in the user's Obsidian vault for cross-linking.
Image Breaker Setup
To effectively use this part of the Openclaw Skills library, ensure you have the obsidian-sync skill configured in your environment.
# Ensure dependencies for image and web processing are available
pip install requests
# Configure your Obsidian vault path within your environment variables
# or ensure the sync script is located at:
# skills/obsidian-sync/scripts/sync_to_obsidian.py
Image Breaker Data Schema & Taxonomy
The skill organizes data using a strict Markdown schema with integrated metadata for maximum compatibility with Openclaw Skills workflows.
| Field | Type | Description |
|---|---|---|
| date | String | ISO-8601 formatted date of extraction. |
| tags | List | Up to 3 auto-assigned categories (e.g., bloodwork, research). |
| source | String | Original URL or filename of the document. |
| type | String | Static value image-breaker-note for database filtering. |
Image Breaker Advanced Features
- Intelligent Tagging: Uses context-aware analysis to assign specific tags for niches like longevity, performance, and clinical data.
- Multi-Skill Integration: Functions seamlessly with Paper Fetcher to process academic documents via DOI.
- Automated Table Generation: Converts complex numerical data from images into clean, readable Markdown tables.
- Dynamic Routing: Automatically selects the most appropriate output directory (e.g., research/papers/ vs projects/business-docs/) based on document classification.
SKILL.md
Loading
Related Openclaw Skills
Cortana Persona
A specialized AI persona skill that transforms your assistant into Cortana, a witty and tactical partner focused on high-performance missions and biohacking.
Medical Triage
An AI-driven classification engine that prioritizes medical messages into critical, urgent, or routine categories based on symptom severity and clinical context.
Medical Entity Extractor
A specialized clinical NLP tool for extracting structured medical data from unstructured patient messages.
Copilot CLI
A powerful CLI bridge to GitHub Copilot enabling automated code generation, file editing, and shell task execution using cutting-edge LLMs.
Paper Fetcher
A dedicated research tool that automatically retrieves and organizes academic papers from Sci-Hub using DOI identifiers.
Research Automation
An automated web research system for discovering and organizing the latest developments in peptides, longevity science, and biohacking protocols.
Featured*
