A smart OCR tool that automatically detects image types and extracts structured content into high-quality Markdown format.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-content-extractor
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-content-extractor 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 Content Extractor?
The Image Content Extractor is a versatile technical tool designed to bridge the gap between visual data and structured documentation. As a key component of Openclaw Skills, it provides a unified interface for extracting text and structure from terminal screenshots, technical documents, and general images. It uses a modular architecture to apply specific processing logic based on the detected content type, ensuring high-fidelity extraction of code blocks, headers, and lists.
This skill goes beyond simple character recognition by incorporating intelligent preprocessing, smart splitting for long images, and seamless merging for overlapping content. It is optimized for developers who need to quickly digitize terminal logs or long-form documentation into actionable Markdown, making it an indispensable part of any modern AI-driven workflow.
Image Content Extractor Use Cases
- Extracting bash commands and error logs from terminal screenshots for debugging.
- Converting long-scrolling technical documentation images into structured Markdown files.
- Automating the ingestion of technical screenshots into centralized knowledge bases.
- Batch processing directories of design or research screenshots for easier searching.
How Image Content Extractor Works
- The image is provided as input, and the system automatically detects whether it is a Terminal, Document, or General image.
- Mode-specific preprocessing is applied, including contrast enhancement and binary thresholding for better OCR results.
- Long images are intelligently split into blocks based on content boundaries to ensure processing stability.
- Text is recognized using the Tesseract engine with an optional AI-driven fallback for complex layouts.
- Intelligent merging logic identifies and removes overlapping content to create a continuous text flow.
- Structure analysis identifies logical elements like headers, lists, and code blocks to generate the final Markdown output.
Image Content Extractor Setup
To install the Image Content Extractor, ensure you have Python and Tesseract OCR installed, then run the provided installation script:
./install.sh
Once installed, you can extract content from any image with a simple command:
python3 scripts/extract.py /path/to/image.png
Image Content Extractor Data Schema & Taxonomy
The skill organizes its technical logic and output through a structured file system and a central configuration schema:
| Directory/File | Purpose |
|---|---|
config/extractor-config.json |
Defines OCR engine settings, language support, and output formatting. |
core/ |
Contains the engine for preprocessing, merging, and structure analysis. |
modes/ |
Houses specialized logic for Terminal, Document, and General modes. |
scripts/extract.py |
The main entry point for executing extraction tasks via CLI. |
output.md |
The generated Markdown file containing extracted text, metadata, and Table of Contents. |
Image Content Extractor Advanced Features
- Automatic Mode Detection: Intelligently selects the best processing logic based on visual features.
- QMD Integration: Seamlessly updates knowledge base indices and supports automatic Git commits.
- Smart Overlap Detection: Accurately stitches together long screenshots by identifying duplicate content segments.
- Batch Processing: High-throughput capability to process entire directories of images in a single run.
- AI Fallback: Leverages LLM-based vision capabilities when local OCR engines encounter low-quality or complex imagery.
SKILL.md
Loading
Related Openclaw Skills
Context Manager
An intelligent context management skill that automates session transitions through background monitoring and seamless memory persistence.
ClawBox Link to Docs
Converts web URLs into two distinct Feishu documents: a high-fidelity source archive and a structured analysis brief.
mol-render
A powerful tool for generating ray-traced 3D ball-and-stick molecular models from SMILES strings or PDB structures.
OfdReader
A Python-powered utility to extract content from Chinese national standard OFD files and convert them into clean Markdown or plain text.
Interactive Card Reader
A specialized tool for Openclaw Skills that automatically extracts and parses structured JSON data from interactive message cards on enterprise platforms.
Context Manager
An intelligent context management skill that automates session switching and memory persistence to ensure uninterrupted AI agent workflows.
Featured*
