A specialized tool for extracting structured knowledge, OCR text, and summaries from images to be stored in a local database.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-collect
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-collect 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 Collect?
The Image Collect skill is a powerful utility designed for AI agents to process visual information into actionable data. By integrating this capability within Openclaw Skills, developers can transform raw images—whether from URLs, base64 strings, or local paths—into a structured local knowledge base. It handles the heavy lifting of image downloading, content understanding, and metadata generation in a single workflow.
This skill is particularly valuable for building searchable archives of visual content. It ensures that the information contained within an image is not lost but is instead converted into text, summarized, and indexed for future retrieval by your AI agents or automation pipelines.
Image Collect Use Cases
- Processing user-uploaded images to extract and save relevant information.
- Automating OCR tasks when a user requests to save an image as persistent knowledge.
- Building a local searchable database of visual assets with extracted text and meaning.
- Integrating visual content understanding into existing Openclaw Skills workflows.
How Image Collect Works
- The skill receives an image input via a URL, base64 string, or local file path.
- It downloads and prepares the image for processing.
- Advanced AI models perform OCR to extract raw text and interpret the visual meaning.
- A concise summary and relevant keywords are generated based on the image content.
- The image is saved to a local directory for persistence.
- The extracted knowledge is appended to a JSON database for easy querying.
Image Collect Setup
To start using this skill within your environment, ensure you have Node.js installed and execute the following commands:
# Build the project
npm run build
# Run the skill with a remote image URL
node dist/index.js "https://example.com/image.png"
# Run the skill with a local file path
node dist/index.js "/tmp/image.png"
Image Collect Data Schema & Taxonomy
The skill organizes extracted data into a structured format to ensure compatibility with other Openclaw Skills. Each entry includes:
| Field | Description |
|---|---|
| summary | A high-level description of the image content. |
| keywords | A list of relevant tags for indexing and search. |
| text | The full OCR output extracted from the image. |
| path | The local filesystem path where the image is stored. |
Image Collect Advanced Features
- Supports multiple input formats including data URIs (base64) and remote HTTPS links.
- Automated JSON database management for persistent knowledge storage.
- Semantic content understanding beyond simple OCR text extraction.
- Seamless integration as a modular component for complex AI agent behaviors.
SKILL.md
Loading
Related Openclaw Skills
KingSumo
A comprehensive integration for KingSumo that enables AI agents to automate viral giveaway management and email list growth.
KimiClaw Bridge
A bridge connecting Openclaw Skills to the Kimi K2.5 coding model via the Anthropic Messages API protocol.
Thinking Frameworks
A collection of 20 human-centric cognitive frameworks designed to empower AI agents with deep analytical and decision-making capabilities.
TestCase Generator
An automated testing intelligence tool that transforms project documentation into professional, high-coverage Excel test cases.
UniFi Integration
A read-only monitoring skill for UniFi networks that provides instant visibility into devices, clients, health, and traffic data.
No More Forget
A comprehensive memory optimization toolkit that prevents agent amnesia, slashes token consumption, and enhances semantic search capabilities.
Featured*
