← Back to Skills Marketplace
5998
Downloads
0
Stars
30
Active Installs
1
Versions
Install in OpenClaw
/install image-vision
Description
Analyze and interpret images by describing content, extracting text, answering questions, comparing visuals, and extracting structured data from JPG, PNG, GI...
Usage Guidance
Install if you need OCR or image understanding, but treat every uploaded image as potentially sensitive. Redact secrets, IDs, payment details, account numbers, private business information, and authentication material before use, and avoid submitting regulated or confidential content unless necessary.
Capability Assessment
Purpose & Capability
The described capability of analyzing images and extracting text from receipts, business cards, forms, and screenshots is coherent with an OCR/image-analysis skill.
Instruction Scope
The instructions appear purpose-aligned, but the skill should more clearly warn users to avoid or redact sensitive personal, financial, authentication, or business data in images.
Install Mechanism
No supplied evidence shows install-time code, hidden setup behavior, package execution, or deceptive installation mechanics.
Credentials
Processing user-provided images is proportionate for OCR, but those images may contain sensitive data and should be handled with explicit user consent and data minimization.
Persistence & Privilege
No supplied evidence shows persistence, privilege escalation, credential access, background workers, destructive actions, or automatic data exfiltration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install image-vision - After installation, invoke the skill by name or use
/image-vision - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Image analysis skill using multimodal vision models
Metadata
Frequently Asked Questions
What is Image Vision?
Analyze and interpret images by describing content, extracting text, answering questions, comparing visuals, and extracting structured data from JPG, PNG, GI... It is an AI Agent Skill for Claude Code / OpenClaw, with 5998 downloads so far.
How do I install Image Vision?
Run "/install image-vision" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Image Vision free?
Yes, Image Vision is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Image Vision support?
Image Vision is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Image Vision?
It is built and maintained by cntuang (@cntuang); the current version is v1.0.0.
More Skills