skills.rest
iia-arg
iia-argCOMMUNITY
Explore all skills by this author →
GitHub

add-image-vision

Download, resize, and encode WhatsApp images for multimodal agent processing.

Updated Apr 25, 2026
Search Tags:#image#multimodal#vision#whatsapp#processing#sharp
One-click install
npx skills add https://github.com/iia-arg/claudeclaw --skill add-image-vision-iia-arg
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-image-vision
Source: https://github.com/iia-arg/claudeclaw/tree/main/skills/add-image-vision
Command: npx skills add https://github.com/iia-arg/claudeclaw --skill add-image-vision-iia-arg

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sharp, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows ClaudeClaw agents to see and understand images sent via WhatsApp, enabling multimodal perception within conversations.

Core Features & Use Cases

  • Image Preprocessing: Downloads, resizes, and encodes images from WhatsApp attachments using sharp.
  • Multimodal Content Integration: Passes processed images to Claude as base64-encoded content blocks.
  • Use Case: A user shares a photo of a handwritten note in WhatsApp; the agent analyzes the image content to provide insights or transcribe the note.

Quick Start

Use the add-image-vision skill to enable WhatsApp agents to process images by merging the code changes and restarting the service.

Frequently Asked Questions about add-image-vision

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I process WhatsApp image attachments for multimodal AI conversations?▼

To process WhatsApp image attachments for multimodal AI conversations, you download, resize, and encode images using sharp, then pass them as base64-encoded content blocks to Claude for visual understanding.

What is the best way to enable image recognition in a ClaudeClaw agent?▼

The best way to enable image recognition in a ClaudeClaw agent is to integrate a preprocessing skill that downloads and encodes WhatsApp images into base64 content blocks for Claude to interpret.

Do I need sharp to resize images before sending them to Claude?▼

Yes, you need sharp to resize images before sending them to Claude, as it handles the image processing required to encode WhatsApp attachments into base64 format.

Can I transcribe handwritten notes from photos sent through WhatsApp?▼

Yes, you can transcribe handwritten notes from photos sent through WhatsApp by preprocessing the image attachments and passing the encoded visual data to Claude for analysis.

What are the limitations of processing WhatsApp images with sharp for AI agents?▼

Processing WhatsApp images with sharp for AI agents requires integration with WhatsApp channel code and a service restart after merging changes, limiting its use to compatible environments.

Related Skills

Explore More Content & Communication Skills→
LIMITLESS-LONGEVITYLIMITLESS-LONGEVITY

add-image-vision

Download, resize, and base64-encode WhatsApp images for Claude multimodal content blocks.

Official
Advanced
stevengonsalvezstevengonsalvez

add-image-vision

Download, resize, and encode WhatsApp images as base64 multimodal blocks for NanoClaw agents.

Community
Advanced
arnaudjnnarnaudjnn
1

add-image-vision

Process WhatsApp image attachments into multimodal content blocks for NanoClaw agents.

Community
Intermediate
OfirGavishOfirGavish
3

add-image-vision

Process WhatsApp image attachments into multimodal blocks for NinjaClaw agents.

Community
Intermediate