add-image-vision

Community

Enable agents to see images.

Authorarnaudjnn
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill allows NanoClaw agents to process and understand image attachments sent through WhatsApp, enabling multimodal communication.

Core Features & Use Cases

  • Image Processing: Downloads, resizes, and processes WhatsApp image attachments.
  • Multimodal Content: Sends images to Claude as base64-encoded multimodal content blocks.
  • Use Case: When a user sends an image in a WhatsApp chat, the agent can now analyze its content and respond contextually, just as if it were text.

Quick Start

Send an image in a registered WhatsApp group and verify the agent responds with understanding of the image content.

Dependency Matrix

Required Modules

sharp

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: add-image-vision
Download link: https://github.com/arnaudjnn/nanoclaw-railway/archive/main.zip#add-image-vision

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.