add-image-vision

Community

Add image understanding to NanoClaw agents.

Authortheowenyoung
Version1.0.0
Installs0

System Documentation

What problem does it solve?

NanoClaw agents often lack built-in image understanding for visual content shared via WhatsApp. This skill adds image vision by downloading, resizing, and processing attachments, then packaging them as multimodal content blocks sent to Claude.

Core Features & Use Cases

  • Image acquisition: downloads and resizes WhatsApp image attachments for processing.
  • Multimodal delivery: passes base64-encoded image blocks to Claude as multimodal content.
  • Group/self-chat workflows: supports images in both group chats and self-chat contexts.

Quick Start

Send a WhatsApp image in a NanoClaw-managed group and watch the agent respond with a multimodal interpretation.

Dependency Matrix

Required Modules

sharp

Components

Standard package

💻 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/theowenyoung/nanoclaw/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 471,000+ vetted skills library on demand.