add-image-vision

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

Updated Apr 2, 2026

Search Tags:#image #multimodal #vision #whatsapp #sharp #base64 #nanoclaw

Ready to run

npx skills add https://github.com/LIMITLESS-LONGEVITY/limitless --skill add-image-vision-limitless-longevity

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: add-image-vision
Source: https://github.com/LIMITLESS-LONGEVITY/limitless/tree/main/apps/nanoclaw/.claude/skills/add-image-vision
Command: npx skills add https://github.com/LIMITLESS-LONGEVITY/limitless --skill add-image-vision-limitless-longevity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables NanoClaw agents to understand and process images sent via WhatsApp by downloading, resizing, and encoding them as multimodal content blocks for Claude.

Core Features & Use Cases

Image download and resize using sharp
Base64-encoded multimodal content delivery to Claude
Works within WhatsApp group channels for automated image understanding

Quick Start

Process an incoming WhatsApp image by downloading, resizing with sharp, encoding to base64, and sending to Claude as a multimodal content block.

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 Claude in a NanoClaw deployment?▼

You can enable image vision for NanoClaw agents by downloading WhatsApp images, resizing them via sharp, base64 encoding the data, and passing it as multimodal content blocks directly to Claude.

What is the best way to send base64-encoded images to Claude as multimodal content?▼

The best way to send base64-encoded images to Claude is by resizing the source image with sharp, converting the output to a base64 string, and structuring it as a multimodal content block for Claude's vision API.

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

Yes, you need the sharp library to resize images before sending them to Claude, as it handles the image processing step required to create the base64-encoded multimodal content blocks for Claude.

Can I use NanoClaw agents to understand images sent in WhatsApp group channels?▼

Yes, you can use NanoClaw agents to understand images sent in WhatsApp group channels by processing the attachments into base64-encoded multimodal content blocks for Claude vision processing.

Why does my NanoClaw image processing pipeline require code changes in src/image.ts?▼

Your NanoClaw image processing pipeline requires code changes in src/image.ts to properly handle the download, sharp resizing, and base64 encoding logic needed to deliver multimodal content blocks to Claude.