add-image-vision

Download, resize, and base64-encode WhatsApp images for multimodal agent reasoning.

Updated Apr 13, 2026

Search Tags:#image #multimodal #vision #whatsapp #image-processing #base64 #nanoclaw

Ready to run

npx skills add https://github.com/nrupala/nanoclaw --skill add-image-vision-nrupala

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

NanoClaw agents currently cannot understand image content from WhatsApp attachments. This skill provides automatic image handling, resizing, base64 encoding, and multimodal content delivery to agents for interpretation.

Core Features & Use Cases

Image download and processing: fetches image attachments, resizes with sharp, and stores in the group workspace.
Multimodal content blocks: passes base64-encoded images to agents as multimodal content blocks.
Use Case: in a WhatsApp group, agents can reason about the content of shared photos to inform decisions.

Quick Start

Provide the agent with a WhatsApp image and request an interpretation of its content.

Frequently Asked Questions about add-image-vision

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

FAQPage Schema

How do I add image vision to WhatsApp agents for multimodal reasoning?▼

Image vision for multimodal agents works by downloading WhatsApp image attachments, resizing them with sharp, and encoding them into base64. These base64 images are then passed as content blocks to the agent for visual reasoning.

What's the best way to process WhatsApp image attachments for AI agents?▼

Processing WhatsApp image attachments for AI agents involves fetching the files, resizing them with sharp, and base64 encoding the results. This workflow delivers optimized visual content blocks to the agent for interpretation.

Why do I need base64 encoding to send images to multimodal agents?▼

Base64 encoding is needed for multimodal agents because it converts binary image attachments into a text format that agents can process. This allows visual content blocks to be passed directly into the agent's reasoning pipeline.

Can I use sharp for image resizing in a WhatsApp agent workflow?▼

Yes, sharp is used for image resizing in a WhatsApp agent workflow. It fetches, resizes, and stores image attachments in the group workspace before passing them to the agent for visual interpretation.

Does NanoClaw support multimodal content blocks from WhatsApp images?▼

NanoClaw supports multimodal content blocks from WhatsApp images by downloading and processing the attachments. It encodes the images as base64, allowing agents to reason about shared photos to inform group decisions.