skills.rest
breakcafe
breakcafeOFFICIAL
Explore all skills by this author →
GitHub

add-image-vision

Download, resize, and deliver WhatsApp images to Claude as multimodal blocks.

1|Updated Mar 9, 2026
Search Tags:#multimodal#vision#whatsapp#sharp#image-processing#nanoclaw
One-click install
npx skills add https://github.com/breakcafe/picoclaw --skill add-image-vision-breakcafe
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-image-vision
Source: https://github.com/breakcafe/picoclaw/tree/main/.claude/skills/add-image-vision
Command: npx skills add https://github.com/breakcafe/picoclaw --skill add-image-vision-breakcafe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Integrates image recognition and handling into NanoClaw agents by downloading, resizing, and passing image attachments to Claude as multimodal blocks, enabling agents to understand visual content in chats.

Core Features & Use Cases

  • Resize and process WhatsApp image attachments with sharp
  • Convert images to base64 multimodal content blocks for Claude
  • Works with WhatsApp channels to enrich agent responses with visual context

Quick Start

Enable the image vision skill in NanoClaw to automatically download, resize, and attach images as multimodal content blocks.

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 chat agents?▼

Image processing for WhatsApp chat agents works by downloading image attachments, resizing them with sharp, and passing them to Claude as base64 multimodal content blocks for visual interpretation.

How do I process WhatsApp image attachments for Claude multimodal input?▼

Processing WhatsApp image attachments for Claude involves downloading the images, resizing them with sharp, and converting them into base64 multimodal content blocks that Claude can interpret visually.

Does this image vision skill support WhatsApp group chats?▼

Yes, the image vision skill supports image attachments within WhatsApp group chats, handling captions and delivering visual context to the agent alongside the message content.

Do I need sharp to handle image attachments for NanoClaw agents?▼

Yes, you need sharp as a dependency to resize and process image attachments before delivering them to Claude as multimodal blocks within NanoClaw agents.

What happens if image download or processing fails for WhatsApp attachments?▼

If image download or processing fails for WhatsApp attachments, the skill gracefully degrades, allowing the agent to continue operating without the visual context rather than crashing the workflow.

Related Skills

Explore More Software Engineering Skills→
arnaudjnnarnaudjnn
1

add-image-vision

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

Community
Intermediate
TIAN0517TIAN0517

VLM

Analyze images and generate natural language descriptions via image_url or base64 inputs.

Community
Intermediate
theowenyoungtheowenyoung

add-image-vision

Download, resize, and pass WhatsApp images to Claude as multimodal content blocks.

Community
Advanced
atro2829-hubatro2829-hub

image-understand

Analyze static images to extract descriptions, objects, text, and visual structure.

Community
Advanced