skills.rest
E01N
E01NCOMMUNITY
Explore all skills by this author →
GitHub

add-image-vision

Download, resize with sharp, and base64-encode WhatsApp images for NanoClaw agents.

Updated Mar 24, 2026
Search Tags:#multimodal#whatsapp#sharp#image-processing#base64#agent-runner#image-vision
One-click install
npx skills add https://github.com/E01N/ClawOutreach --skill add-image-vision-e01n
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-image-vision
Source: https://github.com/E01N/ClawOutreach/tree/main/nanoclaw/.claude/skills/add-image-vision
Command: npx skills add https://github.com/E01N/ClawOutreach --skill add-image-vision-e01n

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adds the ability for NanoClaw agents to see and understand images sent via WhatsApp. Images are downloaded, resized with sharp, saved to the group workspace, and passed to the agent as base64-encoded multimodal content blocks.

Core Features & Use Cases

  • Image download, resize via sharp, and base64 encoding to create multimodal content blocks.
  • WhatsApp integration: attachment handling in the group chat context.
  • End-to-end flow: from receiving a WhatsApp image to supplying the agent with a ready-to-use content block for analysis.

Quick Start

Send a test image in a registered WhatsApp group to trigger image-vision processing.

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 a WhatsApp chat agent?▼

To add image vision to a WhatsApp chat agent, you download attachments, resize them with sharp, and pass them as base64-encoded multimodal content blocks for agent analysis.

How does multimodal image processing work for NanoClaw agents?▼

Multodal image processing for NanoClaw agents works by downloading WhatsApp images, resizing them with sharp, and encoding them into base64 content blocks that the agent can visually analyze.

What dependencies are required for base64 image encoding in agent runners?▼

Base64 image encoding in agent runners requires the sharp image processing library for resizing, along with npm install, a build, and syncing agent-runner sources to enable the multimodal content blocks.

Does this image vision skill work with individual WhatsApp chats or only groups?▼

This image vision skill targets WhatsApp group chats specifically, handling attachments within the group workspace context and applying code changes to channel modules to enable image processing.

Why is my WhatsApp image attachment not processing in the agent runner?▼

WhatsApp image attachment processing requires merging the WhatsApp skill, applying src code changes, running npm install, building, syncing agent-runner sources, and restarting the container to verify functionality.

Related Skills

Explore More Software Engineering Skills→
LIMITLESS-LONGEVITYLIMITLESS-LONGEVITY

add-whatsapp

Add WhatsApp messaging to NanoClaw with QR or pairing-code authentication.

Official
Advanced
stevengonsalvezstevengonsalvez

add-image-vision

Download, resize, and encode WhatsApp images as base64 multimodal blocks for NanoClaw agents.

Community
Advanced
LIMITLESS-LONGEVITYLIMITLESS-LONGEVITY

add-image-vision

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

Official
Advanced
qwibitaiqwibitai
10

add-image-vision

Download, resize via sharp, and encode WhatsApp images as base64 multimodal blocks for NanoClaw agents.

Official
Intermediate