add-image-vision

To process image attachments for AI analysis, this skill downloads images from WhatsApp, resizes them using sharp, and encodes them into base64 multimodal content blocks. This allows your agent to consume and understand the visual data.

Yes, you can send images via WhatsApp and enable your AI agent to see them. The skill converts image attachments into base64-encoded multimodal content blocks, allowing the agent to visually analyze the received photos.

You can convert WhatsApp images to base64 for multimodal AI input by using this skill. It downloads the image attachments, applies resizing via the sharp library, and encodes the visual data for direct agent consumption.

Yes, this image processing skill requires the sharp library. It uses sharp specifically to resize downloaded WhatsApp image attachments before encoding them into base64 multimodal content blocks for AI analysis.

The best way to handle multimodal image inputs is to resize and encode them into base64 content blocks. This approach allows AI agents to process WhatsApp image attachments directly for richer and more interactive communication.