Vision Skill

Understand images (describe content, answer questions about them, extract text/OCR) via a vision model. Use when the user asks what an image, screenshot, chart, scan, or photo contains.

zeenie-ai Updated 1.1k repo stars
OpenCompany: professional AI cat employees turn tokens into finished work for a paying customer.

File contents

zeenie-ai/opencompany commit e2de8f2a87

Frequently asked questions

npx get-skill add zeenie-ai/vision-skill