# Multimodal Eye

> SKILL: Multimodal Eye

- Skill: `moeabdelaziz007/multimodal-eye` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add moeabdelaziz007/multimodal-eye`
- Raw SKILL.md: https://api.skillmd.com/api/skills/moeabdelaziz007/multimodal-eye/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: Moeabdelaziz007 (https://skillmd.com/u/moeabdelaziz007)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/moeabdelaziz007/multimodal-eye

---

# SKILL: Multimodal Eye

## Description
Provides the agent with "Vision". Can analyze images or video frames provided via URL or local path.

## Capabilities
1.  **`analyze_image(image_path)`**:
    *   Describes the content of an image.
    *   Extracts text (OCR).
    *   Identifies UI elements (for frontend coding).

## Usage Prompt
"Agent, look at `screenshot.png` and tell me what the error message says."