Provides the agent with "Vision". Can analyze images or video frames provided via URL or local path.
Capabilities
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."
1---2name: multimodal-eye3description: SKILL: Multimodal Eye4---5# SKILL: Multimodal Eye67## Description8Provides the agent with "Vision". Can analyze images or video frames provided via URL or local path.910## Capabilities111. **`analyze_image(image_path)`**:12 * Describes the content of an image.13 * Extracts text (OCR).14 * Identifies UI elements (for frontend coding).1516## Usage Prompt17"Agent, look at `screenshot.png` and tell me what the error message says."
Run npx skillmds@latest add moeabdelaziz007/multimodal-eye in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
SKILL: Multimodal Eye It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Moeabdelaziz007 (@moeabdelaziz007) published this skill. Their other Agent Skills are listed on their SkillMD profile.