# Image Analysis

> Analyzes images using a vision-capable LLM (Optic). Can read workspace images, URLs, base64 data, or previously generated images by ID.

- Skill: `rotoslider/image-analysis` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add rotoslider/image-analysis`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rotoslider/image-analysis/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: rotoslider (https://skillmd.com/u/rotoslider)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rotoslider/image-analysis

---


# Image Analysis (Optic)

## When to Use
- User asks to look at/describe/analyze an image -> `analyze_image`
- After generating an image, review it -> `analyze_image` with `image_id`

## Input Sources (provide exactly one)
- `image_path`: workspace-relative path
- `image_url`: URL to fetch
- `image_base64`: raw base64 data
- `image_id`: ID from generate_image result

## Important
- Images resized to 768px max before analysis
- 10MB size limit
- MIME type auto-detected from extension