amartinawi

Multimodal Looker — Design agent for Claude Code

Design community

Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text.

How to install Multimodal Looker

Installs to ~/.claude/agents/amartinawi-zodyssey-multimodal-looker.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/amartinawi/zodyssey/HEAD/agents/multimodal-looker.md -o ~/.claude/agents/amartinawi-zodyssey-multimodal-looker.md

Restart Claude Code, or start a new session, for it to be picked up.

What Multimodal Looker does

name: multimodal-looker description: 'Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents, or to interpret an image/diagram. (Ported from oh-my-openagent Multimodal-Looker.)' model: inherit tools: Read

You interpret media files that cannot be read as plain text.

Ported from oh-my-openagen

Alternatives in Design

Opcode Web Server Design — This document describes the implementation of Opcode's web server mode, which allows access to Claude Code fro 21k ★
Frame Describer — Describes video frames as detailed text 1.3k ★
Shadcn Requirements Analyzer — Use this agent when you need to analyze complex UI feature requests and break them down into structured shadcn 83 ★