Observer — Design agent for Claude Code
Visual analysis specialist.
How to install Observer
Installs to ~/.claude/agents/east5ringroad-kyle-oh-my-zcode-slim-observer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/East5RingRoad-kyle/oh-my-zcode-slim/HEAD/agents/observer.md -o ~/.claude/agents/east5ringroad-kyle-oh-my-zcode-slim-observer.md Restart Claude Code, or start a new session, for it to be picked up.
What Observer does
oh-my-zcode-slim managed
name: "observer" description: "Visual analysis specialist. Interprets images, screenshots, PDFs, and diagrams; extracts exact text via OCR (never paraphrases errors or code). Keeps heavy media out of the orchestrator's context." color: "yellow" tools: ["Glob", "Grep", "Read", "TodoWrite"] disallowedTools: ["Agent", "Task"] model: "inherit"
You are Observer, a visual analysis specialist.
**Role**: interpret images, screenshots, PDFs, and diagrams on behalf of
Alternatives in Design
- Module Debugger — Use this agent to debug module issues — registration failures, route problems, view errors, migration issues 407 ★
- Review Code Statistics — A code review agent that verifies the statistical methodology implemented in scripts matches the research desi 134 ★
- Browser Pilot — Playwright browser automation — navigate URLs, screenshot, interact with UI, check accessibility, capture cons 85 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Multimodal Looker
Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific in
Wp Context
Project-docs analyzer — reads a docs/ folder (scope spreadsheets, design PDFs, estimate/scope markdown) and ex
Design Gatherer
SDD Phase 1 sub-agent. Fetches ALL Claude Design files (HTML + README) to disk, extracts exact labels, CSS tok
Media Producer
Produces short-attention media - feature demo videos, social cuts, screenshots, generated images - built as co
Graphic Designer
Produces web-ready visual assets from the project's design direction and token file, in four media — stills (h
Design Study
Studies reference images, GIFs, prior designs, or public visual references and extracts reusable design DNA be
Related Skills
Video2context
Turn screen recordings into compact, timestamped context for AI coding agents. A Python CLI that extracts key
Analyze Visual
Analyze images, PDFs, screenshots, or diagrams using vision-capable models
Rtfm.Ocr
Enable persistent OCR fallback for scanned PDFs and run the OCR pass in the background