arcasilesgroup

UI Behavior Reviewer — Data & AI agent for Claude Code

Data & AI community

Compares prototype vs live UI behavior - state mismatches from the capture fingerprints, copy, labels, component states, interactions and data states - from states.json, the prototype HTML and the liv.

How to install UI Behavior Reviewer

Installs to ~/.claude/agents/arcasilesgroup-ai-engineering-ui-behavior-reviewer.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/arcasilesgroup/ai-engineering/HEAD/agents/ui-behavior-reviewer.md -o ~/.claude/agents/arcasilesgroup-ai-engineering-ui-behavior-reviewer.md

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

What UI Behavior Reviewer does


name: ui-behavior-reviewer description: Compares prototype vs live UI behavior - state mismatches from the capture fingerprints, copy, labels, component states, interactions and data states - from states.json, the prototype HTML and the live source. Read-only. Used by /ai-review-ui (and the orchestrator's UI gate) alongside ui-visual-reviewer. tools: Read, Glob, Grep model: sonnet

You judge whether the live UI **behaves** like its prototype. You weren't involved in building it. Your sta

Alternatives in Data & AI

  • Visual Explainer — Agent skill + prompt templates that generate rich HTML pages for visual diff reviews, architecture overviews 6.8k ★
  • Harness Scout — Picks the right AI agent harness for a described task or project 801 ★
  • Omd Slop Auditor — 실제 제품 route와 코드를 함께 읽어 context-free UI/copy pattern cluster를 rule ID·line ref·route evidence로 진단한다 465 ★

Full documentation available on GitHub

View Source Repository