UX Comparator — Design agent for Claude Code
Compares multiple WordPress plugins after individual UX reviews, returning a comparison table with ratings and verdict.
How to install UX Comparator
Installs to ~/.claude/agents/shub-rajput-design-superskills-ux-comparator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/shub-rajput/design-superskills/HEAD/agents/ux-comparator.md -o ~/.claude/agents/shub-rajput-design-superskills-ux-comparator.md Restart Claude Code, or start a new session, for it to be picked up.
What UX Comparator does
name: ux-comparator description: Compares multiple WordPress plugins after individual UX reviews, returning a comparison table with ratings and verdict. model: inherit
You are a Senior UX Analyst specializing in WordPress plugin comparisons. You receive completed UX review annotations for multiple plugins and produce a structured comparison.
Input
You will receive:
- Plugin annotations — the full JSON annotation output from each plugin's ux-reviewer agent
- Review briefs
Alternatives in Design
- Async Code — Use Claude Code or CodeX CLI to perform multiple tasks in parallel with a Codex-style UI, functioning as a per 513 ★
- Heuristic Evaluator — Use this agent to evaluate a design against established usability heuristics (Nielsen's 10) and conduct cognit 240 ★
- Otgw Device Verify — Runs the OTGW on-device verify loop (build LittleFS/firmware -> flash the bench ESP32-S3 over USB -> verify th 200 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Bd Validate
Interprets the S7 verdict. Reads the seal-verification result and the prediction comparison table, decides whe
Design Advisor
Researches a single gray area and produces a 5-column comparison table with rationale. Spawned by design-conte
UX Expert
Reviews usability, accessibility, and interaction design of UI changes, returning severity-ranked findings. Us
Stamity Design Quality
Reviews rendered surfaces and the flows through them when a component, view, or style file changes, deciding n
Jarvis Critic Design Reviewer
Use after implementing or modifying the Phase-6 Critic-Loop to review prompts, verdict schema, and escalation
Fix Builder
Fresh session that revises a Blender asset after a critic FAIL. Use only when gauntlet/evidence/ / / contains
Related Skills
Refocus
Re-read state.json and restate the active task in one tight block. Use after distractions, context drift, or r
Aeo Benchmark
Benchmarks AEO performance across multiple URLs or documentation sets. Compares scores, tracks improvements ov
Three Axes Set
Set individual axis values. Usage: /three-axes-set = [--project --global]. Default scope is session. Multiple