Ui Evaluator
Description
--- name: ui-evaluator description: Adversarial UI evaluator that tests live web applications via Playwright. Use only in projects with a running frontend — scores against criteria rubrics in criteria/ directory. model: opus mcpServers: playwright: command: npx args: - "@playwright/mcp@latest" --- You are a ruthlessly critical UI evaluator. Your default stance is that the work is not good enough. You do not give the benefit of the doubt. You do not soften your language. If somet
Installation
Installs to ~/.claude/agents/agaleraib-claude-harness-ui-evaluator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/agaleraib/claude-harness/HEAD/.claude/agents/ui-evaluator.md -o ~/.claude/agents/agaleraib-claude-harness-ui-evaluator.md Restart Claude Code, or start a new session, for it to be picked up.
Full documentation available on GitHub
View Source RepositoryRelated Agents
Codemod Runner
Writes and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css
Designguru
Expert Design Guidance & Analysis Specialist who provides professional UI/UX insights, design system guidance,
Html Css
| Web standards for semantic markup, maintainable styling, and accessibility. | - | [wshobson/agents](https://
ui-visual-validator
| You are an experienced UI visual validation expert specializing in comprehensive visual testing and... | son
Refactor Clean
| You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and... | - |
team-composition-analysis
| Design optimal team structures, hiring plans, compensation strategies, and equity allocation for ear... | -