MCP HubMCP Hub
← スキル一覧に戻る

visual-validation-skill

Eibon7
更新日 Today
56 閲覧
0
GitHubで表示
メタtestingmcpdesign

について

このClaudeスキルは、Playwright MCPを使用した自動視覚的UI検証を実行し、複数のビューポートでのスクリーンショット取得とアクセシビリティテストを行います。ユーザー操作をシミュレートし、視覚的証拠レポートを生成することで、開発者がフロントエンドの変更を検証するのに役立ちます。UIコンポーネントのテスト、フロントエンドの更新テスト、または視覚的回帰テストの実施時にご利用ください。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/Eibon7/roastr-ai
Git クローン代替
git clone https://github.com/Eibon7/roastr-ai.git ~/.claude/skills/visual-validation-skill

このコマンドをClaude Codeにコピー＆ペーストしてスキルをインストールします

ドキュメント

name: visual-validation-skill description: Ejecuta validación visual de UI con Playwright MCP y genera evidencias. triggers:

  • "UI change"
  • "frontend"
  • "visual"
  • "component"
  • "screenshot" used_by:
  • ui-designer
  • front-end-dev
  • test-engineer
  • whimsy-injector steps:
  • paso1: "Conectar a Playwright MCP server (ya configurado en settings.local.json)"
  • paso2: "Identificar componentes/rutas afectadas por cambios"
  • paso3: "Lanzar navegación a páginas relevantes con mcp.playwright.browse"
  • paso4: "Capturar screenshots en múltiples viewports (desktop, tablet, mobile)"
  • paso5: "Ejecutar tests de accesibilidad automáticos (a11y)"
  • paso6: "Simular interacciones de usuario (clicks, hovers, form submissions)"
  • paso7: "Revisar consola del navegador y network logs"
  • paso8: "Generar reporte visual con capturas y métricas" output: |
  • Screenshots multi-viewport: docs/test-evidence/issue-{id}/screenshots/
    • desktop-{page}.png
    • tablet-{page}.png
    • mobile-{page}.png
  • Reporte visual: docs/test-evidence/issue-{id}/ui-report.md
  • Logs de accesibilidad: docs/test-evidence/issue-{id}/a11y-logs.txt
  • Network logs: docs/test-evidence/issue-{id}/network-log.json examples:
  • contexto: "Se implementó nuevo componente UserProfile" accion: |
    1. Navegar a /profile
    2. Capturar en 1920x1080 (desktop), 768x1024 (tablet), 375x667 (mobile)
    3. Probar interacción: click en "Edit" button
    4. Verificar que modal aparece correctamente
    5. Capturar estado hover de botones output: "6 screenshots + ui-report.md con métricas a11y"
  • contexto: "Cambios en formulario de login" accion: |
    1. Navegar a /login
    2. Capturar estado inicial
    3. Simular focus en input de email
    4. Capturar estado de error al submit incorrecto
    5. Validar que contraste cumple WCAG AA output: "Capturas de estados + reporte de contraste" viewports: desktop: "1920x1080" tablet: "768x1024" mobile: "375x667" checks:
  • "Contraste de colores (WCAG AA mínimo)"
  • "Focus visible en elementos interactivos"
  • "Alt text en imágenes"
  • "Labels en formularios"
  • "Responsive sin roturas"
  • "Loading states visibles"
  • "Error states con mensajes claros" tools:
  • mcp.playwright.browse: "Navegar páginas"
  • mcp.playwright.screenshot: "Capturar estado visual"
  • mcp.playwright.inspect: "Inspeccionar elementos" rules:
  • SIEMPRE capturar en 3 viewports mínimo
  • Incluir estados: loading, error, empty, success
  • Verificar a11y en cada captura
  • Documentar cualquier inconsistencia visual
  • Comparar con specs en docs/ui.md si existen references:
  • "docs/ui-review.md"
  • "docs/test-evidence/ - Evidencias visuales"
  • "CLAUDE.md - Visual validation"

GitHub リポジトリ

Eibon7/roastr-ai
パス: .claude/skills/visual-validation-skill.md

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

creating-opencode-plugins

メタ

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

スキルを見る

evaluating-llms-harness

テスト

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

スキルを見る

polymarket

メタ

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

スキルを見る