test-generation-skill
について
このClaudeスキルは、包括的なコードカバレッジを達成するために、単体テスト、結合テスト、E2Eテストを自動生成および検証します。変更されたソースファイルを分析し、JestとPlaywrightを使用して適切なテストを作成し、85%以上の最小カバレッジとテスト失敗ゼロを強制します。新機能を追加する際、テストが失敗した場合、またはプロジェクトのカバレッジを向上させたい場合にご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/Eibon7/roastr-aigit clone https://github.com/Eibon7/roastr-ai.git ~/.claude/skills/test-generation-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: test-generation-skill description: Genera y valida tests unitarios, de integración y E2E con cobertura completa. triggers:
- "sin tests"
- "test fail"
- "añadir tests"
- "coverage" used_by:
- front-end-dev
- back-end-dev
- test-engineer steps:
- paso1: "Analizar archivos modificados en src/ para identificar componentes/servicios nuevos o modificados"
- paso2: "Generar tests unitarios usando Jest con mocks apropiados (sin datos reales)"
- paso3: "Generar tests de integración para flujos clave (auth, API, workers)"
- paso4: "Generar tests E2E con Playwright para UI cuando aplique"
- paso5: "Ejecutar npm test -- --coverage para validar cobertura"
- paso6: "Verificar que Coverage Source es 'auto' en nodos GDD afectados"
- paso7: "Asegurar cobertura >= 85% y 0 tests fallando"
- paso8: "Generar reporte en docs/test-evidence/issue-{id}/summary.md con resultados" output: |
- Tests generados en tests/unit/, tests/integration/, tests/e2e/
- Reporte de cobertura: coverage/coverage-summary.json
- Evidencias visuales: docs/test-evidence/issue-{id}/screenshots/
- Resumen: docs/test-evidence/issue-{id}/summary.md examples:
- contexto: "Se añadió un nuevo endpoint POST /api/roastr/persona" accion: "Generar tests para validar creación, actualización y borrado de persona" output_esperado: "tests/unit/routes/roastr-persona.test.js + tests/integration/persona-flow.test.js"
- contexto: "Se creó nuevo componente UserProfile.jsx" accion: "Generar tests unitarios + E2E visual con Playwright" output_esperado: "tests/unit/components/UserProfile.test.jsx + tests/e2e/profile-page.test.js + screenshots" rules:
- NUNCA usar datos reales (siempre mock data)
- Seguir patrones de tests existentes en tests/
- Cada archivo de producción debe tener su contraparte de test
- Tests deben ser aislados, reproducibles y auto-contenidos
- Usar nomenclatura descriptiva (test describe el comportamiento esperado) references:
- "docs/TESTING.md - Guía completa de testing"
- "docs/GDD-PHASE-15.1.md - Coverage authenticity"
- "CLAUDE.md - Commit sin tests prohibido"
GitHub リポジトリ
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.
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.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
cloudflare-cron-triggers
テストThis skill provides comprehensive knowledge for implementing Cloudflare Cron Triggers to schedule Workers using cron expressions. It covers setting up periodic tasks, maintenance jobs, and automated workflows while handling common issues like invalid cron expressions and timezone problems. Developers can use it for configuring scheduled handlers, testing cron triggers, and integrating with Workflows and Green Compute.