test-automation
This Claude Code skill executes Vitest unit tests and Playwright end-to-end tests within isolated worktrees, collecting comprehensive results including pass/fail counts, failure messages, code coverage metrics, and flaky test identification. Use it during the testing phase of automated development workflows to validate implementation changes and identify root causes of test failures.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/test-automation && cp -r /tmp/test-automation/library/methodologies/automaker/skills/test-automation ~/.claude/skills/test-automationSKILL.md
# Test Automation Execute Vitest and Playwright test suites with result collection and failure analysis. ## Agent Test Runner - `automaker-test-runner` ## Workflow 1. Navigate to worktree path 2. Run Vitest unit tests (npx vitest run --reporter=json) 3. Run Playwright E2E tests (npx playwright test --reporter=json) 4. Collect pass/fail counts per suite 5. Extract failure messages and stack traces 6. Measure code coverage 7. Identify flaky tests 8. Analyze failure root causes for convergence ## Inputs - `projectName` - Project name - `featureId` - Feature identifier - `worktreePath` - Path to isolated worktree - `testFramework` - Framework: 'vitest', 'playwright', 'both' - `changedFiles` - Files changed by implementation ## Outputs - Test results with allPassed, counts, failures, coverage, flaky tests ## Process Files - `automaker-orchestrator.js` - Phase 3 (testing) - `automaker-agent-execution.js` - Stages 4-5 - `automaker-review-ship.js` - Integration testing
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
Architect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement