Skill1.3k repo starsupdated today

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.

View source Repository: babysitter

Install in Claude Code

Copy

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-automation

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.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