What problem does it solve?
QA agents often claim tests passed without actually running them, producing unverifiable results. This Skill enforces real test execution by detecting the project's test framework, running the correct commands, and parsing structured output for pass/fail counts and coverage.
Core Features & Use Cases
- Framework Detection: Identifies Jest, Vitest, Playwright, Cypress, pytest, unittest, and Go tests from config files and package dependencies.
- Real Test Execution: Runs unit tests (npm test, pytest, go test) and E2E tests (Playwright) with explicit commands, forbidding mocked results.
- Result Parsing: Extracts total, passed, failed, flaky, and skipped counts from Playwright JSON reports for quality gate evaluation.
- Use Case: A QA agent validating a Node.js feature detects Playwright, runs
npx playwright test --reporter=json, and reports exact pass/fail statistics as gate evidence.
Quick Start
Ask the QA agent to run the project's test suite and report the real pass, fail, and coverage results.