What problem does it solve? Test suites often contain hidden quality problems like hard waits, missing assertions, shared state, and flakiness patterns that erode reliability without anyone noticing. This Skill audits existing test files against a fixed criteria registry and produces a deterministic 0-100 quality score with severity-classified findings and concrete fixes. ## Core Features & Use Cases - Rubric-Based Test Audit: Evaluates tests against a criteria registry covering disabled tests, tautological assertions, hard waits, determinism, isolation, fixtures, data factories, and network-first patterns, with pinned severities so two reviewers reach the same verdict. - Scored Review Report: Generates a structured Markdown report with a quality score, letter grade, computed recommendation (Approve, Request Changes, or Block), code-level findings with file:line locations, and recommended fixes grounded in a knowledge base. - Framework-Aware Analysis: Adapts to Playwright, Jest, Cypress, Vitest, Pact contract tests, and Maestro mobile flows, including optional adoption checks for playwright-utils and pactjs-utils packages. - Use Case: Before merging a pull request, run the review on the changed test files to catch a committed test.only, a waitForTimeout race condition, or a test with no assertions, and receive a scored report that CI can gate on. ## Quick Start Ask the agent to review the test quality of the spec files changed in your current pull request and generate the scored review report.
