What problem does it solve? Test suites often contain hidden quality problems such as hard waits, missing assertions, shared state, and non-deterministic logic that pass silently in CI. This Skill audits existing test files against a fixed criteria registry and produces a deterministic 0-100 quality score with actionable, line-level findings. ## Core Features & Use Cases - Rubric-Based Test Audit: Evaluates test files against pinned severity rules covering disabled tests, tautological assertions, hard waits, isolation, fixtures, data factories, and network-first patterns. - Deterministic Scoring and Verdict: Computes a 0-100 score, letter grade, and a computed recommendation (Approve, Approve with Comments, Request Changes, or Block) from violation counts rather than reviewer judgment. - Multi-Mode Workflow: Supports Create, Resume, Validate, and Edit modes, plus a headless non-interactive mode for CLI runners, with optional inline TODO comments written into reviewed test files. - Use Case: A QA engineer points the workflow at a Playwright spec directory before a merge; the review flags a committed test.only as critical, deducts points for hard waits, and emits a report with file:line fixes grounded in knowledge base fragments. ## Quick Start Ask the agent to review the test quality of the files in your tests directory and generate a scored test review report.
