What problem does it solve? Manually executing large test suites is slow, error-prone, and disruptive to the user's desktop. This Skill automates structured test case execution in a silent background architecture, producing consistent execution reports, defect records, and screenshot evidence without taking over the user's keyboard or mouse. ## Core Features & Use Cases - Three-Layer Silent Execution Engine: Routes each test case to API Direct (data checks), Playwright Headless (UI verification), or read-only browser exploration based on a decision tree, with an optional interactive diagnostic layer. - Self-Healing & Safety Protocols: Includes environment pre-checks (E1 gate), IP-block self-rescue via admin whitelist, automatic test data setup, snapshot-execute-restore for config changes, and a gated DB mock-seed channel with audit logging. - Structured Deliverables: Generates dated execution reports, defect lists with severity/category taxonomy (Critical to Low; Functional, Visual, Console, UX, Content, Accessibility), Playwright reproduction scripts, and organized screenshot evidence. - Use Case: Given a handoff manifest of 80 test cases for a membership system, the Skill pre-checks the environment, queues cases by priority, executes them headlessly in batches with checkpointing, and outputs a full execution report plus a defect list with root-cause hypotheses. ## Quick Start Execute all test cases in the handoff manifest and generate the execution report and defect list.
