Deterministic, evidence-backed QA runtime for Claude Code, Codex, and Cursor. Versioned artifact contracts, a Playwright Runtime Browser Driver, redacted evidence, and reproducible release gates. The runtime never calls an LLM.
Bootstraps @gwinnguyen/qa-skills in a project: resolves the local runtime, verifies its version range, installs the checksummed canonical Skill Bundle, and verifies the Runtime Binding. The eight QA skills themselves are installed by the runtime, never copied by this plugin.
Install and verify the QA Skills runtime in this project so the eight canonical QA skills become available. Use when the user asks to set up QA Skills, when qa-skill is missing or its runtime binding is broken, or when a QA skill stopped with setup guidance.
Execute approved bounded browser Test DSL cases with fresh isolated contexts and auditable attempts. Use when running browser tests, reruns, regression checks, or blocked execution diagnostics.
Generate deduplicated, reproducible QA bug reports only from failed product-defect attempts and registered evidence. Use when triaging failures, creating bug candidates, or preparing retest inputs.
Collect and validate redacted, immutable QA evidence and evidence gaps for browser attempts. Use when capturing screenshots, traces, logs, telemetry, or explaining unavailable evidence.
Generate an auditable QA execution report and deterministic release recommendation from registered run artifacts. Use when summarizing a QA run, reviewing release readiness, or rendering English or Vietnamese QA reports.
Coordinate a bounded, evidence-backed QA run from requirements through release recommendation. Use for end-to-end QA planning, execution, retests, regressions, or exploratory browser checks.
Turn product requirements into traceable QA requirements and coverage obligations. Use when analyzing specifications, acceptance criteria, ambiguities, risks, or test scope.
Prepare, bind, and clean up declared QA test data through trusted runtime hooks. Use when a test run needs fixtures, secret references, data setup, or cleanup verification.
Design deterministic, traceable browser test cases from approved requirements and coverage obligations. Use when creating, revising, parameterizing, or reviewing QA test cases.