Explorar skills

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Spec-driven manual QA testing and Playwright E2E code generation. Orchestrates browser skills to navigate apps like a human tester, producing structured test reports or production-ready .spec.ts files. Always prompts user for credentials — never guesses or stores auth. Use for QA testing, E2E generation, login flow testing, or exploratory testing from a URL. NOT for AI-autonomous flows (see mk:age

Use when implementing new frontend behavior, fixing bugs, or refactoring logic where tests can describe the expected behavior first. Apply to components, hooks/composables, utilities, API clients, route guards, or user workflows; Chinese triggers include TDD, 测试驱动, 先写测试, 红绿重构, 回归测试.

Run a consensus-loop audit manually — Codex reviews pending trigger_tag items in the watch file. Use when you want to trigger an audit without editing the watch file, re-run a failed audit, or test the audit prompt.

Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.

Native macOS GUI automation via peekaboo 3.0+. AX-first hybrid with VLM fallback, FSM-based workflows with bug-specific transitions. Safari web automation, native app control, social media operations, system dialogs, cross-app workflows.

End-to-end task orchestration across AI coding engines. Coordinates Claude, Codex, Codex Spark (the faster Codex variant), and OpenCode workers using dispatch-verify-synthesize workflows. Requires the upstream agent-mux CLI for worker dispatch. Use when work spans multiple dependent steps, benefits from model diversity, or needs structured quality verification.

AI-agent-driven browser automation (long autonomous sessions, Browserbase-capable). Use when the user needs to interact with websites across many steps, automate complex browser tasks, or run unattended flows. Triggers include 'open a website', 'fill out a form', 'automate browser actions', 'login to a site', or any task requiring programmatic web interaction. NOT for manual E2E test generation (s

Use when running builds, executing tests, or improving developer experience workflows - provides structured guidance for build/test execution and DX improvement.

Uma ferramenta dialética adversarial inspirada em GAN, que alterna entre um Gerador (advogado criativo) e um Discriminador (crítico adversarial). Suporta seleção forçada de papéis (g/d), modos de intensidade (hard/soft) e saída multilíngue, sendo ideal para testar ideias, planos de negócios, código e designs de especificações.

Complete knowledge domain for Cloudflare Browser Rendering - Headless Chrome automation with Puppeteer and Playwright on Cloudflare Workers for screenshots, PDFs, web scraping, and browser automation workflows. Use when: taking screenshots, generating PDFs from HTML or URLs, web scraping content, crawling websites, browser automation tasks, testing web applications, managing browser sessions, perf

Review test quality and audit test coverage for any module. This skill should be used when reviewing existing tests, auditing test gaps, writing new tests, or when asked to assess test health. It pipelines testing standards into the audit workflow to produce a prioritized gap report. The output is a report, not code — do not write test implementations until the report is reviewed.