625건 · 관련도순
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when starting, stopping, or inspecting the dev stack for this Hydrolix Grafana datasource plugin — Grafana (with the plugin bind-mounted), ClickHouse, Keycloak (OAuth), and the on-demand playwright runner. Covers `docker compose up` semantics, the `dist/` prerequisite, serving plugin artifacts from an alternate folder (any path, live or frozen, via an ephemeral compose override), switching Grafana versions, hot-reload behaviour, delve attach, log streaming, OAuth/anonymous auth, and ClickHouse fixture access. Apply whenever a task needs the plugin running locally, needs to reset the stack, or needs to debug why Grafana won't come up.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when running the dev Grafana stack and/or the Playwright e2e suite against a *packaged* plugin zip (a release/RC artifact like `hydrolix-hydrolix-datasource-<ver>.zip`) rather than the working-tree `dist/`. Unpacks the package into a timestamped `dist_<timestamp>/dist` sandbox alongside copies of the compose artifacts, so the run is reproducible and the folder stays available to experiment with afterwards. Delegates stack bring-up to `stack-run` (frozen mode: read-only mount + `DEV=false` so the mage-watcher can't rebuild the packaged Go binary), verifies signature/version, runs the suite, and treats cleanup as optional — the sandbox is deleted only with the user's approval. Apply whenever the task is "test this plugin package / zip" or "run e2e against the built artifact".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Playwright automation, Chrome DevTools debugging, and browser interaction testing. Use for E2E/unit tests, capturing screenshots, inspecting network/console logs, or validating user flows in web applications.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to React/Next.js/Playwright/docs/code-quality experts. Keywords: which agent, best agent for this, delegate to expert, agent capability mapping.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
To test local web applications, write native Python Playwright scripts.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Web scraper with SPA/JavaScript rendering, page interaction, and JS execution. Two-tier engine (HTTP → Playwright browser). Smart discovery, batch fetch, interactive content extraction, OpenAPI parsing. Use when read_url_content fails, SPA rendering needed, or page interaction required.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Smoke tests contra URL Vercel deployada (preview ou production). Verifica saude minima do deploy — homepage, assets, auth, console errors, performance. Usa Playwright CLI ou suite de smoke tests. Use apos cada deploy para garantir que nada quebrou.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Avalia qualidade UX de um projeto comparando screenshots reais contra a Design Library (24 solucoes + design system). Captura telas via Playwright, pontua aderencia a tokens/patterns, identifica desvios. Produz UX Compliance Report.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Automated WCAG 2.1 AA accessibility testing with axe-core and Lighthouse CI. Auto-detects frontend framework (React, Next.js, Vue, Angular, Svelte, Astro, Flutter, React Native), discovers all routes and interactive components, installs Playwright + axe-core for page-level scanning and jest-axe/vitest-axe for component-level testing. Generates tests for color contrast (4.5:1), alt text, form labels, ARIA attributes, heading order, landmark regions, focus visibility, keyboard navigation (tab order, focus traps, modal focus management, skip-to-content), screen reader compatibility (aria-live regions, error announcements, toast notifications), and Flutter Semantics validation (48dp touch targets, semanticLabel). Reports violations by severity (critical, serious, moderate, minor) with WCAG criterion references. Use when adding a11y testing, auditing accessibility compliance, fixing contrast issues, or validating keyboard and screen reader support.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when you need to run real accessibility tests — Playwright keyboard interactions, axe-core scanning, visual regression, and WCAG 2.2 compliance checks. The measurement layer that feeds evidence into a11y-critic reviews.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use after the backend follows the model — derive E2E flow scripts from Lean golden traces, replay them against the Lean-backed dev screens and the real REST backend with Playwright, and compare observations. Also use to add a flow when a new command or screen appeared.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use whenever the screens, UX, wording, feedback after actions, accessibility, or layout of frontend/ come up, even without the word "review" — delegates to the frontend-ux-reviewer agent, which runs the dev screens against the Lean CLI with Playwright and reports with evidence. Not for reviewing the domain model itself (that is the ddd skill's review).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only for external windows or desktop UI that needs OS-level control, and Playwright or CDP for external pages.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
23 engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365. 30+ Python tools (stdlib-only).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot diff", "screenshot test", "storybook regression", "playwright snapshot", asks why a PR is blocked or what changed visually, wants to triage the VR backlog, decide whether a snapshot diff is real vs flaky, or check whether a story has been changing across runs. Also invoke when a PR has a failing `visual-review` status check, when a PR comment mentions "Visual review", or when the user is on a branch with an open VR run.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Execute a user flow step-by-step in Cursor's built-in browser while documenting each action, then emit a Playwright test that replays the same flow using stable selectors derived from the accessibility tree.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Set up Playwright end-to-end testing in a project, including test configuration, example tests, and CI integration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.