> browse/registry

> develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

> detox

When the user wants to write end-to-end tests for React Native apps using Detox's gray-box testing approach. Also use when the user mentions "detox," "React Native testing," "React Native E2E," "gray-box testing," or "Wix Detox." For general mobile testing, see appium. For simpler mobile UI flows, see maestro.

> puppeteer

Automate browsers and scrape dynamic websites with Puppeteer. Use when a user asks to scrape JavaScript-rendered pages, automate browser interactions, take screenshots of web pages, generate PDFs from URLs, test web UIs, fill out forms programmatically, crawl SPAs, extract data from dynamic sites, automate login flows, or build web scrapers that need a real browser. Covers headless Chrome, page navigation, DOM interaction, network interception, screenshots, PDF generation, and stealth techniques

> browser-automation

Non-testing browser automation - web scraping, form filling, screenshot capture, PDF generation, workflow automation. For TESTING with Playwright, use e2e-playwright skill instead. Activates for web scraping, form automation, screenshot, PDF, headless browser, Puppeteer, Selenium, automation scripts, data extraction.

> kaggle-finetune

End-to-end workflow for fine-tuning LLMs using Kaggle datasets. Use when downloading datasets from Kaggle for model training, preparing conversation/customer service data for chatbot fine-tuning, or building domain-specific AI assistants. Covers dataset discovery, download, preprocessing into chat format, and integration with PEFT/LoRA training.

> cypress

Assists with end-to-end testing of web applications using Cypress. Use when writing E2E tests, setting up component testing, configuring CI pipelines with parallelization, or building custom test commands. Trigger words: cypress, e2e testing, end-to-end, cypress run, cy.get, integration testing, browser testing.

> crawlee

Build reliable web scrapers and crawlers with Crawlee — Apify's open-source framework for structured web scraping. Use when someone asks to "scrape a website", "build a crawler", "Crawlee", "web scraping at scale", "scrape JavaScript-rendered pages", "crawl with Playwright/Puppeteer", or "extract data from websites reliably". Covers HTTP crawling, browser crawling, request queues, proxy rotation, and data export.

> observability-setup

Set up end-to-end observability for microservices. Use when someone asks to "add tracing", "set up monitoring", "configure OpenTelemetry", "build Grafana dashboards", "distributed tracing", "structured logging", "metrics collection", or "debug production issues". Covers OpenTelemetry instrumentation, collector configuration, Grafana LGTM stack deployment, dashboard provisioning, and alert rules.

> puppeteer-pdf

Generate pixel-perfect PDFs from HTML and CSS using Puppeteer — render web pages or HTML templates to PDF with full CSS support including flexbox, grid, web fonts, and print media queries. Use when tasks involve converting HTML reports to PDF, generating invoices from templates, or creating PDFs that require complex CSS layouts.

> azure-playwright-workspaces

Expert knowledge for Playwright Workspaces development including troubleshooting, best practices, decision making, limits & quotas, security, and configuration. Use when managing Playwright Testing workspaces, tokens/RBAC, quotas, monitoring/metrics, or run/AADSTS7000112 issues, and other Playwright Workspaces related development tasks.

> research-refine-pipeline

Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

> research-pipeline

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research direction all the way to a submission-ready paper. Use when user says \"全流程\", \"full pipeline\", \"从找idea到投稿\", \"end-to-end research\", or wants the complete autonomous research lifecycle.

> customer-journey-map

Create an end-to-end customer journey map with stages, touchpoints, emotions, pain points, and opportunities. Use when mapping the customer experience, identifying friction points, improving onboarding, or visualizing the user journey.

> chrome-devtools

Browser debugging, performance profiling, and automation via Chrome DevTools MCP. Use when user says "debug this page", "take a screenshot", "check network requests", "profile performance", "inspect console errors", or "analyze page load". Do NOT use for full E2E test suites (use playwright-skill) or non-browser debugging.

> designing-tests

Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.

> azure-microsoft-playwright-testing-ts

Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scaling browser tests across cloud-hosted browsers, integrating with CI/CD pipelines, or publishing test results to the Azure portal.

> web-to-markdown

Use ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or 'use a skill web-to-markdown ...'). Converts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages.

> playwright-skill

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing. Do NOT use for quick page debugging or network inspection (use chrome-devtools instead).

> ml-pipeline-workflow

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

> playwright-blazor-testing

Write UI tests for Blazor applications (Server or WebAssembly) using Playwright. Covers navigation, interaction, authentication, selectors, and common Blazor-specific patterns.