发现优质的 AI Agent 技能

Remote browser automation via Playwright WebSocket server. No local browser installation required.

Cloud browser-use via [Steel.dev](https://steel.dev) + Playwright Python SDK. Ideal for web automation, scraping, form filling, and AI agent browser loops.

Run the bundled Playwright script to log into WPS Time NetTime using macOS Keychain credentials, perform the requested punch action (or status check), take a screenshot, and report results.

v1.2.1: the runtime source is maintained directly in this repository and packaged with the skill. Install script copies repository source locally and runs `npm install --ignore-scripts` to fetch npm dependencies from the registry. Playwright downloads browser binaries on first browser-mode use; API-only tasks (including all Prospairrow tasks) do not require browser binaries.

基于 Python Playwright 的小红书（rednote）交互工具，通过浏览器自动化从 `window.__INITIAL_STATE__`（Vue SSR 状态）中提取结构化数据。

`StealthyFetcher` is a stealthy browser-based fetcher similar to [DynamicFetcher](dynamic.md), using [Playwright's API](https://playwright.dev/python/docs/intro). It adds advanced anti-bot protection bypass capabilities, most handled automatically. It shares the same browser automation model as `DynamicFetcher`, using [Playwright's Page API](https://playwright.dev/python/docs/api/class-page) for page interaction.

`DynamicFetcher` (formerly `PlayWrightFetcher`) provides flexible browser automation with multiple configuration options and built-in stealth improvements.

- A fast Rust-based headless browser automation CLI with a Node.js fallback. - Designed for AI agents to navigate, click, type, and snapshot pages via structured commands. - Uses a background daemon and Playwright for browser control.

> **Platform key:** Lessons marked **(macOS only)** apply when OpenClaw manages the browser via Playwright (e.g. Titan). Lessons marked **(Linux/Ubuntu)** apply to standalone Chrome with direct CDP (e.g. headless Ubuntu server). Unmarked lessons apply to **both platforms**.

电商动态网站爬虫技能，基于Playwright处理JavaScript渲染。

> **⚠️ This is a design / roadmap document, not a description of current functionality.** > > It describes possible future capabilities (Playwright scrapers, flight APIs, hotel search). > **None of the scraping features described here are implemented in the current release.** > Playwright is NOT a dependency. No scraping code exists in `src/`.

> Part of **[ScrapeClaw](https://www.scrapeclaw.cc/)** — a suite of production-ready, agentic social media scrapers for Instagram, YouTube, X/Twitter, and Facebook built with Python & Playwright, no API keys required.