Web, Search & Scraping Agent Skills for OpenAI Agents SDK

MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web…

Build a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI.

Vannmiljo data pipeline — scrape water monitoring data from vannmiljo.miljodirektoratet.no, build GeoJSON, and ingest into ODP

Use when asked to verify UI changes, check the frontend visually, confirm a page looks correct, test UI interactions, or validate that…

Explicit-use only — invoke when the user explicitly names this skill, or when an active explicitly invoked workflow calls it.

Download video and audio from YouTube and 1000+ sites using yt-dlp.

Visually verify web UI using a rubber duck MCP with Chrome browser tools.

Automate Hyperbrowser tasks via Rube MCP (Composio).

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Browser automation with Puppeteer CLI scripts.

Cloudflare Browser Rendering with Puppeteer/Playwright.

MUST USE for any browser automation tasks.

Enables comprehensive web interaction including deep search, dynamic site scraping, and authenticated browser actions through CDP.

Authenticate to websites with human-in-the-loop browser handoff.

Complete guide for investigating and implementing web browser automation.

Record any web app operation once, AI turns it into a reusable automation tool.

Browse and interact with web pages headlessly.

Web search via Gemini CLI for latest information.

Extracts fully rendered web content and PDFs into ingestion-ready Markdown for AI research and analysis.

Automate Webscraping AI tasks via Rube MCP (Composio).

Extracts full WeChat Official Account articles and exports them into editable Markdown, DOCX, or text formats.