Automate browser interactions for navigation, form filling, clicking, screenshots, and data extraction.
npx skills add https://github.com/dandaka/skills --skill agent-browser-dandaka
Please help me install this Agent Skill. Skill: agent-browser Source: https://github.com/dandaka/skills/tree/main/agent-browser Command: npx skills add https://github.com/dandaka/skills --skill agent-browser-dandaka
Automates manual and fragile browser tasks like navigating websites, filling forms, clicking UI elements, taking screenshots, and extracting data so workflows become repeatable, faster, and less error-prone.
Open the target site, take an interactive snapshot to discover element refs, perform the required fills and clicks to reach the desired page, wait for the page to stabilize, and save the session state for reuse.
High-intent search queries and answers about installing and using this skill.
To automate web scraping with session persistence, you log into the web app once, save the authenticated state including cookies and localStorage, and reuse that session programmatically across multiple pages to extract structured data.
Yes, Playwright browser automation supports connecting to an existing Chrome instance via CDP connectivity, running in headed mode for debugging, and automating iOS simulators or mobile flows for responsive testing.
For reliable dynamic page scraping, you take an interactive snapshot to discover interactive elements with stable refs, use these semantic locators to perform form filling and clicks, then wait for the page to stabilize before extracting data.
Yes, headless browser automation supports multi-session orchestration by running isolated sessions in parallel, allowing you to manage multiple agents concurrently while maintaining separate authenticated states.
The best way to capture screenshots and PDFs from authenticated web pages is to automate the navigation and login sequence, persist the session state, and programmatically capture pages across the site during your workflow.
You should avoid browser automation for web scraping if the target site offers a stable API, as direct API integration is faster and less fragile than scripting dynamic page interactions and waiting for UI elements to stabilize.
rhpdsConfigure and validate the Playwright MCP server for Claude Code browser automation.
temple-slopeConvert Google Sheets spreadsheets to CSV for backup or downstream processing.
faw01Configure Clerk authentication state for Playwright and Cypress end-to-end tests.
Zerone-AgentAutomate headless browser navigation, form submission, and data extraction via CLI.
