Skip to content

Automate & organise

Browser tasks · scraping · connecting apps · notes · planning

← Automate & organiseSkills for Automate tasks in a browser

Let your AI click, type and check web pages for you.

  • playwright

    Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.

    From OpenAIIncludes 1 script
  • browser-testing-with-screenshots

    Automate Chrome browser testing with visual verification using browser-tools. Connect to Chrome DevTools Protocol for navigation, interaction, and screenshot capture to confirm application functionality.

    AgentWorkforceRuns terminal commands
  • chromium-browser

    Use Chrome DevTools through PRB's shared attach-only Chromium browser for browsing, debugging, automation, visual inspection, console or…

    PaulRBergIts code sends data over the internet
  • Browser-Use Automation

    CLI tool for persistent browser automation with multi-session support, featuring Chromium/Real/Remote browser modes, cookie management,…

    PramodDuttaInstalls other software
  • browser-edge-cases

    SOP for debugging browser automation failures on complex websites.

    aden-hiveIncludes 10 scripts
  • ego-browser

    ego-browser (ego-lite) is a Chromium-based browser designed from the ground up to be friendly to both human users and AI Agents.

    citrolabsIncludes 9 scripts
  • agent-browser

    Browser automation CLI for AI agents.

    Why this one: Vercel's browser-automation CLI for agents; ~1M installs, 43k stars

    vercel-labsInstalls other software
  • browser-trace

    Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page…

    mxyhiIncludes 8 scripts
  • playwright-cli

    Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli.

    zebbernRuns terminal commands
  • dev-browser

    Browser automation with persistent named pages via the dev-browser CLI.

    SawyerHoodInstalls other software
  • hive.browser-automation

    Required before any hive-browser CLI command.

    aden-hiveContacts outside web addresses
  • mk:playwright-cli

    Session-persistent browser automation via Playwright CLI — form filling, screenshots, data extraction, multi-step flows.

    ngocsangyemRuns terminal commands

See all 36 for “Automate tasks in a browser”

Connectors for Automate tasks in a browser

Connectors (MCP servers) link your AI to an outside tool or service — a different kind of add-on from a skill.

  • com.mcparmory/browserbase

    Create and control browser sessions for web automation, testing, and AI agent tasks

    com.mcparmoryConnectorRuns a program on your computer
  • com.browser-use/browser-use

    Control a real Chrome browser to complete any task: fill forms, extract data, book flights.

    com.browser-useConnectorRuns a program on your computer
  • WebRun Browser Automation

    Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.

    ai.webrunConnectorAsks for an API key
  • Remote Browser MCP Server from MCPBundles

    Automate cloud Chrome—navigate, click, type, screenshot, run code, record screen video

    com.mcpbundlesConnectorAsks for an API key