MCP App StoreMCP App Store
from skill-factory219
Control a web browser via terminal: snapshot accessibility trees, interact with elements by reference, and automate web forms.
This skill provides a command-line interface for driving a browser using Playwright. It allows an agent to 'see' the page via snapshots of the accessibility tree (with stable references), act on elements, and verify results through screenshots or console logs.
Use this skill for automating browser interactions, filling out web forms, testing UI elements, or interacting with logged-in web applications where a standard API is unavailable.
Compatible with any agent harness providing a shell and the playwright-cli binary (e.g., OpenClaw, Codex, etc.).
This skill has not been reviewed by our automated audit pipeline yet.
Agent Browser — Core
Core usage guide for agent-browser: snapshot-and-ref browser automation to navigate pages, interact with elements, extract data, take screenshots, manage sessio
Skyvern — AI Browser Automation
Cloud-first AI browser automation platform and SDKs for extracting data, filling forms, downloading files, and running multi-step web workflows from agents or c
PinchTab Development
Developer guide for building, testing, and contributing to PinchTab — commands, workflows, and PR checklist for local development and CI.
AutoCLI
CLI bridge that exposes 50+ websites as command-line interfaces using the user's Chrome session — fast, scriptable browsing and data retrieval.
Deep Research
Run multi-step autonomous research workflows: search, crawl, validate sources, and produce structured research reports and market analyses.
Avenir-Web
Run and improve Avenir-Web autonomous web tasks: choose run mode, validate and refine instructions, execute single or batch runs, and analyze outputs to propose
Browser-Use Automation
CLI-driven browser automation with persistent multi-session support, cookie management, JavaScript execution and parallel workflows for long-running automated t
Dream-to-Video
Convert a user's dream description into a cinematic video prompt, submit to a video-generation pipeline, and download the resulting video files (automated workf