Tag: browser-automation
Deterministic CLI for Agentic Browser Automation
A high-performance command-line interface for headless browser automation, enabling AI agents to perform multi-step workflows with deterministic element selection via accessibility tree snapshots. It supports session isolation, state persis…
Firefox Browser Automation and Debugging
Automate browser interactions, perform E2E testing, and scrape web content using a real Firefox instance. It enables DOM inspection, element interaction via UIDs, and monitoring of console and network activity.
Browser Automation via MCP Tools
A suite of MCP tools for programmatic browser control, featuring a high-performance scripting engine for multi-step web automation. It enables navigating, interacting with elements, and extracting data through efficient single-call workflow…
Automated web research and multi-source analysis
This skill automates comprehensive web research by searching multiple sources, gathering relevant data, cross-referencing facts, and presenting the findings in a structured summary with source citations.
Chrome File Download Automation
Automates file downloads in Chrome on Windows and macOS by managing triggers, handling browser popups, and verifying download completion. The skill monitors progress via Chrome's internal downloads page and validates the file's presence on …
Automating Google Sheets Interactions via Browser
This skill provides comprehensive patterns for automating Google Sheets interactions using browser automation techniques. It guides developers through complex tasks like data entry, formula application, and formatting, while emphasizing rel…
Deterministic CLI for AI Agent Browser Automation
This CLI provides fast, deterministic browser automation for AI agents, utilising accessibility tree snapshots and reference-based element selection. It supports complex multi-step workflows, session isolation, and network control for robus…
Collaborative Headed Browser Session
An interactive skill for collaborative UI development using a headed Playwright Chromium session. It enables agents to drive a visible browser, allowing users to provide real-time visual feedback while the agent performs navigation, interac…
Playwright E2E Testing for Langflow
This skill enables the creation, debugging, and maintenance of Playwright-based end-to-end tests for the Langflow UI. It utilises custom fixtures for automated error detection in API responses and provides a structured approach to testing c…
Comprehensive Browser Automation and Web Interaction Tool
This comprehensive suite enables robust browser automation, allowing developers to perform complex, multi-step web workflows—such as logins or form submissions—in a single call using runtime CSS selectors. It provides granular control over …
Automate Google Sheets interactions via browser automation
This skill provides patterns for automating complex Google Sheets interactions using browser automation techniques. It covers data entry, formula application, formatting, and navigation, advising the use of keyboard shortcuts over standard …
Real browser automation and web interaction
This skill enables the agent to interact with the user's live browser environment. It supports reading page content, filling forms, clicking elements, and handling dynamic Single Page Applications (SPAs) via comprehensive browser APIs.
Firefox Browser Automation and Debugging
Automate Firefox browser interactions, perform E2E testing, and scrape web content using DOM snapshots and element UIDs. It also provides capabilities for monitoring console messages and network requests for debugging.
Playwright CLI for Browser Automation and Testing
This tool provides a comprehensive command-line interface for automating browser interactions. It allows developers to perform tasks such as form filling, data extraction, state management, and complex web testing scenarios.
OpenCLI: Turn Websites into Command Line Tools
OpenCLI transforms any website or Electron application into a functional command-line interface. It provides AI-powered discovery and interaction, allowing developers to automate complex web tasks using familiar CLI syntax while reusing exi…
Chrome DevTools Protocol Automation Skill
Enables deep browser control and inspection via the Chrome DevTools Protocol for network forensics, DOM analysis, and automated screenshots. It supports both headless and visible Chrome instances for complex, authenticated, or interactive a…
CLI for Advanced Browser Automation and Testing
This CLI enables agents to programmatically interact with websites using the Chrome DevTools Protocol (CDP). It supports full web automation, including element snapshotting, complex authentication flows, and robust command chaining for reli…
Playwright Browser Automation and Screenshotting
Provides capabilities for automating a real browser instance to capture screenshots and interact with web content from the terminal.
Automated diff-driven smoke testing
Automates smoke testing by analysing git diffs to identify changes and executing targeted browser-based validation sequences. It utilises Skyvern browser tools to navigate, interact, and validate application state, reporting results directl…
AI-Powered Browser Automation CLI
An agentic CLI tool for automating complex web workflows, including form filling, data extraction, and navigating dynamic content. It supports both deterministic Playwright actions and autonomous AI-driven exploration.
Automated Diff-Driven QA Validation
This skill automates code validation by analysing git diffs to determine the appropriate testing strategy for frontend, backend, or mixed changes. It executes targeted browser automation, API requests, or repository-native tests to report p…
AI-powered browser automation and extraction
An AI-driven engine that uses LLMs and computer vision to automate web workflows, extract structured data, and manage browser sessions. It integrates via Python and TypeScript SDKs, a REST API, and an MCP server.