Browser Automation Agent Skills

Opens plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like "move this, change that" is easier pointed at than typed.

Automates Chrome/Chromium via CDP with accessibility-tree snapshots and element refs, covering web pages, Electron apps, Slack, and cloud browsers.

Iteratively builds websites with Stitch by reading a baton file, generating pages via MCP tools, integrating them, and writing the next task.

Automates filling out developer job applications on crypto exchange career sites using browser automation, with the user manually submitting each form.

Discover online MetaBots and their services, browse Bot pages in a local browser, and maintain local directory sources for the MetaWeb network.

Test local web applications by writing native Python Playwright scripts, with helpers for server lifecycle management and a reconnaissance-then-action pattern for dynamic UIs.

Extract content, metadata, and images from a webpage for import or migration to AEM Edge Delivery Services.

Searches for existing content pages containing a specific block in AEM Edge Delivery Services, reporting URLs with occurrences and variants to help identify test content during development.

Generates a Playwright test from a user-provided scenario by recording browser interactions via Playwright MCP, then saves and runs the test until it passes.

Detects and removes disruptive overlays (cookie banners, modals, paywalls, login walls) from webpages before screenshots, scraping, or browser automation.

Reduces a webpage to a structural skeleton by tokenizing content in the browser and applying LLM reasoning to collapse repeated patterns.

Extract structured resources (icons, metadata, text, forms, videos, social links) from any webpage using playwright-cli.

Reverse-engineers custom JavaScript-based WASM virtual machines and risk-control engines by identifying DSL VM patterns, extracting opcodes, analyzing constant tables, and tracing exported functions through static analysis and runtime injection.

Automates Xiaohongshu (Little Red Book) operations including authentication, content publishing, search, social interaction, and composite workflows via a CLI tool.

Transforms ideas, files, folders, URLs, or exported data into polished single-file HTML pages with auto-selected design systems.

Posts text, images, videos, and long-form articles to X (Twitter) using a real Chrome browser to bypass anti-bot detection.

Turns websites into CLI commands, reusing an existing Chrome login session for browser-backed data extraction and structured output.

Interact with and test local web applications using Playwright, including verifying frontend functionality, debugging UI behavior, capturing screenshots, and viewing browser logs.

Handles all networked operations through a real browser via CDP, including search, page scraping, login-required actions, and social media content extraction.

Automates browser testing and interaction with Playwright, including form filling, screenshots, responsive checks, and login flows, with automatic dev server detection.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Search the web, scrape pages, crawl sites, and interact with dynamic content via the Firecrawl CLI, returning clean markdown for LLM contexts.

Automates browser interactions and testing with Playwright, including form filling, screenshots, responsive checks, and login flows, with automatic dev server detection.

Records polished demo videos of web applications using Playwright, with an injected cursor overlay, natural pacing, and a discover-rehearse-record workflow.

Interact with and test local web applications using Playwright, including verifying frontend functionality, debugging UI behavior, capturing screenshots, and viewing browser logs.

Records polished UI demo videos of web applications using Playwright, with an injected cursor overlay, natural pacing, and a discover-rehearse-record workflow.

Runs comprehensive SEO audits and analysis for websites, covering technical SEO, content quality, schema markup, Core Web Vitals, local SEO, and AI search optimization using browser automation tools.

Guides users through creating, testing, and deploying browser automation functions with the Stagehand CLI, including interactive site exploration, coding, and deployment to Browserbase.

Activates for web scraping and Actor development, discovering APIs via traffic interception, recommending optimal strategies, and implementing iteratively. For production, it guides TypeScript Actor creation via Apify CLI.

Mint a unique 1/1 villain NFT from CHUM's agent-only collection on Solana, with a 0.001 SOL mint fee plus network fees.

Tests and debugs web applications in real browsers using Chrome DevTools MCP, enabling DOM inspection, console error capture, network analysis, performance profiling, and visual verification with live runtime data.

Execute AEM Edge Delivery Services admin operations: manage content, cache, code, indexes, sitemaps, snapshots, logs, users, jobs, sites, config, secrets, API keys, tokens, profiles, and versioning. Also supports Document Authoring operations.

Convert static HTML pages to Edge Delivery Services while preserving original design and enabling content authoring in Document Authoring.

Import a single webpage from any URL into canonical EDS block format — structured HTML that authors edit in DA. Scrapes the page, analyzes structure, maps to existing blocks, and generates HTML for immediate local preview.

Run the HyperFrames CLI to scaffold, author, lint, preview, render, and publish video compositions locally or on HeyGen Cloud, AWS Lambda, and Google Cloud Run.

Extract audio and video metadata such as duration and dimensions using the Mediabunny library in the browser.