agent-browser-stagehandAutomate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Install via ClawdBot CLI:
clawdbot install peytoncasper/agent-browser-stagehandGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
$ANTHROPICCalls external URL not in known-safe list
https://example.comAI Analysis
The skill legitimately uses Browserbase API keys for remote browser automation as documented, and example.com is a standard example URL, not evidence of malicious data exfiltration. However, accessing environment variables and external APIs creates a low-level risk surface that warrants user awareness.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 1, 2026
Automate daily price checks across competitor websites to track market trends and adjust pricing strategies. Extract product details and prices using natural language commands, enabling real-time competitive analysis without manual browsing.
Navigate to financial news sites and extract key metrics like stock prices or economic indicators for automated reporting. Use screenshots to verify data accuracy and schedule regular updates to support investment decision-making.
Automate property searches on listing websites to collect details such as prices, locations, and amenities. Fill search forms and click through pagination to aggregate data for market analysis or lead generation.
Browse academic journals or databases to extract publication metadata, abstracts, and citations for literature reviews. Use natural language actions to navigate complex sites and capture structured data for research projects.
Automate visits to social media platforms to observe trends, extract post analytics, or monitor brand mentions. Take screenshots for visual verification and use stealth mode to avoid detection during frequent checks.
Offer a subscription-based service where businesses pay monthly for automated web scraping and interaction tasks. Use Browserbase's stealth mode for reliable production scraping, targeting industries like e-commerce and finance with scalable pricing tiers.
Sell curated datasets extracted from websites using this skill, such as competitor prices or market trends. Automate data collection with natural language commands and provide updates via API or reports, focusing on high-demand verticals like real estate.
Provide consulting services to help companies integrate browser automation into their workflows, such as for form filling or monitoring. Charge for setup, training, and ongoing support, leveraging the skill's beginner-friendly commands for quick deployment.
💬 Integration Tip
Start with local mode for testing, then switch to Browserbase for production to handle proxies and CAPTCHAs; always use screenshots to debug actions.
Scored Apr 19, 2026
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows.
Performs deep scraping of complex sites like YouTube using containerized Crawlee, extracting validated, ad-free transcripts and content as JSON output.
Extract structured information from websites using web_fetch for simple pages and browser automation for dynamic sites, login-gated flows, pagination, infini...
OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
A modern text-based browser. Renders web pages in the terminal using headless Firefox.