agent-browse
Automate browsers, test UIs, and research leads with AI
All Skills in This Repository (6)
Pure Emerald Level IndicatorsBrowser Automation
Automate browser interactions with persistent Playwright sessions via CLI commands.
company-research
Discover and research target companies matching an ICP using Browserbase Search API.
ui-test
Tests web UIs adversarially in a real browser via the browse CLI with structured pass/fail assertions.
browser
Automate web browser interactions through the browse CLI with local and Browserbase remote sessions.
autobrowse
Iteratively runs browser tasks and improves navigation strategies from execution traces.
competitor-analysis
Research competitors via Browserbase Search API and compile HTML comparison reports.
Frequently Asked Questions
FAQPage SchemaHow to install agent-browse?▼
Run `npx skills add browserbase/agent-browse --all -g -y` in your terminal to install the full skill suite globally.
What can I do with Browserbase skills?▼
You can automate browser tasks, scrape protected websites, QA test your app, research sales prospects, and analyze competitors using plain-English requests to your AI agent.
Do I need a Browserbase API key?▼
Only for cloud features like remote browsers, proxies, and CAPTCHA solving. Local browsing and UI testing on localhost work without any API key.
Does agent-browse work with Claude Code?▼
Yes. All skills follow the standard SKILL.md format and run natively in Claude Code and other compatible AI coding agents.
Can it test my website for bugs automatically?▼
Yes. The ui-test skill analyzes your git changes or explores your whole app in a real browser, then reports bugs with screenshots and suggested fixes.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core