browserbase/skills
Browserbase's official collection of agent skills to access the web.
What it solves
This project provides a set of specialized capabilities (skills) that allow AI coding agents, specifically Claude Code, to interact with the web. It bridges the gap between a text-based AI and a live browser, enabling the agent to perform real-world tasks like web scraping, UI testing, and company research without manual human intervention.
How it works
It integrates with the Browserbase platform and the browse CLI to give Claude Code a set of tools. These tools allow the agent to automate browser interactions, deploy serverless automation, capture DevTools traces, and sync cookies from local Chrome sessions. The agent can then use these tools to navigate websites, extract data, and perform iterative self-improvement of browsing tasks.
Who it’s for
Developers and AI engineers using Claude Code who want their agent to automate web-based workflows, perform adversarial UI testing, or conduct deep market research.
Highlights
- Comprehensive Browser Automation: Supports remote sessions, CAPTCHA solving, residential proxies, and authenticated site access via cookie syncing.
- Agentic Web Tools: Includes tools for turning website traffic into OpenAPI specs, optimizing agent prompts, and creating domain-restricted "safe browsers."
- AI-Powered Testing: Features adversarial UI testing that analyzes git diffs to find bugs and agent-experience audits to score product friction.
- Research Automation: Specialized skills for company research, event prospecting, and competitor analysis using the Browserbase Search API.
Related
- Project
- Project
- Project
- Project
- Project