Agent Browser - Stagehand

Automate 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. As a specialized domain skills skill, Agent Browser - Stagehand extends AI agent capabilities by providing structured instructions and tools that agents can dynamically load and execute.

Key Capabilities:

• Coordinate and dispatch tasks across multiple AI agents
• Author and verify new agent skills automatically
• Maintain session continuity and context across interactions
• Enable agents to self-improve through captured learnings

Common Use Cases:

• Building multi-agent systems for complex workflows
• Automated skill creation and quality verification
• Long-running agent session management and summarization
• Continuous agent improvement through error and learning capture

How It Works: Agent Browser - Stagehand works as a modular skill package that AI agents load on demand. When you ask an agent to perform a related task, it dynamically activates this skill's instructions, scripts, and templates — no configuration changes or API keys required. Skills are portable across Claude Code, GitHub Copilot, VS Code, Cursor, Windsurf, and other compatible agents.

Details: Category: Specialized Domain Skills · Type: Content & Media · Provider: ClawHub Community