agent-browser
When to use this skill
Use this skill whenever the user wants to:
- Automate browser interactions via CLI commands
- Use browser automation for AI agents
- Navigate websites and interact with pages using command-line tools
- Use refs-based element selection for deterministic automation
- Integrate browser automation into AI agent workflows
- Capture snapshots of web pages with accessibility trees
- Fill forms, click elements, and extract content via CLI
- Use semantic locators for more reliable element selection
- Work with browser automation in agent mode with JSON output
- Manage multiple browser sessions
- Debug browser automation with headed mode
- Use authenticated sessions with custom headers
- Connect to existing browsers via CDP
- Stream browser viewport for live preview
How to use this skill
This skill is organized to match the agent-browser official documentation structure (https://github.com/vercel-labs/agent-browser/blob/main/README.md). When working with agent-browser:
-
Install agent-browser:
- Load
examples/getting-started/installation.mdfor installation instructions
- Load
-
Quick Start:
- Load
examples/quick-start/quick-start.mdfor basic workflow examples
- Load
-
Learn core commands:
- Load
examples/commands/basic-commands.mdfor basic commands (open, click, fill, etc.) - Load
examples/commands/advanced-commands.mdfor advanced commands (snapshot, eval, etc.) - Load
examples/commands/get-info/for information retrieval commands - Load
examples/commands/check-state/for state checking commands - Load
examples/commands/find-elements/for semantic locator commands - Load
examples/commands/wait/for wait commands - Load
examples/commands/mouse-control/for mouse control commands - Load
examples/commands/browser-settings/for browser configuration - Load
examples/commands/cookies-storage/for cookies and storage management - Load
examples/commands/network/for network interception - Load
examples/commands/tabs-windows/for tab and window management - Load
examples/commands/frames/for iframe handling - Load
examples/commands/dialogs/for dialog handling - Load
examples/commands/debug/for debugging commands - Load
examples/commands/navigation/for navigation commands - Load
examples/commands/setup/for setup commands
- Load
-
Understand selectors:
- Load
examples/selectors/refs.mdfor refs-based selection (@e1, @e2, etc.) - Load
examples/selectors/traditional-selectors.mdfor CSS, XPath, and semantic locators
- Load
-
Use agent mode:
- Load
examples/agent-mode/introduction.mdfor agent mode overview - Load
examples/agent-mode/optimal-workflow.mdfor optimal AI workflow - Load
examples/agent-mode/integration.mdfor integrating with AI agents
- Load
-
Advanced features:
- Load
examples/advanced/sessions.mdfor session management - Load
examples/advanced/headed-mode.mdfor debugging with visible browser - Load
examples/advanced/authenticated-sessions.mdfor authentication via headers - Load
examples/advanced/custom-executable.mdfor custom browser executable - Load
examples/advanced/cdp-mode.mdfor Chrome DevTools Protocol integration - Load
examples/advanced/streaming.mdfor browser viewport streaming - Load
examples/advanced/architecture.mdfor architecture overview - Load
examples/advanced/platforms.mdfor platform support - Load
examples/advanced/usage-with-agents.mdfor AI agent integration patterns
- Load
-
Configure options:
- Load
examples/options/global-options.mdfor global CLI options - Load
examples/options/snapshot-options.mdfor snapshot-specific options - Load
examples/options/session-options.mdfor session management options
- Load
-
Reference API documentation when needed:
api/commands.md- Complete command referenceapi/selectors.md- Selector referenceapi/options.md- Options reference
-
Use templates for quick start:
templates/basic-automation.md- Basic automation workflowtemplates/ai-agent-workflow.md- AI agent workflow template
Doc mapping (one-to-one with official documentation)
- See examples and API files → https://github.com/vercel-labs/agent-browser
Examples and Templates
This skill includes detailed examples organized to match the official documentation structure. All examples are in the examples/ directory (see mapping above).
To use examples:
- Identify the topic from the user's request
- Load the appropriate example file from the mapping above
- Follow the instructions, syntax, and best practices in that file
- Adapt the code examples to your specific use case
To use templates:
- Reference templates in
templates/directory for common scaffolding - Adapt templates to your specific needs and coding style
API Reference
- Commands API:
api/commands.md- Complete command reference with syntax and examples - Selectors API:
api/selectors.md- Selector types and usage reference - Options API:
api/options.md- All options reference
Best Practices
- Use Refs: Prefer refs (@e1, @e2) over traditional selectors for deterministic automation
- Snapshot First: Always snapshot before interacting with elements to get refs
- Agent Mode: Use
--jsonflag for machine-readable output in agent mode - Session Management: Use
--sessionto maintain state across commands - Interactive Snapshot: Use
-iflag for interactive snapshot selection - Semantic Locators: Use semantic locators (role/name) when refs are not available
- Error Handling: Check command exit codes and error messages
- Wait for Navigation: Commands automatically wait for navigation to complete
- Headed Mode: Use
--headedfor debugging, headless for production - CDP Integration: Use
--cdpfor Chrome DevTools Protocol integration - Streaming: Use
AGENT_BROWSER_STREAM_PORTfor live browser preview - Authenticated Sessions: Use
--headersfor authentication without login flows - Custom Executable: Use
--executable-pathfor serverless deployments or custom browsers - Snapshot Options: Combine
-i,-c,-d,-soptions to optimize snapshot output
Resources
- GitHub Repository: https://github.com/vercel-labs/agent-browser
- Official README: https://github.com/vercel-labs/agent-browser/blob/main/README.md
- Agent Mode Documentation: https://agent-browser.dev/agent-mode
- Issues: https://github.com/vercel-labs/agent-browser/issues
Keywords
agent-browser, CLI browser automation, AI agents, browser automation CLI, refs, snapshot, agent mode, semantic locators, browser automation tool, command-line browser, AI agent browser, deterministic selectors, accessibility tree, browser commands, web automation CLI, sessions, headed mode, authenticated sessions, CDP mode, streaming, Chrome DevTools Protocol, Playwright, browser automation for AI
More from teachingai/agent-skills
element-plus-vue3
Provides comprehensive guidance for Element Plus Vue 3 component library including installation, components, themes, internationalization, and API reference. Use when the user asks about Element Plus for Vue 3, needs to build Vue 3 applications with Element Plus, or customize component styles.
9vue2
Provides comprehensive guidance for Vue 2.x development including Options API, components, directives, lifecycle hooks, computed properties, watchers, Vuex state management, and Vue Router. Use when the user asks about Vue 2, needs to create Vue 2 components, implement reactive data binding, handle component communication, or work with Vue 2 ecosystem tools.
8cypress
Provides comprehensive guidance for Cypress end-to-end testing including commands, assertions, component testing, CI/CD integration, and best practices. Use when the user asks about Cypress, needs to write E2E tests, component tests, or configure Cypress for testing.
8cocos2d-x
Provides comprehensive guidance for Cocos2d-x v4 game engine including scene graph, nodes, sprites, actions, animations, physics, rendering, shaders, and platform deployment. Use when the user asks about Cocos2d-x, needs to create games, implement game features, set up development environments, or deploy games to multiple platforms.
7dalle
Provides comprehensive guidance for DALL-E AI image generation including prompt creation, image generation, variations, and editing. Use when the user asks about DALL-E, needs to generate AI images, create image variations, or work with DALL-E API.
6uniapp-mini-guide
A comprehensive skill for uni-app mini program development. Use when building uni-app mini programs, configuring mini program settings, or working with mini program components and APIs based on the official native support docs.
6