agent-browser
agent-browser enables Claude Code to interact with web pages programmatically, handling clicks, form submissions, and navigation tasks. This skill bridges AI agents and browser automation, letting you build workflows that manipulate web content dynamically. Perfect for testing, data collection, and repetitive web tasks.
agent-browser enables Claude Code to interact with web pages programmatically, handling clicks, form submissions, and navigation tasks. This skill bridges AI agents and browser automation, letting you build workflows that manipulate web content dynamically. Perfect for testing, data collection, and repetitive web tasks. The tool automates browser interactions like clicking, filling forms, and navigating websites with a weight priority of 0.95, making it the primary use case for the skill.
AI-generated summary based on this skill's SKILL.md
Install
ReflexioAI/claude-smart/agent-browser · repository language: Python
git clone https://github.com/ReflexioAI/claude-smart
cp -r claude-smart/.agents/skills/agent-browser ~/.claude/skills/agent-browserFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is agent-browser and how does it enable browser automation for AI agents?
agent-browser enables Claude Code to interact with web pages programmatically, handling clicks, form submissions, and navigation tasks. This skill bridges AI agents and browser automation, letting you build workflows that manipulate web content dynamically. Perfect for testing, data collection, and repetitive web tasks. The tool automates browser interactions like clicking, filling forms, and navigating websites with a weight priority of 0.95, making it the primary use case for the skill.
Can agent-browser click buttons and fill forms programmatically?
Yes, agent-browser is specifically designed to click buttons and fill forms programmatically. It provides the core automation capability to interact with web page elements, enabling you to automate repetitive web tasks without manual intervention. This functionality is central to the skill's purpose of automating browser interactions.
How do I extract data and take screenshots from web pages using agent-browser?
agent-browser supports extracting data and taking screenshots from web pages as a high-priority feature (weight 0.85). You can capture visual snapshots of websites and pull structured data from page content, making it ideal for web scraping, visual regression testing, and documentation purposes. This capability complements the automation features for comprehensive web interaction workflows.
Does agent-browser support testing web applications and verifying page state changes?
Yes, agent-browser enables testing web applications and verifying page state changes (weight 0.75). You can automate web app testing through CLI workflows, validate that page elements respond correctly to interactions, and ensure your web applications behave as expected. This makes it suitable for automated web testing and quality assurance processes.
Can agent-browser handle authentication and maintain browser sessions across tasks?
agent-browser supports handling authentication and maintaining browser sessions across tasks (weight 0.65). This allows you to automate login workflows, persist session state between multiple interactions, and manage authenticated workflows programmatically. Browser session management ensures continuity across complex multi-step automation scenarios.
Does agent-browser support mobile device emulation and responsive layout testing?
agent-browser includes mobile device emulation capabilities (weight 0.5) that enable you to test responsive layouts and verify how web applications behave on different device types. This feature allows you to validate mobile responsiveness and test web apps across various screen sizes and device configurations programmatically.
SKILL.md
rendered from the published skill — quoted content, verbatim
Browser Automation with agent-browser
The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser, brew install agent-browser, or cargo install agent-browser. Run agent-browser install to download Chrome.
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
```bash agent-browser open
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 11 files
.agents/skills/agent-browser/SKILL.md
.agents/skills/agent-browser/references/authentication.md
.agents/skills/agent-browser/references/commands.md
.agents/skills/agent-browser/references/profiling.md
.agents/skills/agent-browser/references/proxy-support.md
.agents/skills/agent-browser/references/session-management.md
.agents/skills/agent-browser/references/snapshot-refs.md
.agents/skills/agent-browser/references/video-recording.md
.agents/skills/agent-browser/templates/authenticated-session.sh
.agents/skills/agent-browser/templates/capture-workflow.sh
.agents/skills/agent-browser/templates/form-automation.sh