browser-act
0Browser-act is a browser automation command-line interface specifically designed for AI agents. It offers features like navigation, data extraction, and session management, making it suitable for developers and data scientists who need to automate web interactions.
000Updated 2mo ago
Browser Automation
Quick InstallView Source
uv tool install browser-act-cli --python 3.12Overview
About This Skill
browser-act is a browser automation command-line interface built specifically for AI agents like Claude Code and Cursor. It handles JavaScript-rendered content extraction, multi-browser session management, form automation, screenshots, and network request capture without requiring visible browser windows. The tool manages isolated browser profiles, maintains authenticated sessions across multiple accounts in parallel, and includes verification assistance for interactive challenges. Developers and data scientists use browser-act to automate web interactions, extract dynamic content, fill complex forms, and manage multi-account workflows while keeping all credentials and session data stored locally on their machine.
How to Use
Install using `$ npx skills add https://github.com/browser-act/skills --skill browser-act`
Use Cases
Automate web form filling and data extraction
Capture screenshots of web pages for reports
Enable complex interactions in web applications
Tags
Setup & Installation
Quick Install
Terminal
uv tool install browser-act-cli --python 3.12Alternative Install (Git Clone)
git clone https://github.com/browser-act/skillsRequirements
- Claude Code or compatible AI agent
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Act as a browser automation expert using the browser-act CLI tool. Navigate to [WEBSITE_URL], extract [SPECIFIC_DATA_ELEMENTS], and save the results to [OUTPUT_FILE_PATH]. Use headless mode if possible. Handle any pop-ups or CAPTCHAs with appropriate delays or user interaction. Provide the final output in a structured format (JSON/CSV).
Example Output
```markdown # Browser Automation Report for [WEBSITE_URL] **Generated on:** 2023-11-15 **Session ID:** b8a2c1f4-7e3d-11ee-a503-0242ac120002 ## Extracted Data - **Page Title:** How to Automate Browsers with AI Agents - **Key Metrics:** - Page Load Time: 1.2s - Total Links Found: 47 - Broken Links: 2 - **Top 3 Article Titles:** 1. "Top 10 Browser Automation Tools in 2023" 2. "Headless Browsing: A Developer’s Guide" 3. "AI-Powered Web Scraping Techniques" ## Screenshot Captured  ## Next Steps - Review broken links for fixes. - Schedule automated re-scraping every 24 hours. ```
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan