An advanced browser automation skill for simulating user interactions and performing web-based testing through the Membrane framework.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install selenium
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install selenium using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Selenium?
Selenium is a widely adopted open-source framework designed for the automation of web browsers. This integration within the Openclaw Skills ecosystem allows developers and AI agents to simulate complex user interactions on websites, ensuring that applications function correctly across various environments. By leveraging Membrane, it abstracts the complexities of browser drivers and authentication, providing a streamlined interface for web control.
Through this skill, agents can navigate pages, interact with DOM elements, manage session cookies, and capture visual state via screenshots. It is built to be secure and efficient, handling credential management server-side so that developers can focus on building automation logic rather than infrastructure.
Selenium Use Cases
- Performing automated regression testing for web applications to find UI bugs.
- Scraping data from modern, JavaScript-heavy websites that require browser rendering.
- Automating repetitive web tasks like form filling or report generation.
- Monitoring web services by capturing screenshots and logs for auditing purposes.
How Selenium Works
- The user installs the Membrane CLI to act as the interface between the agent and the browser.
- Authentication is performed via a login command, associating the session with Openclaw Skills.
- A connection is established to a specific URL or domain, which triggers the setup of a Selenium instance.
- The agent searches for available actions (e.g., clicking, typing, or reading elements) using natural language intent.
- Commands are sent to the Selenium driver, and the resulting data or screenshots are returned in a structured format.
Selenium Setup
First, install the CLI globally:
npm install -g @membranehq/cli@latest
Authenticate your agent session:
membrane login --tenant --clientName=openclaw
Establish a connection to your target website:
membrane connection ensure "https://www.example.com/" --json
Once the connection state is READY, you can begin listing and running actions against the browser instance.
Selenium Data Schema & Taxonomy
The skill organizes web data into logical entities for easy manipulation by Openclaw Skills:
| Component | Details |
|---|---|
| Browser/Tab | Managed sessions and active window contexts. |
| Elements | Access to attributes (id, class) and CSS properties. |
| Cookies | Full CRUD operations on browser session cookies. |
| Logs | Access to console logs and browser performance data. |
| Screenshots | Base64 or file-based image captures of the viewport. |
Selenium Advanced Features
- Direct Proxy Requests: Send custom HTTP requests to the Selenium API for edge-case functionality not covered by standard actions.
- Natural Language Action Discovery: Find the right automation command by describing your intent to the CLI.
- Automated Credential Management: Transparently handles OAuth and API keys without exposing secrets locally.
- Headless Execution Support: Optimized for running in CI/CD pipelines or serverless environments without a GUI.
SKILL.md
Loading
Related Openclaw Skills
Nearby Budget Hotels
An intelligent location-based skill for finding and filtering highly-rated budget accommodations in real-time.
Incident Response Plan Generator
A specialized tool for generating tailored incident response plans to secure AI agent deployments and ensure operational resilience.
Shift Scheduler
An AI-driven workforce management tool that automates shift queries, swap requests, and manager approvals for retail environments.
Textin Document Parser
A powerful document AI skill that parses complex PDFs, images, and Office files into structured Markdown and JSON data.
FMP MCP
A comprehensive financial data skill providing real-time stock quotes, deep fundamental analysis, and technical indicators for AI agents.
TestCase Generator
An LLM-driven testing system that generates over 20 detailed test cases by analyzing service code and live database data.
Featured*
