A powerful automation skill for controlling Chrome via Selenium to browse URLs and capture screenshots programmatically.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install selenium-browser
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-browser 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 Browser Skill?
The Selenium Browser skill empowers AI agents within the Openclaw Skills ecosystem to interact with the web directly. By leveraging Selenium and Chrome, this skill allows agents to navigate to specific URLs, render complex web pages, and generate visual confirmations through high-quality screenshots. It is designed for developers who need their agents to perform real-time web verification, visual auditing, or data extraction from dynamic sites.
This skill is highly configurable, supporting both headless environments for server-side execution and proxy configurations for localized browsing. By integrating this into your workflow, you bridge the gap between text-based AI processing and visual web analysis.
Selenium Browser Skill Use Cases
- Automating visual audits of web pages during development cycles.
- Capturing high-resolution screenshots of dynamic content for documentation.
- Verifying page rendering across different environments using headless mode.
- Accessing geo-restricted content or bypassing IP-based limitations using proxy support.
- Integrating web-based visual feedback into automated agentic workflows.
How Selenium Browser Skill Works
- The skill triggers when a message contains keywords such as Chrome, browser, or screenshot.
- It initializes a Selenium-controlled Chrome or Chromium instance based on pre-defined environment paths.
- The browser navigates to the target URL provided by the user or agent.
- A navigation wait period ensures that dynamic elements are fully rendered before the screenshot is captured.
- The screenshot is saved to a designated local directory, and a JSON payload containing the file path is returned to the Openclaw Skills interface.
Selenium Browser Skill Setup
To get started, ensure you have Google Chrome and Chromedriver installed on your system. Then, install the required Python library within your environment:
pip install selenium
If your binaries are located in non-standard paths, you can configure them via environment variables in your scripts:
export CHROME_BIN="/usr/bin/google-chrome"
export CHROMEDRIVER_PATH="/usr/local/bin/chromedriver"
Selenium Browser Skill Data Schema & Taxonomy
The skill produces a structured JSON response for the agent to process. By default, images are stored in /home/main/clawd/diffusion_pdfs/.
| Property | Type | Description |
|---|---|---|
| status | string | The execution status (e.g., ok or error) |
| screenshot | string | The absolute path to the saved PNG image |
| error | string | Detailed error message if the operation fails |
Selenium Browser Skill Advanced Features
- Full headless mode support for background execution without a display.
- Proxy server integration via CLI arguments for secure browsing.
- Extensible Python backbone allowing for the addition of custom WebDriverWait conditions.
- Automatic directory management for storing and reporting screenshot assets.
- Standardized JSON reporting for easy piping into other Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Humann.Capital Agent Marketplace
A specialized marketplace integration allowing AI agents to outsource complex tasks to humans or other agents via a unified API.
ClawVault Payments
A security middleware enabling AI agents to safely handle crypto payments and virtual Visa card transactions with human-in-the-loop oversight.
DingTalk Push
A versatile utility for sending automated, formatted, and secure messages to DingTalk group robots via webhooks.
shellf.ai
An API-driven philosophy library where AI agents read, reflect, and engage with a community of digital minds.
Towns Protocol Bot SDK
A comprehensive development toolkit for building interactive, blockchain-integrated bots on the Towns Protocol using the Bun runtime and Base network.
SkillForge GitHub Automation Skill
An enterprise-grade automation toolkit for managing GitHub workflows, issues, and pull requests via AI-driven agents.
Featured*
