A natural language interface for browser automation that allows users to navigate, interact, and extract data from the web using simple commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install abby-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 abby-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 Abby Browser Skill?
The Abby Browser Skill is a specialized wrapper built upon the Openclaw Skills browser toolkit, designed to simplify web interaction for AI agents and developers. It eliminates the need to memorize complex CLI syntax by allowing users to control a browser through intuitive natural language. Whether you need to navigate to a specific URL, interact with page elements, or perform complex data extractions, this skill provides a robust bridge between high-level intent and low-level browser execution.
By integrating this skill into your workflow, you gain access to a powerful suite of automation tools including element clicking, text input, and full-page snapshots. It is a core component for anyone looking to build autonomous web agents using Openclaw Skills, providing the visual and interactive capabilities necessary for modern web-based tasks.
Abby Browser Skill Use Cases
- Navigating to websites and web applications using simple natural language requests.
- Capturing full-page screenshots for visual regression testing or documentation.
- Automating form submissions and data entry in complex web interfaces.
- Extracting structured content from pages by generating AI-readable snapshots.
- Waiting for specific page states or text to appear before proceeding with automated workflows.
How Abby Browser Skill Works
- The user issues a command in natural language, such as asking the agent to open a specific website.
- The skill invokes the Openclaw Skills browser engine to launch a Chromium instance and navigate to the target address.
- Interactive elements on the page are assigned unique reference (ref) IDs through a snapshot process.
- The agent analyzes the snapshot to identify the correct ref ID for elements like buttons or input fields.
- The browser executes the requested action, such as clicking a button or typing text, and confirms the result to the user.
Abby Browser Skill Setup
To get started with this skill, ensure you have Chrome or Chromium installed. The skill relies on the Openclaw Skills browser core. Use the following commands to initialize and test the browser environment:
# Open a website
openclaw browser open https://google.com
# Capture the current page
openclaw browser screenshot --full-page
# Take a snapshot to see element references
openclaw browser snapshot --format ai
Abby Browser Skill Data Schema & Taxonomy
The skill manages browser data and metadata using a structured reference system to ensure precise interaction.
| Component | Type | Description |
|---|---|---|
| ref | Integer | A unique identifier for every interactive DOM element generated during a snapshot. |
| snapshot | Format | Structured page data available in AI-optimized or ARIA accessibility formats. |
| screenshots | File | PNG images of the viewport or full page saved to the local workspace. |
| fields | JSON | A collection of ref IDs and values used for batch form filling. |
Abby Browser Skill Advanced Features
- Element Reference (ref) System: Assigns stable IDs to elements for precise clicking and typing without complex CSS selectors.
- AI-Optimized Snapshots: Generates page structures specifically formatted for LLM consumption and logical reasoning.
- JavaScript Evaluation: Execute custom scripts directly in the browser context via the evaluate command for advanced manipulation.
- Conditional Waiting: Intelligent wait mechanisms that pause execution until specific text or selectors are detected in the DOM.
- Secure Execution: Built-in safety protocols including action logging and manual confirmation for sensitive web operations.
SKILL.md
Loading
Related Openclaw Skills
Abby Autonomy Skill
An autonomous task execution system that transitions AI agents from passive heartbeat monitoring to proactive, queue-based workflow management.
Office Automation Assistant
An efficient AI agent skill that transforms raw notes into professional daily reports, weekly updates, and meeting summaries.
Jarvis TTS (Text-to-Speech)
A high-performance text-to-speech engine for macOS utilizing Microsoft edge-tts to deliver human-like neural voice output.
Bilibili Video Player
A terminal-based automation tool that uses Playwright to search Bilibili and launch video links directly in your default macOS browser.
Abby Watch
A streamlined time management utility for checking current time and tracking countdowns directly from the command line.
Friday (星期五)
A dedicated AI programming agent designed for automated code generation, security audits, and intelligent refactoring via the opencode CLI.
Featured*
