A comprehensive HTTP API for controlling browser navigation, element interaction, and structured data extraction.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browserwing
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 browserwing 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 BrowserWing?
BrowserWing is a robust browser automation executor designed to provide granular control over web browsers through a clean HTTP API. It allows developers to programmatically navigate URLs, interact with complex page elements, and extract structured data without the overhead of managing browser drivers manually. As a versatile tool within the Openclaw Skills ecosystem, it bridges the gap between high-level AI instructions and low-level browser operations.
The tool is specifically optimized for reliability by utilizing accessibility-based snapshots. This approach provides stable element references (RefIDs) that are more resilient to changes in web design than traditional CSS selectors, making it an ideal choice for building durable automation workflows and AI-driven agents.
BrowserWing Use Cases
- Automating complex login sequences and multi-step form submissions.
- Scraping structured data from dynamic, JavaScript-heavy websites.
- Performing automated accessibility audits and structural analysis of web pages.
- Generating screenshots for visual monitoring and reporting.
- Executing batch web operations to minimize latency and improve agent performance.
How BrowserWing Works
- The skill starts by reading the BROWSERWING_EXECUTOR_URL environment variable to establish a connection to the executor service.
- Users call the discovery endpoint to identify supported commands and required parameters.
- The automation navigates to a target URL and immediately generates an accessibility snapshot to understand the page structure.
- Elements are identified using stable RefIDs (e.g., @e1, @e2) mapped from the accessibility tree.
- Commands like click, type, and extract are sent via POST requests to perform interactions.
- The browser returns JSON-formatted responses containing execution status and any requested data.
BrowserWing Setup
To get started with this component for your Openclaw Skills, configure the executor URL and verify the connection:
# Set the environment variable for the executor service
export BROWSERWING_EXECUTOR_URL="http://127.0.0.1:8080"
# Call the help endpoint to verify the installation
curl -X GET "${BROWSERWING_EXECUTOR_URL}/api/v1/executor/help"
BrowserWing Data Schema & Taxonomy
BrowserWing organizes interaction data through structured identifiers and JSON responses. Below is the metadata taxonomy used for page interaction:
| Data Type | Description | Formats Supported |
|---|---|---|
| Identifiers | How elements are targeted | RefID (@e1), CSS, XPath, Text, ARIA |
| Snapshot | Page structure representation | Accessibility roles, labels, and states |
| Extraction | Structured data fields | Text, href, src, value, attributes |
| Operations | Execution results | Success status, messages, and timestamps |
BrowserWing Advanced Features
- Batch Operation Support: Execute multiple commands in a single HTTP request to optimize performance.
- Intelligent Form Filling: Automatically detect and populate multiple form fields simultaneously.
- Tab Management: Programmatically list, create, switch, and close browser tabs.
- Network & Console Monitoring: Capture network requests and browser console logs for debugging.
- JavaScript Evaluation: Inject and execute custom JavaScript directly within the browser context.
SKILL.md
Loading
Related Openclaw Skills
Relationship OS
An advanced framework enabling AI agents to develop long-term memory, consistent personalities, and evolving relationship stages with users.
Claude Code OAuth Auto-Renewal
A robust automation skill that silently manages the Claude Code OAuth token lifecycle to prevent AI agent interruptions.
Skill Creator
A specialized development framework for scaffolding, documenting, and validating modular AI agent capabilities.
Aliyun OSS Upload
A streamlined tool for uploading local files to Alibaba Cloud OSS and generating secure, time-limited access URLs.
A-Share Real-time Market Monitor & Technical Analysis
A comprehensive A-share monitoring skill offering real-time data, advanced technical analysis, and smart investment advisory without the need for API keys.
World Room
A real-time 3D virtual environment where AI agents collaborate as animated avatars using Nostr-backed communication.
Featured*
