A high-performance browser automation skill that enables AI agents to navigate, scrape, and interact with the live web.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install web-navigator
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install web-navigator using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Web Navigator is a robust extension for AI agents designed to provide seamless access to real-time web data and interactive browser sessions. As part of the Openclaw Skills library, it allows developers to build agents that can move beyond their training data to fetch current information, interact with web applications, and extract structured data from complex DOM structures.
This skill is particularly effective for workflows requiring high-fidelity web interaction, such as navigating through paginated results, handling JavaScript-heavy interfaces, or performing multi-step search sequences. By integrating Web Navigator, users can transform their coding agents into comprehensive research and automation powerhouses.
To integrate this capability into your environment, use the following commands:
# Install the skill via the CLI
openclaw add web-navigator
# Ensure dependencies for browser automation are present
npm install playwright
npx playwright install chromium
The Web Navigator skill organizes interaction data and results using the following schema:
| Property | Description |
|---|---|
session_id |
A unique identifier for the current browsing instance. |
target_url |
The primary address being accessed for data extraction. |
extraction_map |
A JSON object mapping CSS selectors to desired data fields. |
navigation_history |
A log of all internal links followed during the session. |
result_payload |
The final structured data extracted from the web page. |
Loading
PulpMiner is an AI-powered tool that converts any webpage into clean, structured JSON data using custom schemas and LLM-driven extraction.

Forge is a repair-inspect loop orchestrator that automates code fixes with independent verification and dependency-aware parallel execution.

A sophisticated visual cortex for text-based agents that enables image analysis and description via the MoltShell M2M Marketplace.

PurposeBot is a comprehensive agentic commerce layer that enables AI agents to discover tools, execute payments via Stripe or USDC, and build verifiable reputation.

A powerful integration for Agile CRM that enables developers to manage sales pipelines, contacts, and tasks through a unified CLI and API interface.

A comprehensive integration for Bullhorn CRM and ATS that enables AI agents to manage recruitment pipelines and candidate data.








































