skills.rest
Lento47
Lento47COMMUNITY
Explore all skills by this author →
GitHub

browser-automation

Automates Chrome browser navigation, form filling, and data extraction via agent-browser MCP tools.

1|Updated Jun 17, 2026
Search Tags:#browser automation#mcp#web scraping#form filling#chrome#screenshot#agent-browser
One-click install
npx skills add https://github.com/Lento47/arcana --skill browser-automation-lento47
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-automation
Source: https://github.com/Lento47/arcana/tree/main/skills/browser-automation
Command: npx skills add https://github.com/Lento47/arcana --skill browser-automation-lento47

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser.

What problem does it solve? Manually browsing websites to fill forms, click through flows, take screenshots, or scrape data is slow and error-prone. This Skill gives an AI agent direct control of a real Chrome browser through agent-browser MCP tools, so web tasks can be executed and verified programmatically. ## Core Features & Use Cases - Page Interaction: Open URLs, snapshot the accessibility tree, and click or fill elements using stable @eN refs that survive DOM changes. - Data Extraction & Capture: Read page text, run JavaScript in the page for structured extraction, and take full-page annotated screenshots. - Login & Session Handling: Automate login flows with wait conditions, and optionally persist cookies across runs using agent-browser's --session and --restore flags. - Use Case: Ask the agent to log into a web app, navigate to a reports page, fill in filter criteria, and extract the resulting table data — all without writing any test code. ## Quick Start Ask the agent to open a website, fill in the login form, and take a screenshot of the dashboard.

Frequently Asked Questions about browser-automation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks with agent-browser?▼

Open a URL, take a snapshot to get the accessibility tree with @eN refs, then interact using click and fill with those refs. Re-snapshot after every page change because refs go stale when the page updates.

How to fill forms and click buttons in browser automation?▼

Snapshot the page to find the input and button refs, then use fill for text fields and click for buttons. For custom inputs that reject fill, focus the element first and type character by character.

Does agent-browser keep cookies and login state between sessions?▼

Each session starts fresh with no cookies or login state by default. For persistence, run agent-browser with --session and --restore flags via the shell, which saves state to disk on close.

Why does my browser automation fail with ref not found errors?▼

The @eN refs become stale whenever the page changes through navigation, form submits, or re-renders. Take a fresh snapshot after every page change before using refs again.

What to do when browser tools are missing from the tool list?▼

Missing browser tools mean agent-browser is not installed. Install it globally with npm install -g agent-browser and run agent-browser install, then restart the session.

Related Skills

Explore More Software Engineering Skills→
8b-is8b-is

agent-browser

Automate browser navigation, element interaction, and data extraction via CLI.

Official
Advanced
bharthraj1412bharthraj1412

BrowserControl

Automate browser tasks by navigating pages, interacting with elements, and extracting data.

Community
Advanced
kzinmrkzinmr
7

dogfood

Automate exploratory QA testing of web applications with browser toolset commands and generate structured bug reports.

Community
Advanced
pynbj1001pynbj1001
2

scrapling-official

Scrapes JavaScript-rendered and anti-bot protected websites using adaptive parsing and stealth browser automation.

Community
Advanced