skills.rest
KentwareDemo
KentwareDemoCOMMUNITY
Explore all skills by this author →
GitHub

browser

Automates web browser navigation, interaction, and data extraction using AI-optimized accessibility snapshots.

1|Updated Jun 3, 2026
Search Tags:#browser automation#web scraping#form filling#e2e testing#agent-browser#mcp tools#accessibility snapshot
One-click install
npx skills add https://github.com/KentwareDemo/RuView --skill browser-kentwaredemo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/KentwareDemo/RuView/tree/main/.claude/skills/browser
Command: npx skills add https://github.com/KentwareDemo/RuView --skill browser-kentwaredemo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manual web browsing for testing, scraping, and form filling is slow and error-prone, and raw DOM dumps overwhelm AI agents with irrelevant markup. This Skill provides browser automation with compact accessibility-tree snapshots that reduce context usage by 93% through element references. ## Core Features & Use Cases - AI-Optimized Snapshots: Capture interactive elements only with stable refs (@e1, @e2) instead of full DOM trees, then click, fill, or extract using those refs. - Full Interaction Set: Navigate, click, fill forms, press keys, scroll, wait for elements or URLs, and capture screenshots. - Multi-Session Support: Run isolated parallel sessions for swarm workflows, including saving and loading authentication state between sessions. - Use Case: Automate a login flow by opening the page, snapshotting interactive elements, filling credentials via refs, clicking submit, and waiting for the dashboard URL. ## Quick Start Ask the agent to open a URL with the browser skill, take an interactive snapshot, and click or fill elements using the returned refs.

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate browser interactions with an AI agent?▼

Open a URL with agent-browser, run snapshot -i to get interactive elements with refs like @e2, then use click, fill, or type commands against those refs. Re-snapshot after any navigation since page state changes invalidate old refs.

How to fill and submit a web form programmatically?▼

Navigate to the form page, snapshot interactive elements, then use fill with each input's ref to set values and click the submit button's ref. Confirm success with wait --text or wait --url to detect the post-submit state.

What is the difference between element refs and CSS selectors in browser automation?▼

Element refs (@e1, @e2) come from accessibility snapshots and are deterministic for the current page state, while CSS selectors target DOM structure directly. Refs are recommended because they are more reliable and produce smaller, AI-friendly output.

Can I run multiple browser sessions in parallel?▼

Yes, use the --session flag to create isolated sessions, each with its own browser state. You can save authentication state from one session with state save and load it into another with state load.

Why does my browser automation fail after clicking a link?▼

Element refs become stale after navigation or DOM changes, so clicks using old refs fail. Always run a fresh snapshot after page transitions and use wait commands to ensure the page has finished loading.

Related Skills

Explore More Software Engineering Skills→
kachilu-inckachilu-inc
38

kachilu-browser

Automate browser navigation, form filling, and data extraction for AI agents.

Official
Advanced
YrzheYrzhe
33

intelligent-web-scraper

Learn and reuse web scraping patterns across list and detail pages.

Community
Advanced
involvexinvolvex

android_ui_verification

Automate Android emulator UI testing with ADB and uiautomator.

Community
Intermediate
eddmanneddmann
2

playwright

Render dynamic web pages with Playwright to capture HTML, text, and screenshots.

Community
Intermediate