skills.rest
yutna
yutnaCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser tasks including form filling, screenshots, and content scraping.

2|Updated Feb 13, 2026
Search Tags:#automation#testing#screenshots#ai#agent#browser#data-extraction
One-click install
npx skills add https://github.com/yutna/vibe-next-template --skill agent-browser-yutna
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/yutna/vibe-next-template/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/yutna/vibe-next-template --skill agent-browser-yutna

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for AI agents that need to interact with websites, fill forms, capture data, or test web apps.

Core Features & Use Cases

  • Navigate and interact with web pages programmatically
  • Snapshot-based refs for efficient data extraction and validation
  • Multi-session isolation, templates, and references to extend workflows

Quick Start

Open a login page, snapshot the form, fill credentials, submit, and verify the dashboard.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser tasks like filling forms and capturing screenshots for testing?▼

Browser automation handles web page navigation, form filling, and screenshot capture programmatically for AI agents. It uses snapshot-based refs to interact with elements and validate results across isolated sessions, reducing manual testing and data extraction effort.

What is the best way to scrape web content and extract data using an AI agent?▼

Scraping web content with an AI agent uses snapshot-based refs for efficient data extraction and validation. The runtime supports session isolation so agents can open sites, capture content, and automate recurring extraction workflows without manual browser interaction.

How do I set up session isolation for automated browser workflows across multiple sessions?▼

Session isolation is configured through the agent-browser runtime, which supports multi-session templates and references to extend workflows. AI agents run isolated browser tasks concurrently, maintaining separate contexts for different automated interactions without session collision.

Do I need the agent-browser runtime to use snapshot-based refs for web testing?▼

The agent-browser runtime is required to support session isolation, refs-based interactions, and optional references that extend capabilities. Snapshot-based refs enable efficient data extraction and validation by targeting specific page elements during automated web app testing.

Can I automate recurring browser workflows like opening websites and submitting forms across sessions?▼

Recurring browser workflows are supported through templates and multi-session isolation. Agents automate opening websites, filling forms, capturing screenshots, and scraping content across sessions, reducing manual testing and data extraction toil through programmable interactions.

What are the limitations of using AI-driven browser automation for web app testing?▼

AI-driven browser automation depends on the agent-browser runtime for session isolation and refs-based interactions. Complex dynamic pages may require optional references to extend capabilities, and workflows rely on snapshot-based element targeting rather than visual rendering for validation.

Related Skills

Explore More Software Engineering Skills→
hidonguyenhidonguyen

ck:agent-browser

Automate browser navigation and element interaction via refs-based CLI snapshots.

Community
Advanced
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
farzanmrzfarzanmrz
6

agent-browser

Automate browser UI tasks via CLI for testing and data extraction.

Community
Advanced
ricablericable
1

Claude Flow Browser

Automate browser interactions with Playwright for scraping, form filling, and testing.

Community
Intermediate