skills.rest
krbylit
krbylitCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate web navigation, form filling, and data extraction via ref-based element interaction.

1|Updated Jan 11, 2025
Search Tags:#cli#web-scraping#browser-automation#form-filling#agent-browser#element-refs
One-click install
npx skills add https://github.com/krbylit/dotfiles --skill agent-browser-krbylit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/krbylit/dotfiles/tree/main/cm-util/pkg-backups/beads-compound/0.6.8/gemini/skills/agent-browser
Command: npx skills add https://github.com/krbylit/dotfiles --skill agent-browser-krbylit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables AI agents to automate web interactions using Vercel's agent-browser CLI, allowing scripted browsing, form filling, and data extraction without manual browser control.

Core Features & Use Cases

  • Navigate to URLs and interact with page elements using ref-based selectors (@e1, @e2) for deterministic automation.
  • Snapshot page state to identify interactive elements, then perform actions such as click, fill, type, and scroll.
  • Scrape data or verify page content by extracting text or attributes and exporting results for downstream tasks.
  • Use Case: Automate a form submission workflow across multiple websites, capturing results and errors for reporting.

Quick Start

Open a website, snapshot interactive elements to obtain refs, and perform actions using those refs to complete a task.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web form filling using a CLI browser automation tool?▼

Automate web form filling by navigating to a URL, snapshotting the page to find interactive elements, and using ref-based selectors to fill and submit forms deterministically. This approach captures results and errors without manual browser control.

How does ref-based element interaction work for web scraping?▼

Ref-based element interaction works by snapshotting a page to identify interactive elements, then performing actions like click, fill, or scroll using assigned ref selectors. This deterministic method ensures accurate data extraction and web navigation.

Do I need Chromium installed to automate web navigation with the agent-browser CLI?▼

Yes, automating web navigation with the agent-browser CLI requires both the CLI installed via npm and a local Chromium download. These components provide the underlying browser environment required to execute scripted browsing and data extraction tasks.

Can I extract text and attributes from web pages for downstream automation tasks?▼

Yes, you can extract text and attributes by snapshotting page state and interacting with elements using ref selectors. This allows you to scrape data or verify page content and export results for downstream automation workflows.

What is the best way to automate a form submission workflow across multiple websites?▼

Automate form submission workflows by navigating to URLs, snapshotting interactive elements to obtain refs, and performing fill and click actions. This deterministic ref-based approach ensures reliable execution and captures errors for reporting.

Why use ref-based selectors instead of standard CSS selectors for browser automation?▼

Ref-based selectors provide deterministic automation by referencing elements directly from a page snapshot. This avoids the fragility of standard CSS selectors during web navigation, form filling, and data extraction tasks.

Related Skills

Explore More Software Engineering Skills→
drhazemibclcdrhazemibclc

agent-browser

Drive a headless browser via CLI using ref-based element selection.

Community
Advanced
yudameyudame
2

podcast-feed-validator

Validate podcast RSS feeds against the Yudame RSS specification.

Official
Intermediate
8b-is8b-is

agent-browser

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

Official
Advanced
shades-of-webshades-of-web

agent-browser

Automates web page navigation, form filling, and data extraction using Python libraries like selenium and pyppeteer.

Official
Intermediate