skills.rest
roberto-mello
roberto-melloCOMMUNITY
Explore all skills by this author →
Website𝕏@robertobmelloGitHub

agent-browser

Automate browser interactions using ref-based element selectors via the agent-browser CLI.

50|2|Updated Feb 8, 2026
Search Tags:#cli#headless#browser-automation#form-filling#agent-browser#web-interaction#data-scraping
One-click install
npx skills add https://github.com/roberto-mello/beads-compound-plugin --skill agent-browser-roberto-mello
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/roberto-mello/beads-compound-plugin/tree/main/plugins/beads-compound/gemini/skills/agent-browser
Command: npx skills add https://github.com/roberto-mello/beads-compound-plugin --skill agent-browser-roberto-mello

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browser automation using Vercel's agent-browser CLI enables AI agents to interact with web pages, fill forms, take screenshots, and scrape data without manual UI, using a bash-based workflow with ref-based element selection for deterministic results.

Core Features & Use Cases

  • Navigate, snapshot, and interact with pages via agent-browser commands.
  • Ref-based element targeting (@e1, @e2, etc.) for deterministic interactions.
  • Parallel sessions and a simple CLI workflow for automation tasks like login flows, data extraction, and form submission.

Quick Start

Open a URL with agent-browser open, then snapshot to identify refs and interact with elements using those refs.

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 and data scraping for AI workflows?▼

Browser automation uses a CLI workflow with ref-based element selection to execute deterministic web tasks like form filling and data scraping. It enables AI agents to navigate pages, snapshot content, and interact with elements without manual UI.

What is ref-based element targeting for deterministic browser interactions?▼

Ref-based element targeting assigns identifiers like @e1 or @e2 to page elements during a snapshot. This allows scripts to interact with specific elements deterministically, ensuring consistent execution for navigation, form submission, and data extraction.

How do I start automating web tasks with a headless browser CLI?▼

To start browser automation, open a target URL using the CLI, then snapshot the page to identify element refs. Once refs are identified, use them in subsequent commands to interact with the page for login flows or data extraction.

Does this browser automation approach support running parallel sessions across multiple sites?▼

Yes, the CLI browser automation supports parallel sessions. This allows you to manage multiple web interactions simultaneously, executing tasks like data scraping and page testing across single or multiple sites concurrently.

What are the limitations of using a CLI browser for scripted web interactions?▼

This CLI browser automation enforces safe scripted interactions using explicit element references, meaning tasks require deterministic ref-based selection. It requires the agent-browser CLI and a compatible runtime, limiting ad-hoc or dynamic UI interactions.

Related Skills

Explore More Software Engineering Skills→
ruska-airuska-ai
17

agent-browser

Automate browser navigation, form filling, screenshots, and data extraction via agent-browser CLI.

Official
Advanced
netlifynetlify
32

netlify-forms

Collect HTML form submissions on static sites via Netlify Forms.

Official
Intermediate
moogieonmoogieon

scrape

Extract data from web pages using scripting and HTML parsing.

Community
Intermediate
hathbangerhathbanger

agent-browser

Automate web navigation and interaction via a headless browser CLI.

Community
Intermediate