skills.rest
hAcKlyc
hAcKlycCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser tasks via CLI with snapshots and element refs.

815|96|Updated Jan 23, 2026
Search Tags:#automation#testing#cli#browser#data-extraction#web-automation#form-filling
One-click install
npx skills add https://github.com/hAcKlyc/MyAgents --skill agent-browser-hacklyc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/hAcKlyc/MyAgents/tree/main/bundled-skills/agent-browser
Command: npx skills add https://github.com/hAcKlyc/MyAgents --skill agent-browser-hacklyc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automate browser-driven tasks for AI agents by giving a stable CLI to open websites, locate elements, and perform actions without manual scripting.

Core Features & Use Cases

  • Open and navigate pages, interact with elements (click, fill, select), and take snapshots for reliable references.
  • Extract data from pages, validate UI flows, run form submissions, and test web apps across sessions.
  • Use Case: automatically sign in to a site, verify content, and capture proof of success across multiple pages.

Quick Start

Open a website using agent-browser, snapshot the page to identify element refs, perform a form fill, click to submit, and take a screenshot.

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 tasks like form filling and data extraction for AI agents?▼

Automate web tasks by using a CLI to open URLs, snapshot pages for element refs, and execute deterministic actions like form filling and data extraction without manual scripting.

How does snapshotting work for reliable web automation?▼

Snapshotting captures page state to generate stable element refs, which agents use to interact with page elements, minimizing prompt size and ensuring deterministic actions across sessions.

Can I use browser automation to test authentication flows across multiple sessions?▼

Yes, browser automation supports authentication flows across multiple sessions by using the CLI to open URLs, interact with elements, automatically sign in, verify content, and capture proof of success.

What's the best way to extract data from web pages without manual scripting?▼

The best way to extract data without manual scripting is using a CLI that opens websites, locates elements via refs, and collects output, handling data extraction and visual testing deterministically.

Do I need the core CLI to perform deterministic browser actions?▼

Yes, deterministic browser actions require the agent-browser core CLI, which enforces a modular structure with optional references and assets to ensure reliable page interactions and output collection.

Why does web automation fail when interacting with dynamic page elements?▼

Web automation fails when elements shift without stable references. Using snapshotting and ref-based interactions minimizes prompt size and ensures the agent targets the correct page elements deterministically.

Related Skills

Explore More Software Engineering Skills→
abhay-ranaabhay-rana
2

agent-browser

Automate browser tasks via the agent-browser CLI with snapshot-based refs.

Community
Intermediate
zizhenchen47-osszizhenchen47-oss

pdf

Extract text, tables, and metadata from PDF documents.

Community
Advanced
eggent-aieggent-ai
330

playwright-cli

Automate browser interactions for testing, form filling, and data extraction via CLI.

Official
Advanced
krbylitkrbylit

agent-browser

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

Community
Intermediate