skills.rest
mirandagabrieldev
mirandagabrieldevCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

Updated Aug 23, 2026
Search Tags:#automation#web-testing#browser#screenshot#form-filling#element-refs
One-click install
npx skills add https://github.com/mirandagabrieldev/claude-build-template --skill agent-browser-mirandagabrieldev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/mirandagabrieldev/claude-build-template/tree/main/skills/agent-browser
Command: npx skills add https://github.com/mirandagabrieldev/claude-build-template --skill agent-browser-mirandagabrieldev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Core Features & Use Cases

  • Automated navigation and interaction with web pages using element refs or semantic locators
  • Snapshotting and element manipulation with actions like click, fill, type, and hover
  • Data extraction and screenshot capture for QA, form digitization, and research

Quick Start

Open a URL, snapshot the interactive elements to get refs, then perform clicks, fills, and data extraction as needed.

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 interactions to navigate pages and extract data?▼

Automating browser interactions involves using a CLI tool to open URLs, snapshot interactive elements for refs, and execute clicks, fills, and data extraction. This method handles dynamic websites with built-in waits and state management.

What is the best way to fill forms and capture screenshots during web testing?▼

The best way to fill forms and capture screenshots is by automating browser tasks through a CLI. You open a page, snapshot elements to get semantic locators, fill the target fields, and issue a screenshot command for QA records.

How do element refs and semantic locators work when automating web page snapshots?▼

Element refs and semantic locators work by snapshotting the interactive elements of a web page. The automation tool assigns refs to these elements, allowing subsequent actions like click, fill, type, and hover to target them accurately.

Does browser automation handle dynamic websites that require waits and state handling?▼

Yes, browser automation handles dynamic websites by supporting explicit waits and state handling. This ensures elements are fully loaded and interactive before actions like clicking, filling forms, or extracting data are executed.

Can I use a CLI tool for automated navigation and form filling on dynamic web pages?▼

Yes, you can use a CLI tool for automated navigation and form filling. It provides specific commands for open, snapshot, click, fill, wait, and screenshot, enabling robust interaction with dynamic web pages using safe defaults.

Related Skills

Explore More Software Engineering Skills→
sandmark78sandmark78

agent-browser-wrapper

Map Agent Browser CLI commands to OpenClaw's native browser tool.

Community
Intermediate
rar-filerar-file
42

JSON Formatter

Parse, transform, and validate structured data in JSON, YAML, XML, and related formats.

Community
Intermediate
tharunramagiritharunramagiri

agent-browser

Automate web navigation, element interaction, and data extraction via a headless browser.

Community
Advanced
richardnguyen0715richardnguyen0715

scrapling

Scrape static and JavaScript-rendered web content with stealth and Cloudflare bypass.

Community
Advanced