skills.rest
hellosimplerick
hellosimplerickCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser navigation, form filling, data extraction, and screenshot capture.

Updated Aug 23, 2026
Search Tags:#screenshots#data-extraction#web-scraping#browser-automation#form-filling#headless-browser
One-click install
npx skills add https://github.com/hellosimplerick/nanoclaw-smoke --skill agent-browser-hellosimplerick
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/hellosimplerick/nanoclaw-smoke/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/hellosimplerick/nanoclaw-smoke --skill agent-browser-hellosimplerick

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the manual effort of interacting with web pages for research, testing, form submission, data extraction, and visual captures so users can automate repetitive browser tasks safely and reproducibly.

Core Features & Use Cases

  • Navigation & Interaction: Navigate pages, click, type, select, upload, and interact with elements using stable refs or semantic locators.
  • Page Analysis & Data Extraction: Snapshot the accessibility/DOM tree, extract text, attributes, and counts, and re-snapshot after navigation or dynamic changes.
  • Stateful Automation & Outputs: Save and load authentication state, manage cookies and storage, evaluate JavaScript, capture screenshots or PDFs, and export extracted data for downstream processing.
  • Use Case: Log into a web app, perform a multi-step form submission, capture the resulting page as a PDF, and extract key fields into a CSV for reporting.

Quick Start

Open the target website, snapshot interactive elements, and extract product titles and links into a CSV file.

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 scraping and extract data from dynamic web pages?▼

You can automate web scraping by navigating to target pages, snapshotting the accessibility or DOM tree, and extracting specific text, attributes, and element counts into structured formats for downstream processing.

Can I automate browser form filling and multi-step logins into web apps?▼

Yes, browser automation supports interacting with web pages by clicking, typing, selecting, and uploading files using stable element refs, allowing you to complete multi-step form submissions and authenticate into web apps.

How do I capture screenshots or save web pages as PDFs for reporting?▼

You can capture page state by taking screenshots or saving pages as PDF outputs during browser automation, providing visual captures of the resulting web page after performing automated interactions like form submissions.

Does headless browser automation maintain authentication state and cookies across sessions?▼

Yes, it provides stateful automation by saving and loading authentication state, managing cookies and storage, so you can maintain persistent web app sessions across multiple automated browser interactions.

What is the best way to test UIs and handle dynamic content during web scraping?▼

The best way to test UIs with dynamic content is to snapshot interactive elements, perform actions like clicks, and re-snapshot the accessibility tree after navigation to capture the updated page state accurately.

Can I evaluate custom JavaScript on a web page during browser automation?▼

Yes, you can evaluate custom JavaScript directly within the browser automation context to manipulate page elements, extract data, or trigger dynamic interactions before capturing screenshots or exporting data.

Related Skills

Explore More Software Engineering Skills→
AmitabhainArunachalaAmitabhainArunachala
1

Agent Browser

Automate web browser interactions for AI agents via CLI.

Community
Advanced
K-Dense-AIK-Dense-AI
33.0k

flowio

Parse FCS files and extract event data as NumPy arrays.

Official
Intermediate
marktantongcomarktantongco

firecrawl-scrape

Extract HTML content from URLs and convert it to markdown.

Community
Advanced
Xza85hrfXza85hrf

browser-control

Automate browser navigation, clicks, and data extraction via PinchTab commands.

Community
Intermediate