skills.rest
Runchuan-BU
Runchuan-BUCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate web browsing to navigate pages, click elements, fill forms, and extract data.

401|53|Updated Feb 26, 2026
Search Tags:#session-management#web-testing#screenshot#web-scraping#browser-automation#form-filling
One-click install
npx skills add https://github.com/Runchuan-BU/BioClaw --skill agent-browser-runchuan-bu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Runchuan-BU/BioClaw/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/Runchuan-BU/BioClaw --skill agent-browser-runchuan-bu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Many workflows require repetitive manual browsing tasks such as logging into web apps, filling forms, clicking through interfaces, capturing screenshots, and extracting data from dynamic pages; agent-browser automates these interactions to save time and reduce human error.

Core Features & Use Cases

  • Interactive Navigation & Control: Open pages, navigate history, reload, and close sessions programmatically.
  • Element Interaction & Data Extraction: Snapshot DOM to get element references, click, fill, type, select, upload, and extract text, attributes, and HTML from controls on dynamic sites.
  • Session & State Management: Save/load authentication state, manage cookies and storage, evaluate JavaScript, and capture screenshots or PDFs for reporting or testing.
  • Use Case: Log into a web dashboard, navigate to a report, extract the table of results into CSV, and save a screenshot for documentation.

Quick Start

Open the target page, snapshot interactive elements, click the login button, fill credentials, navigate to the desired report page, and extract the table into CSV.

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 interaction and data extraction from dynamic pages?▼

To automate web interaction and data extraction, you can programmatically navigate pages, click elements, fill forms, and extract structured data from dynamic sites using semantic locators and JavaScript evaluation. This handles tasks like automated form submission and scraping dynamic pages.

Can I save and load authentication state like cookies for browser automation sessions?▼

Yes, browser automation supports session and state management by allowing you to save and load authentication state, manage cookies and storage, and maintain persistent logins across multiple automated browsing sessions.

What is the best way to capture visual reports during web application testing?▼

The best way to capture visual reports during web application testing is to use browser automation to take screenshots or export PDFs of your web pages after performing interactive navigation and element interactions.

How do I extract structured data from web pages into CSV after logging in?▼

You can extract structured data into CSV by opening a target page, snapshotting interactive elements to get element references, filling login credentials, navigating to the desired report page, and extracting the table text or HTML.

Does browser automation work with form filling and file uploads on dynamic sites?▼

Yes, browser automation works with dynamic sites by supporting element interactions such as clicking, typing, selecting, filling forms, and uploading files, while using DOM snapshots to accurately locate interactive controls.

Related Skills

Explore More Software Engineering Skills→
ericdahl-devericdahl-dev

setup-browser-cookies

Import cookies from real Chromium browsers into headless sessions for QA testing.

Official
Intermediate
ano4lano4l

data-export

Generate Swift data export/import infrastructure for JSON, CSV, and PDF formats.

Community
Advanced
SakshamKandelSakshamKandel

setup-browser-cookies

Import Chromium cookies into headless Playwright sessions for authenticated QA testing.

Community
Advanced
zhayujiezhayujie
46.4k

web-fetch

Fetch web page HTML and extract title and readable text.

Community
Basic