skills.rest
gakonst
gakonstCOMMUNITY
Explore all skills by this author →
Website𝕏@gakonstGitHub

web-browser

Automate web searches and extract cited facts via CDP browser automation.

Updated Aug 27, 2026
Search Tags:#testing#chrome devtools#puppeteer#web automation#browser control#scraping#ui interaction
One-click install
npx skills add https://github.com/gakonst/dotfiles --skill web-browser-gakonst
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-browser
Source: https://github.com/gakonst/dotfiles/tree/main/.codex/skills/web-browser
Command: npx skills add https://github.com/gakonst/dotfiles --skill web-browser-gakonst

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core, and includes scripts (resource) components.

What problem does it solve?

This Skill empowers AI agents to interact with web pages programmatically, overcoming the limitations of text-only browsing. It solves the challenge of automating complex UI interactions, data extraction, and navigation, allowing agents to perform tasks that typically require a human browser user.

Core Features & Use Cases

  • Remote Browser Control: Starts and controls Google Chrome or Chromium browsers (headless or headful) using the Chrome DevTools Protocol (CDP).
  • Web Navigation & Interaction: Navigate to URLs, open new tabs, evaluate JavaScript, click elements, fill forms, and take screenshots.
  • Interactive Element Picking: Provides a tool to visually select elements on a page, returning their attributes for precise interaction.
  • Use Case: An agent needs to log into a website, navigate to a specific report, download it, and then extract data. This Skill allows the agent to automate the entire sequence, from login to data retrieval.

Quick Start

To start a headless Chrome browser for web automation, run './tools/start.js'. Once started, navigate to a URL using './tools/nav.js https://example.com'.

Frequently Asked Questions about web-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web browsing and interact with webpages programmatically?▼

Web automation uses Chrome DevTools Protocol (CDP) to control browsers remotely, enabling you to navigate URLs, click elements, fill forms, and extract data without manual interaction. This Skill starts headless Chrome and provides tools to navigate, interact, and screenshot pages.

Can I use web automation for scraping and data extraction tasks?▼

Yes, web scraping with browser automation handles dynamic content and interactive elements that static parsers cannot. This Skill uses puppeteer-core to navigate pages, evaluate JavaScript, pick elements visually, and extract 3–5 load-bearing facts with citations.

What's the best way to verify time-sensitive information like prices, releases, or regulatory updates?▼

Automated browser navigation lets agents perform targeted searches, traverse results, and extract facts with explicit dates and sources. This Skill automates the full cycle—search queries, navigation, data extraction, and citation attachment—for verification requiring current information.

How do I log into websites and automate multi-step workflows like form filling and downloads?▼

Browser automation sequences complex UI interactions end-to-end: navigate to login, fill credentials, click buttons, access reports, and retrieve data. This Skill controls Chrome headlessly via CDP to perform login flows and extract results without human intervention.

Does web automation work with Chrome DevTools Protocol and headless browsers?▼

Yes, this Skill uses puppeteer-core and CDP to start and control Google Chrome or Chromium in headless or headful mode. CDP provides precise element interaction, JavaScript evaluation, screenshot capture, and full page navigation capabilities.

What are the limitations when automating browser interactions and scraping?▼

Browser automation depends on CDP availability, requires Chrome or Chromium installation, and assumes extractable page structure. Performance scales with page complexity; niche or time-sensitive information may need diverse search terms and citation verification logic.

Related Skills

Explore More Software Engineering Skills→
eykdeykd

web-browser

Control Chrome/Chromium via Chrome DevTools Protocol for navigation, screenshots, JavaScript, and element inspection.

Community
Advanced
LaZy-WolfLaZy-Wolf
1

deep-reasoning-agent

Verify research drafts through citation validation, fact-checking, and content quality assessment.

Community
Advanced
tkerseytkersey
66

web-browser

Automate Chrome/Chromium via CDP to navigate, click, fill forms, evaluate JavaScript, and capture screenshots.

Community
Intermediate
knoopxknoopx
68

scraping

Fetch web pages, parse HTML with CSS selectors, and query REST APIs.

Community
Intermediate