skills.rest
d3ming
d3mingCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate Chrome browser interactions via CDP for testing and data extraction.

Updated Jan 5, 2026
Search Tags:#screenshots#cdp#session-management#e2e-testing#web-scraping#browser-automation#form-filling
One-click install
npx skills add https://github.com/d3ming/dot-agents --skill agent-browser-d3ming
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/d3ming/dot-agents/tree/main/master/skills/agent-browser
Command: npx skills add https://github.com/d3ming/dot-agents --skill agent-browser-d3ming

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates manual, fragile browser interactions by providing a CLI-driven way to navigate pages, fill forms, click elements, take screenshots, extract data, and run repeatable end-to-end browser tasks.

Core Features & Use Cases

  • Browser control via Chrome/Chromium DevTools Protocol for reliable automation and testing.
  • Snapshot-based compact element refs for low-token interactions and deterministic element targeting.
  • Session and profile persistence, auth import, and an encrypted auth vault for automating authenticated workflows.
  • Network tooling including request routing, HAR recording, proxy support, and download handling for scraping and CI evidence collection.
  • Visual and behavioral testing: annotated screenshots, pixel diffs, video recording, and performance profiling for regression checks.
  • Use cases include automated form submission, authenticated scraping, E2E testing, visual regression, CI test evidence, and performance profiling.

Quick Start

Open the login page, take an interactive snapshot to discover refs, fill the username and password fields, submit the form, wait for navigation, and capture a screenshot to verify the authenticated state.

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 fill forms and capture screenshots?▼

Browser automation via Chrome DevTools Protocol allows you to programmatically navigate pages, fill forms, click elements, and capture screenshots for repeatable end-to-end web tasks.

Can I use Chrome DevTools Protocol for authenticated web scraping and session persistence?▼

Yes, CDP-based control supports session and profile persistence along with an encrypted auth vault, enabling reliable authenticated scraping and automated workflows without manual logins.

What is the best way to run E2E testing and visual regression checks in a headless browser?▼

Headless browser automation supports E2E testing and visual regression by capturing annotated screenshots, performing pixel diffs, and recording video for CI evidence collection.

Does browser automation support network routing and proxy configuration for web scraping?▼

Yes, browser automation includes network tooling for request routing, HAR recording, and proxy configuration, providing precise control over traffic during web scraping and testing.

How do I extract structured data from web pages using snapshot-based element refs?▼

Snapshot-based compact element refs enable deterministic element targeting and low-token interactions, allowing you to reliably extract structured or textual data from web pages.

What are the limitations of using CDP-based control for performance profiling?▼

While CDP-based control enables performance profiling and network recording, it requires a Chrome or Chromium-compatible environment, meaning non-Chromium browsers are not supported.

Related Skills

Explore More Software Engineering Skills→
louisburroughslouisburroughs

chrome-devtools

Automate browser interactions and debugging via the Chrome DevTools MCP server.

Community
Advanced
ben-mad-jlpben-mad-jlp

kodex-fix-incorrect

Validate Kodex topic claims against code and update inaccuracies.

Community
Intermediate
LeoyishouLeoyishou
27

browse-use

Automate browser tasks with persistent sessions and auth handling.

Community
Advanced
Mathews-TomMathews-Tom
310

lightpanda-browser

Automate DOM interactions and data extraction via Lightpanda CDP.

Community
Intermediate