skills.rest
metric-space-ai
metric-space-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

interactive-browser

Operate a real browser via Playwright to inspect live DOM state and capture screenshots.

2|Updated Apr 12, 2026
Search Tags:#automation#evidence#playwright#ui-testing#browser#js_repl
One-click install
npx skills add https://github.com/metric-space-ai/ctox --skill interactive-browser
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: interactive-browser
Source: https://github.com/metric-space-ai/ctox/tree/main/skills/system/communication/interactive-browser
Command: npx skills add https://github.com/metric-space-ai/ctox --skill interactive-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Use a real browser through js_repl-backed Playwright when CTOX needs live DOM state, client-side JavaScript execution, auth/session behavior, screenshots, or true UI interaction instead of search, source reading, or durable scraping.

Core Features & Use Cases

  • click, type, scroll, or navigate through a real page
  • inspect client-rendered DOM state after JavaScript runs
  • validate auth or session-bound flows
  • capture screenshots as compact evidence
  • debug local web apps or browser-backed portals
  • derive a reviewed browser observation before deciding whether work should stay one-off or become a durable scraper

Quick Start

Launch a js_repl-backed Playwright session and load the target page to observe DOM state.

Frequently Asked Questions about interactive-browser

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

FAQPage Schema
How do I validate UI behavior and client-side state through live browser interaction?▼

You can validate client-side state by launching a js_repl-backed Playwright session to interact with live pages, inspect the rendered DOM, and capture screenshots as evidence.

What is the best way to capture screenshots as evidence for authenticated web app flows?▼

Capturing evidence for auth flows requires a persistent browser context via Playwright to navigate session-bound pages, execute client-side JavaScript, and screenshot the resulting UI.

Do I need Chromium and Playwright installed to inspect client-rendered DOM state?▼

Yes, inspecting client-rendered DOM state requires a js_repl-enabled Codex session, an existing Playwright-enabled reference workspace, and Chromium installed to initialize a persistent browser context.

Can I execute client-side JavaScript on live webpages to debug local portals?▼

Yes, you can execute client-side JavaScript to debug local web apps or portals using a js_repl-backed Playwright session to observe live DOM state and client-side behavior.

When should I use a real browser for UI testing instead of source reading or scraping?▼

Use a real browser instead of source reading or scraping when surface-level discovery cannot verify UI behavior, auth flows, or client-side state, and durable evidence is required.

How do I decide whether a browser observation should become a durable scraper?▼

Derive a reviewed browser observation by validating UI behavior through Playwright first, then decide whether the task should remain a one-off interaction or become a durable scraper.

Related Skills

Explore More Software Engineering Skills→
jackspacejackspace
16

Browser Daemon

Maintain a persistent Playwright-driven Chrome session via file-based IPC commands.

Community
Advanced
edulazaroedulazaro
12

lc:generate-scraper

Generate Larascraper-compatible scraper classes and crawler logic for Laravel applications.

Community
Advanced
jankneumannjankneumann

browser-testing-with-devtools

Capture browser runtime evidence including screenshots, DOM state, console logs, network requests, accessibility trees, and performance traces.

Community
Intermediate
xalgordxalgord
846

dom-xss

Detect and analyze DOM-based XSS vulnerabilities in client-side applications.

Community
Advanced