cluso-inspector

Capture UI elements visually and extract HTML, CSS selector, bounds, and state classes.

3|1|Updated Jan 11, 2026
One-click install
npx skills add https://github.com/jasonkneen/cluso-inspector-skill --skill cluso-inspector
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cluso-inspector
Source: https://github.com/jasonkneen/cluso-inspector-skill/tree/main
Command: npx skills add https://github.com/jasonkneen/cluso-inspector-skill --skill cluso-inspector

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

When a user’s description of a UI element is unclear, it becomes hard to diagnose the right target and produce correct selectors, HTML, or layout/context.

Core Features & Use Cases

  • Visual element selection to capture the precise on-screen element the user means.
  • HTML and CSS selector extraction to provide the exact structure and selector path for downstream reasoning or fixes.
  • Screenshot + bounds + state classes for visual debugging, including where the element sits and what interactive states it shows.
  • Use case: Troubleshooting a broken button by selecting it visually, then using the returned HTML/selector and bounds to understand why it fails or where it’s positioned incorrectly.

Quick Start

Ask your AI to run the inspector against the page URL, then click the element you want to show so it returns screenshot, HTML, selector, bounds, and state classes.

Frequently Asked Questions about cluso-inspector

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

FAQPage Schema
How do I visually identify a UI element on a web page when its text description is unclear?

You can visually identify a UI element by launching an interactive Electron-based inspector against the page URL, then clicking the exact element on the screen to capture it visually for interactive UI clarification.

Can I extract the HTML and CSS selector of a specific element by clicking on it directly?

Yes, you can extract HTML and CSS selectors by clicking the target element within the visual inspector, which returns the exact structure and selector path needed for downstream reasoning or fixes.

What is the best way to capture an element's screenshot, bounds, and state classes for visual debugging?

To capture an element's screenshot, bounds, and state classes for visual debugging, run the inspector against the page URL and select the target element to return its visual context and interactive states.

Does this visual web inspection tool require any dependencies to run?

No dependencies are required; the visual web inspection tool launches via npx with a page URL, operating as a standalone Electron application to extract element data without additional library installations.

Why does text-based UI element selection fail when troubleshooting broken web page components?

Text-based UI element selection fails because vague descriptions make it hard to diagnose the correct target, whereas visual element selection captures the precise on-screen component to return accurate selectors and bounds.

When should I not use a visual debugging approach for extracting web page elements?

You should not use visual debugging for extracting web page elements when you already have the exact CSS selector or HTML structure, as the interactive Electron inspector is designed for cases where text-based descriptions fail.