page-agent

Embed an in-page GUI agent into web applications for natural language UI interaction.

Updated May 8, 2026
One-click install
npx skills add https://github.com/superfhp/lumi-agent --skill page-agent-superfhp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: page-agent
Source: https://github.com/superfhp/lumi-agent/tree/main/optional-skills/web-development/page-agent
Command: npx skills add https://github.com/superfhp/lumi-agent --skill page-agent-superfhp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill embeds an AI copilot into your web application, allowing users to interact with the UI using natural language.

Core Features & Use Cases

  • In-page GUI Agent: Enables users to control the UI with natural language commands.
  • Web Developer Tool: Suitable for adding AI copilots to SaaS, admin panels, and B2B tools.
  • Legacy Web App Modernization: Allows modernizing legacy web apps without rewriting the frontend.
  • Accessibility: Provides natural language access for voice and screen-reader users.
  • Skill Evaluation: Useful for evaluating page-agent against various LLMs.

Quick Start

Use the page-agent skill to click the login button and fill the username as John.

Frequently Asked Questions about page-agent

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

FAQPage Schema
How do I add an AI copilot to a web app for natural language interaction?

To add an AI copilot to a web app, you embed an in-page GUI agent using a single script tag. This enables natural language interaction with your UI without needing a headless browser or Python backend.

Can I modernize a legacy web app with natural language commands without rewriting the frontend?

You can modernize a legacy web app with natural language commands by embedding an in-page GUI agent via a script tag. This approach allows users to control the existing UI without rewriting the frontend.

Do I need Python or a headless browser to embed an AI agent in a web application?

You do not need Python or a headless browser to embed an AI agent in a web application. This solution operates entirely within the browser using JavaScript and an OpenAI-compatible LLM endpoint.

What is the best way to provide natural language access for screen-reader users in a SaaS tool?

The best way to provide natural language access for screen-reader users in a SaaS tool is integrating an in-page GUI agent. It enables voice and screen-reader users to interact with web UIs using natural language commands.

How does an in-page GUI agent execute natural language commands on a web UI?

An in-page GUI agent executes natural language commands on a web UI by interpreting user text inputs and translating them into UI interactions like clicking buttons and filling forms directly in the browser.

Does the page-agent skill work with any LLM endpoint for evaluating web app interactions?

The page-agent skill works with any OpenAI-compatible LLM endpoint for evaluating web app interactions. You simply need JavaScript to integrate the script tag and configure your endpoint.