page-agent

Drive in-page UI interactions with natural-language commands in a browser.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/nadicodeai/argo-agent --skill page-agent-nadicodeai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: page-agent
Source: https://github.com/nadicodeai/argo-agent/tree/main/optional-skills/web-development/page-agent
Command: npx skills add https://github.com/nadicodeai/argo-agent --skill page-agent-nadicodeai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Embed alibaba/page-agent into your own web application — a pure-Javascript in-page GUI agent that ships as a single <script> tag or npm package and lets end-users of your site drive the UI with natural language ("click login, fill username as John"). No Python, no headless browser, no extension required. Use this skill when the user is a web developer who wants to add an AI copilot to their SaaS / admin panel / B2B tool, make a legacy web app accessible via natural language, or evaluate page-agent against a local (Ollama) or cloud (Qwen / OpenAI / OpenRouter) LLM. NOT for server-side browser automation — point those users to Argo' built-in browser tool instead.

Core Features & Use Cases

  • In-page GUI agent runs inside your website and handles UI interactions using natural language commands.
  • Pure client-side — host includes a script and passes an OpenAI-compatible LLM endpoint.
  • Use cases include adding an AI copilot to SaaS dashboards, admin panels, or legacy apps, or evaluating page-agent against local or cloud LLMs.

Quick Start

Show the page-agent panel in your web app and drive the UI with natural language.

Frequently Asked Questions about page-agent

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

FAQPage Schema
How do I embed an AI copilot inside my web app to automate UI interactions?

To embed an AI copilot for in-page UI automation, include a client-side script and pass an OpenAI-compatible LLM endpoint. The agent runs entirely in the browser, letting users execute actions like clicking buttons or filling forms via natural language commands.

Can I add a natural language interface to a legacy web app without server-side automation?

Yes, you can add a natural language interface to legacy web apps without server-side automation. The in-page GUI agent runs purely client-side in the browser, requiring no Python, headless browser, or browser extension to drive UI interactions.

Does the in-page GUI agent work with local LLMs like Ollama or cloud providers like OpenAI?

The in-page GUI agent works with both local and cloud LLMs. It requires an OpenAI-compatible LLM endpoint, allowing you to evaluate and connect it to local models via Ollama or cloud providers like Qwen, OpenAI, and OpenRouter.

What is the best way to drive a live webpage with natural language commands in a SaaS dashboard?

The best way to drive a live webpage with natural language in a SaaS dashboard is using a pure client-side JavaScript agent. It ships as a single script tag or npm package, automating in-page UI interactions directly within the user's browser environment.

When should I not use a client-side web agent for browser automation?

You should not use a client-side web agent for server-side browser automation tasks. If your use case requires headless browser execution or backend scripting rather than embedding a copilot inside a live site, use server-side browser automation tools instead.