page-agent

Embed a JavaScript in-page GUI agent for natural language UI navigation.

1|Updated Feb 17, 2026
One-click install
npx skills add https://github.com/brittaniebuffiecsu/zerogravityclaw --skill page-agent-brittaniebuffiecsu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: page-agent
Source: https://github.com/brittaniebuffiecsu/zerogravityclaw/tree/main/src/hermes-core/optional-skills/web-development/page-agent
Command: npx skills add https://github.com/brittaniebuffiecsu/zerogravityclaw --skill page-agent-brittaniebuffiecsu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, npm, page-agent, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows web developers to embed an AI copilot into their applications, enabling users to interact with the UI using natural language.

Core Features & Use Cases

  • In-page GUI Agent: Embeds alibaba/page-agent, a pure-JavaScript in-page GUI agent.
  • Natural Language Interaction: Users can drive the UI with natural language commands.
  • Use Case: Ideal for SaaS tools, admin panels, or B2B applications where users can perform tasks like "click login, fill username as John" without complex navigation.

Quick Start

Use the page-agent skill to add a natural language interface to your web application.

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 my web app for natural language interaction?

To add an AI copilot to your web app, you can embed a JavaScript-based in-page GUI agent that enables users to drive UI navigation using natural language commands. This integrates with existing web app structures to enhance user experience.

Can I use an in-page agent to automate UI navigation in a B2B application?

Yes, an in-page agent is ideal for B2B applications and SaaS tools, allowing users to perform tasks like filling usernames or clicking login buttons through natural language commands without complex manual navigation.

Do I need Node.js and npm to embed a natural language interface in my web application?

Yes, embedding this natural language interface requires Node.js and npm to install and manage the page-agent dependency, along with an OpenAI-compatible LLM endpoint to process the UI navigation commands.

What LLM endpoints work with an in-page GUI agent for web apps?

The in-page GUI agent supports various OpenAI-compatible LLM endpoints, allowing your web application to connect to existing language model services to process and execute natural language UI interactions.