skills.rest
m4an5you6
m4an5you6COMMUNITY
Explore all skills by this author →
GitHub

page-agent

Embed alibaba/page-agent into web applications for natural-language UI control.

Updated May 29, 2026
Search Tags:#javascript#web#copilot#embed#page-agent#dom automation#gui agent
One-click install
npx skills add https://github.com/m4an5you6/aspera-agent --skill page-agent-m4an5you6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: page-agent
Source: https://github.com/m4an5you6/aspera-agent/tree/main/optional-skills/web-development/page-agent
Command: npx skills add https://github.com/m4an5you6/aspera-agent --skill page-agent-m4an5you6

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires page-agent.

What problem does it solve? Web developers want to add an AI copilot to their own SaaS, admin panel, or legacy web app so end-users can drive the interface with natural language instead of clicking through screens, without building a headless-browser automation stack. ## Core Features & Use Cases - In-page GUI agent: alibaba/page-agent runs inside the webpage, reads the DOM as text, and executes instructions like "click login, fill username as John" against the live page. - Three integration paths: a 30-second CDN demo script, an npm package wired to any OpenAI-compatible LLM endpoint (Qwen, OpenAI, Ollama, OpenRouter), or a full source-repo clone for hacking and extension development. - Use Case: A B2B dashboard team embeds page-agent so customers can type "create invoice for Acme Corp and email it" instead of navigating five screens, proxying LLM calls through their own backend to keep API keys safe. ## Quick Start Add the page-agent CDN script tag to an HTML page and type a natural-language instruction in the panel that appears.

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 with page-agent?▼

Install the page-agent npm package, instantiate PageAgent with your model, baseURL, and apiKey, then call agent.panel.show() for end users or agent.execute() programmatically. Any OpenAI-compatible LLM endpoint works.

How to test page-agent without installing anything?▼

Add the CDN script tag for page-agent.demo.js from jsDelivr to any HTML page, or use the bookmarklet form in your bookmarks bar. A panel appears where you can type instructions, using alibaba's free evaluation LLM proxy.

Does page-agent work with local LLMs like Ollama?▼

Yes, page-agent supports Ollama by setting baseURL to http://localhost:11434/v1 and a local model such as qwen3:14b. It also works with Qwen DashScope, OpenAI, and OpenRouter since all expose OpenAI-compatible endpoints.

Is it safe to put my LLM API key in page-agent client-side code?▼

No, any apiKey passed to PageAgent ships in your JavaScript bundle and is exposed. For production, proxy LLM calls through your own backend and point baseURL at that proxy instead of embedding keys.

When should I use Playwright instead of page-agent?▼

Use Playwright or browser-use for cross-tab automation without embedding code into the target site, or when you need visual grounding from screenshots. page-agent is text-DOM only and must be embedded in the page it controls.

Why does page-agent fail to load on some websites?▼

Sites with strict Content-Security-Policy may block the CDN script or inline eval. Self-host the bundle from your own origin, and check the console for CORS errors on the LLM endpoint or an incorrect baseURL.

Related Skills

Explore More Software Engineering Skills→
agtktIDagtktID
1

page-agent

Embed an in-page natural-language GUI copilot into web applications using alibaba/page-agent.

Community
Intermediate
episvrepisvr

page-agent

Embed alibaba/page-agent into web applications for natural-language DOM-driven UI control.

Community
Intermediate
dimsourdimsour
2

dotnet:intent-detection

Detect user intent and route requests to /dotnet:* commands.

Community
Advanced
ComposioHQComposioHQ
74.2k

webapp-testing

Automate browser interactions and verify frontend functionality using Playwright scripts.

Official
Intermediate