skills.rest
vivekgoquest
vivekgoquestCOMMUNITY
Explore all skills by this author →
GitHub

page-agent

Embed a natural-language GUI copilot into web applications using DOM-based automation.

Updated Aug 22, 2026
Search Tags:#javascript#embed#page-agent#web copilot#dom automation#gui agent#natural language ui
One-click install
npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill page-agent-vivekgoquest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: page-agent
Source: https://github.com/vivekgoquest/hermes-agent-stable/tree/main/optional-skills/web-development/page-agent
Command: npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill page-agent-vivekgoquest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires page-agent.

What problem does it solve? Web app users often must click through many screens to complete routine tasks, and teams lack a way to let users drive the UI with plain language. This Skill guides you through embedding alibaba/page-agent, an in-page GUI agent that reads the DOM as text and executes natural-language instructions against the current page. ## Core Features & Use Cases - In-page AI copilot: Add a floating panel to SaaS dashboards, admin panels, ERP, or CRM tools so users type instructions like "create invoice for Acme Corp" instead of navigating menus. - Three integration paths: 30-second CDN demo for evaluation, npm install wired to your own OpenAI-compatible LLM endpoint for production, or cloning the source repo to hack on the agent or browser extension. - Flexible LLM backends: Works with Qwen/DashScope, OpenAI, Ollama, OpenRouter, or any endpoint speaking /v1/chat/completions. - Use Case: A B2B SaaS team adds the page-agent panel to their dashboard, proxies LLM calls through their backend, and lets customers complete multi-step workflows by describing them in plain English. ## Quick Start Add the page-agent demo script tag to any HTML page and type a natural-language instruction into 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?▼

Install the page-agent npm package, create a PageAgent instance with your model, baseURL, and apiKey, then call agent.panel.show() to display the UI. Users can then type natural-language instructions that execute against the page DOM.

What LLM providers work with page-agent?▼

page-agent works with any OpenAI-compatible endpoint, including Qwen via DashScope, OpenAI, local Ollama models, and OpenRouter. Providers requiring native Anthropic or Gemini formatting need an OpenAI-compatibility proxy like LiteLLM in front.

Can I use the page-agent demo CDN in production?▼

No, the demo CDN uses alibaba's free testing LLM proxy, which is rate-limited and restricted to evaluation by their terms. For production, install via npm and proxy LLM calls through your own backend to protect your API key.

Does page-agent work without screenshots or vision models?▼

Yes, page-agent reads the DOM as text rather than using screenshots or multimodal models. If you need visual grounding or screenshot-based automation, use a multimodal browser agent instead.

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 browser console for CORS errors on the LLM endpoint or incorrect baseURL values.

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. page-agent is designed for the opposite direction: giving end users of your own web app a natural-language interface inside the page.

Related Skills

Explore More Software Engineering Skills→
xu1713xu1713

page-agent

Embed an in-page GUI agent into web applications via script tag or npm package.

Community
Intermediate
episvrepisvr

page-agent

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

Community
Intermediate
jacardljacardl

openclaw-migration

Migrate OpenClaw memories, skills, and workspace assets into Hermes Agent.

Community
Advanced
yigitkonuryigitkonur
11

run-agent-browser

Drives browser automation via agent-browser CLI for navigation, DOM interaction, sessions, tabs, screenshots, and data extraction.

Community
Intermediate