Edge Developer Platform
  • Pages
    • Product Introduction
    • Quick Start
      • Importing a Git Repository
      • Starting From a Template
      • Direct Upload
      • Start with AI
    • Framework Guide
      • Frontends
        • Vite
        • React
        • Vue
        • Hugo
        • Other Frameworks
      • Backends
      • Full-stack
        • Next.js
        • Nuxt
        • Astro
        • React Router
        • SvelteKit
        • TanStack Start
        • Vike
      • Custom 404 Page
    • Project Guide
      • Project Management
      • edgeone.json
      • Configuring Cache
      • Building Output Configuration
      • Error Codes
    • Build Guide
    • Deployment Guide
      • Overview
      • Create Deploys
      • Manage Deploys
      • Deploy Button
      • Using Github Actions
      • Using Gitlab CI/CD
      • Using CNB Plugin
      • Using IDE PlugIn
      • Using CodeBuddy IDE
    • Domain Management
      • Overview
      • Custom Domain
      • HTTPS Configuration
        • Overview
        • Apply for Free Certificate
        • Using Managed SSL Certificate
      • Configure DNS CNAME Record
    • Observability
      • Overview
      • Metric Analysis
      • Log Analysis
    • Pages Functions
      • Overview
      • Edge Functions
      • Cloud Functions
        • Overview
        • Node.js
        • Python
        • Go
    • Middleware
    • KV Storage
    • Edge AI
    • API Token
    • EdgeOne CLI
    • Copilot
      • Overview
      • Quick Start
    • Pages MCP
    • Pages Skills
    • Message Notification
    • Integration Guide
      • AI
        • Dialogue Large Models Integration
        • Large Models for Images Integration
      • Database
        • Supabase Integration
        • Pages KV Integration
      • Ecommerce
        • Shopify Integration
        • WooCommerce Integration
      • Payment
        • Stripe Integration
        • Integrating Paddle
      • CMS
        • WordPress Integration
        • Contentful Integration
        • Sanity Integration
        • Payload Integration
      • Authentication
        • Supabase Integration
        • Clerk Integration
    • Best Practices
      • AI Dialogue Deployment: Deploy Project with One Sentence Using Skill
      • Using General Large Model to Quickly Build AI Application
      • Use the DeepSeek model to quickly build a conversational AI site
      • Building an Ecommerce Platform with Shopify
      • Building a SaaS Site Using Supabase and Stripe
      • Building a Company Brand Site Quickly
      • How to Quickly Build a Blog Site
    • Migration Guides
      • Migrating from Vercel to EdgeOne Pages
      • Migrating from Cloudflare Pages to EdgeOne Pages
      • Migrating from Netlify to EdgeOne Pages
    • Troubleshooting
    • FAQs
    • Contact Us
    • Release Notes
Docs Overview/
Edge Developer Platform/
Pages/
Pages Skills/

Pages Skills

What is Skills

Skills is an open specification proposed by Anthropic for injecting domain-specific professional expertise and operation processes into AI Agents. Skills exist in the form of structured Markdown files, containing complete task flows, judgment logic, and exception handling mechanisms. Once loaded with Skills, an AI Agent can autonomously complete professional tasks by predefined processes.
Currently, ALL AI programming tools that support the Skills Mechanism can use Skills, including but not limited to Claude Code, CodeBuddy, and Cursor.


EdgeOne Pages Dev Skill

Dev Skill is designed for full stack development scenarios, enabling AI Agents to guide feature development on Pages. This Skill covers development capabilities such as Edge Functions/Cloud Functions (Node.js/Go/Python), middleware, and KV storage. You can describe development requirements in natural language (for example, "help me write an API"), and the AI Agent will automatically choose appropriate runtime environments and function types based on built-in technology decision trees, then generate code by platform specifications.


EdgeOne Pages Deploy Skill

Deploy Skill is designed for deployment scenarios, enabling AI Agents to guide automatic deployment of Web applications to Pages. You can directly tell the AI "Deploy to EdgeOne Pages", and the AI Agent will automatically perform environment check, CLI installation, login authentication, project build, and complete process of deployment upload, then return a direct access online URL.


Installation Method

It is recommended to install directly through natural language. Tell the Agent in AI conversation: "Help me install this skill: https://github.com/edgeone-pages/edgeone-pages-skills". The AI Agent will automatically pull the repository and complete installation.
In addition, it also supports command line installation (npx skills add edgeone-pages/edgeone-pages-skills) and manual installation (download the Skill file and place it in the corresponding directory of the tool). For detailed installation steps and setting methods of each tool, refer to AI Conversational Deployment: Deploy Project in One Sentence with Skill document.


Usage Methods

After installation, use natural language in AI conversation to trigger the corresponding process.

Development

For example: "Help me write a user registration API", "Add a request authentication middleware". The AI Agent will automatically execute the following steps:
1. Requirement analysis: Based on your description, automatically determine the function type to use (Edge Functions / Cloud Functions) and the runtime environment of Cloud Functions (Node.js / Python / Go), or use middleware to process.
2. Code generation: Generate function code in the correct directory as per the platform specification, including route, request processing, and response format.
3. Local debugging: Guide you to use edgeone pages dev to start up the local development service (default port 8088), see changes in real-time and debug.

Deployment

For example: "Help me deploy this project to EdgeOne Pages". The AI Agent will automatically execute the steps below:
1. Environment check: Detect whether EdgeOne CLI is installed and the version is correct. If not installed, perform automatic installation.
2. Login authentication: Detect login status. If not logged in, guide you to select a site (China/Global) and complete authentication.
3. Project building: Automatically identify the project framework and execute the build command.
4. Deployment upload: Deploy build artifacts to EdgeOne Pages.
5. Returned results: Output the direct access online URL and Console Management address.
During the entire process, the AI Agent may ask for confirmation when necessary (such as selecting China site/international site, providing API Token). Just respond by prompt.


Supported Project Type

Pages Skills support all project types supported by EdgeOne Pages, including:
Static and Dynamic Website Hosting: Supports the use of static generators such as Astro and Hexo to build websites, as well as single-page applications developed with modern frontend frameworks like React and Vue.
High Performance Full-Stack Project Development: Supports SSR and ISR features of frameworks such as Next.js and Nuxt, integrates edge and cloud-based double computational capacity, and facilitates the construction of complex projects with integration of front-end and back-end.
The CLI will automatically identify the project framework and select the correct build and deployment strategy without manual configuration.


Login Method

Skills support two login methods. The AI Agent will automatically select based on your runtime environment.
Environment
Login Method
Description
local desktop environment
browser login
Open browser to complete login automatically
remote server
API Token Login
Guide you to create a Token through the console and enter
API Token get address:
China site console
International site console
Note:
API Token has account level permission, keep it safe and never submit it to the code repository.