Start with AI
The AI tools built into EdgeOne Makers, such as the Deploy MCP and AI IDE plugins, together with flexible AI context files, collectively create an intelligent development ecosystem. This ecosystem helps you deliver outstanding Web applications with greater speed and higher quality.
Using Makers MCP
MCP (Model Context Protocol) is an open protocol that enables AI models to securely interact with local and remote resources.
EdgeOne Makers Deploy MCP is a dedicated service that can quickly deploy web applications to EdgeOne Makers and generate publicly accessible links. This enables you to immediately preview and share AI-generated web content. For more details, see MCP.
Using Makers Skills
Skills is an open standard proposed by Anthropic for injecting domain-specific professional knowledge into AI Agents. Unlike MCP which runs as an independent service, Skills are directly loaded into the AI Agent's context in the form of a Markdown file.
EdgeOne Makers Deploy Skill can guide AI Agents to automatically complete the entire process of environment checks, builds, and deployments for a project. After installation, you only need to say "deploy to EdgeOne Makers" in an AI conversation to obtain a publicly accessible online URL. This Skill is compatible with all AI programming tools that support the Skills specification.
For more details, see Skills. For a complete usage example, see AI Conversational Deployment: Deploying a Project with a Single Command Using Skill.
AI Context File
In Makers, AI context files serve as the bridge between you and AI IDEs (such as CodeBuddy, Cursor, Windsurf). Written in Markdown format, these files allow you to define project-specific rules, best practices, code standards, API definitions, and even business logic descriptions. By using context files, you can provide precise contextual information to the AI, ensuring that the code, suggestions, and automated operations it generates better align with your project requirements and platform characteristics.
You can download the Makers context file via this URL: pages-llms.mdc
Using Mdc Files in AI IDEs
For most AI development tools, you only need to place the pages-llms.mdc file in the project root directory as a project-level rule or set it as a global rule in the development tool.
For use in CodeBuddy: Enter the settings interface in the IDE, locate the rule tab, and add the .mdc file under project rules. For more information, view the document Using CodeBuddy IDE.
For use in Cursor: Create a .cursor/rules/ folder in the project root directory and place your .mdc file there. Or add it to the user main directory (such as ~/.cursor/rules/). For more information, view the sample code in Cursor official documentation.
For use in Windsurf: Create a .windsurf/rules/ folder in the project root directory and place your .mdc file there. Or manually add this file through the Windsurf UI. For more information, view the sample code in Windsurf official documentation.
Using Llms.Txt
You can also use llms.txt in AI conversations to share the context of Makers documentation. Typically, if the AI conversation tool supports this format, llms.txt will be referenced as a web resource context.
AI Development Assistance and Deployment Practice
The following best practice will guide you on how to collaborate with AI effectively for faster and better project development.
Optimize Prompt Content
Clear and structured prompts are key to effective communication with AI. Follow the rules below to help AI understand your intent more accurately.
Use the total score structure: First state the overall goal, then gradually refine specific requirements, such as "create a responsive blog homepage with navigation, article list and footer."
Use exact terminology: Use precise descriptions in key instructions, such as "implement a blue color scheme flat design with Tailwind CSS."
Provide existing examples: By providing existing code or design pattern examples, guide AI to generate content compliant with your style.
Continuously adjust and iterate: Try different expressions to organize prompt content for the best results caused by AI.
EdgeOne Makers Prompt Key Phrases
To help the AI better understand your intent and generate project code that can be smoothly deployed to Makers. When you converse with the AI, mentioning these terms will significantly improve the accuracy and relevance of the AI's output.
EdgeOne Makers: Explicitly specify the target deployment platform.
Example: "Create a Next.js blog application for EdgeOne Makers."
Cloud Functions: Specify backend logic that requires the use of Node.js runtime environment.
Example: "I need a Cloud Functions with Node.js runtime to handle user authentication."
Edge Functions: Specify lightweight logic that requires edge computing capability.
Example: "Please write an Edge Functions to implement geolocation redirection."
Full-stack application: Emphasize the project includes frontend and backend.
Example: "Develop a full-stack application to get local weather in real time, using React for the frontend and Node Functions for the backend."
AI Rule file: Specify the use of a specific AI rule file to guide the AI.
Example: "Refer to the rules in the mdc file to generate code that complies with EdgeOne Makers specifications."
Refine Project Information
Provide appropriate AI context to help the AI better understand your project.
Fully utilize context files: Supplement the project structure, API interface, or business logic appropriately in pages-llms.mdc. AI IDE will automatically load these rules to ensure the generated code meets project requirements.
Write a high-quality README: This is the key entry for AI to understand the project. A clear, detailed README.md should include project introduction, technology stack, deployment guide, and key module description to help AI quickly grasp the holistic picture and provide accurate recommendations.
