Rules

Defines architectural principles, 5-layer model, and approved technologies for AI platform development.

Updated Feb 6, 2026
One-click install
npx skills add https://github.com/gyeongsu01/ai-arch-dev --skill rules-gyeongsu01
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Rules
Source: https://github.com/gyeongsu01/ai-arch-dev/tree/main/Rules
Command: npx skills add https://github.com/gyeongsu01/ai-arch-dev --skill rules-gyeongsu01

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill defines the foundational principles, architectural guidelines, and technical stack for building an enterprise AI platform, ensuring consistency, scalability, and maintainability.

Core Features & Use Cases

  • Architectural Governance: Enforces a 5-layer model (Infra, Platform, Data, Service, Agent) with strict dependency rules.
  • Technology Standardization: Specifies approved and prohibited technologies for each layer, promoting efficient resource utilization and avoiding vendor lock-in.
  • Coding Conventions: Provides clear guidelines for infrastructure (YAML/Helm) and backend (Python) development, ensuring code quality and readability.
  • Use Case: A new team joining the AI platform initiative can immediately understand the established best practices, technology choices, and development standards, accelerating their onboarding and contribution.

Quick Start

Review the 5-layer model and the approved technologies for the Data layer.

Frequently Asked Questions about Rules

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is a 5-layer model for enterprise AI platform architecture?

A 5-layer model for enterprise AI platform architecture separates concerns into Infrastructure, Platform, Data, Service, and Agent layers. This governance approach enforces strict dependency rules to ensure scalability and maintainability across the technology stack.

How do I standardize technology choices across an AI platform team?

Standardize technology choices across an AI platform team by defining approved and prohibited technologies for each architectural layer. This governance process enforces efficient resource utilization, maintains coding conventions, and prevents vendor lock-in.

Can I use k3d and Ollama for container-first AI infrastructure?

Yes, you can use k3d and Ollama for container-first AI infrastructure. This architecture governs k3d for Kubernetes provisioning and Ollama for local LLM deployment, enforcing IaC and container-first design principles across the platform layer.

What coding conventions should I follow for FastAPI and LangGraph backend services?

Coding conventions for FastAPI and LangGraph backend services mandate Python development standards ensuring code quality and readability. These backend guidelines align with the Service and Agent architectural layers to enforce consistency across the enterprise platform.

How do I enforce observability and IaC in an enterprise AI tech stack?

Enforce observability and IaC in an enterprise AI tech stack by applying strict architectural principles across infrastructure and platform layers. This requires YAML/Helm coding conventions and container-first design to maintain operational consistency.

Why does the AI platform prohibit certain technologies at the data layer?

The AI platform prohibits certain technologies at the data layer to prevent vendor lock-in and promote efficient resource utilization. Governing technology standardization ensures that tools like ChromaDB integrate cleanly without violating strict architectural boundaries.