agentic_architecture

Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.

16 stars

Best use case

agentic_architecture is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.

Teams using agentic_architecture should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/agentic_architecture/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/development/agentic_architecture/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/agentic_architecture/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How agentic_architecture Compares

Feature / Agentagentic_architectureStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Agentic Architecture Protocol

## 1. Think Before You Code
Before implementing any feature that spans multiple files:
1.  **Analyze Data Flow**: Where does data come from? Where does it go?
2.  **Define Interfaces**: creating `types/*.ts` is often the best first step.
3.  **Check Boundaries**: Ensure API logic stays in `api/`, UI in `components/`, and business logic in `services/` or `hooks/`.

## 2. Scalability & Performance Checks
- **Database**:
    - Are we fetching 1000 items to filter 10? (Use DB filters instead).
    - Is RLS (Row Level Security) compatible with this query?
- **Frontend**:
    - Are we causing unnecessary re-renders? (Use `React.memo`, `useCallback` appropriately).
    - Is this component becoming a "God Component"? (Break it down).

## 3. The "Three-Tier" Rule
For any non-trivial feature, verify you have these three layers:
1.  **Data Layer**: Types + API/Service (e.g., `user.types.ts`, `userService.ts`)
2.  **State Layer**: Hook or Store (e.g., `useUser.ts`)
3.  **View Layer**: Components (e.g., `UserProfile.tsx`)

## 4. Architecture Checklist
- [ ] Have I defined the types first?
- [ ] Is the business logic separated from the UI?
- [ ] Did I consider how this scales to 10,000 users/items?
- [ ] Is the database schema validated (if changing DB)?

Related Skills

agentic-structure

16
from diegosouzapw/awesome-omni-skill

Collaborative programming framework for production-ready development. Use when starting features, writing code, handling security/errors, adding comments, discussing requirements, or encountering knowledge gaps. Applies to all development tasks for clear, safe, maintainable code.

agentic-jumpstart-frontend

16
from diegosouzapw/awesome-omni-skill

Frontend UI patterns with shadcn/ui, Radix UI, Tailwind CSS v4, and Lucide icons. Use when building UI components, styling, layouts, buttons, cards, dialogs, forms, responsive design, or when the user mentions UI, styling, Tailwind, components, or design.

agentic-jumpstart-code-quality

16
from diegosouzapw/awesome-omni-skill

Code quality guidelines for Jarvy CLI - Rust formatting, Clippy linting, error handling patterns, documentation standards, and Conventional Commits.

agentic-jumpstart-architecture

16
from diegosouzapw/awesome-omni-skill

Architecture guidelines for Jarvy CLI - codebase structure, tool implementation patterns, registry system, platform-specific code organization, and module conventions.

Advanced Clean Hexagonal Architecture

16
from diegosouzapw/awesome-omni-skill

Apply Clean Architecture and Hexagonal (Ports & Adapters) patterns for domain isolation and testability. Use when designing system boundaries, creating ports/adapters, or structuring domain-driven applications.

ADR (Architecture Decision Record)

16
from diegosouzapw/awesome-omni-skill

Create and maintain Architecture Decision Records following a consistent template

acc-architecture-doc-template

16
from diegosouzapw/awesome-omni-skill

Generates ARCHITECTURE.md files for PHP projects. Creates layer documentation, component descriptions, and architectural diagrams.

1k-architecture

16
from diegosouzapw/awesome-omni-skill

OneKey monorepo architecture and code organization. Use when understanding project structure, package relationships, import rules, or component organization. Triggers on architecture, structure, packages, imports, hierarchy, dependencies, monorepo, organization.

microservices-architecture

16
from diegosouzapw/awesome-omni-skill

Microservices architecture patterns and best practices. Use when designing distributed systems, breaking down monoliths, or implementing service communication.

architecture-patterns

16
from diegosouzapw/awesome-omni-skill

Padrões de arquitetura de software - Decisões OBJETIVAS sobre design de sistemas

rails-architecture

16
from diegosouzapw/awesome-omni-skill

Guides modern Rails 8 code architecture decisions and patterns. Use when deciding where to put code, choosing between patterns (service objects vs concerns vs query objects), designing feature architecture, refactoring for better organization, or when user mentions architecture, code organization, design patterns, or layered design.

mvvm-architecture

16
from diegosouzapw/awesome-omni-skill

Expert MVVM decisions for iOS/tvOS: choosing between ViewModel patterns (state enum vs published properties vs Combine), service layer boundaries, dependency injection strategies, and testing approaches. Use when designing ViewModel architecture, debugging data flow issues, or deciding where business logic belongs. Trigger keywords: MVVM, ViewModel, ObservableObject, @StateObject, service layer, dependency injection, unit test, mock, architecture