Architecture Paradigms logo

Architecture Paradigms

Community
athola
architecture-paradigms

Selects and routes to the right architecture paradigm. Use when choosing patterns for a new system or comparing trade-offs before making architecture decisions.

Overview

Publisherathola
Repositoryclaude-night-market
Skill namearchitecture-paradigms
Stars
343
Forks
37
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by athola on GitHub. Read the source before you install it.

Installation

Install the Architecture Paradigms AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/athola/claude-night-market/tree/master/plugins/archetypes/skills/architecture-paradigms
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/athola/claude-night-market.git /tmp/claude-night-market
mkdir -p .claude/skills
cp -r /tmp/claude-night-market/plugins/archetypes/skills/architecture-paradigms .claude/skills/architecture-paradigms
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Architecture Paradigms in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Architecture Paradigms on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Architecture Paradigms is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

When NOT To Use

  • The paradigm is already chosen, so go straight to that paradigm's skill
  • Reviewing an existing design against its ADRs (use pensive:architecture-review)

Architecture Paradigm Router

This skill helps you select the right architecture paradigm(s) for your system, then routes you to the specific paradigm skill for implementation details.

Quick Scenario Router

Match your needs to the recommended paradigm:

Your ScenarioPrimary ParadigmLoad Skill
Enterprise app with multiple teamsMicroservices or Modular Monolitharchitecture-paradigm-microservices or architecture-paradigm-modular-monolith
Complex business rules & testingFunctional Core, Imperative Shellarchitecture-paradigm-functional-core
Real-time/event processingEvent-Driven Architecturearchitecture-paradigm-event-driven
Legacy system modernizationHexagonal (Ports & Adapters)architecture-paradigm-hexagonal
Cloud-native/bursty workloadsServerlessarchitecture-paradigm-serverless
ETL/data processing pipelinePipeline Architecturearchitecture-paradigm-pipeline
Simple CRUD appLayered Architecturearchitecture-paradigm-layered
Command/query separationCQRS and Event Sourcingarchitecture-paradigm-cqrs-es
Rich business rules to modelDomain-Driven Designarchitecture-paradigm-domain-driven

One of these is not like the others. Domain-Driven Design answers "what are the concepts and what do we call them." The rest answer "where does the code go." DDD composes with a structural paradigm (commonly layered, hexagonal, or modular monolith) rather than competing with it, so selecting it does not mean deselecting one of the others.

3-Step Selection Workflow

Step 1: Define Your Needs

Primary Concerns (select all that apply):

  • Testability: Isolate business logic → functional-core or hexagonal
  • Team Autonomy: Independent deployment → microservices or modular-monolith
  • Infrastructure Flexibility: Swap databases/frameworks → hexagonal
  • Real-time Scaling: Variable loads with events → event-driven or space-based
  • Simplicity: Maintainable without complexity → layered or modular-monolith
  • Legacy Integration: Work with existing systems → hexagonal or microkernel

System Context:

  • Team Size: < 5 → Layered/Functional Core | 5-15 → Modular Monolith | 15-50 → Microservices | 50+ → Microservices/Space-Based
  • Domain Complexity: Simple → Layered | Moderate → Hexagonal/Modular Monolith | Complex → Functional Core/CQRS | Highly Complex → Microservices/Event-Driven

Step 2: Evaluate Paradigms

Based on your needs from Step 1, review these options:

For Testability & Business Logic

  • Load architecture-paradigm-functional-core - Isolates business logic from infrastructure
  • Load architecture-paradigm-hexagonal - Clear domain/infrastructure boundaries

For Team Autonomy

  • Load architecture-paradigm-microservices - Independent deployment and scaling
  • Load architecture-paradigm-modular-monolith - Team autonomy without distributed complexity

For Infrastructure Flexibility

  • Load architecture-paradigm-hexagonal - Swap infrastructure without domain changes

For Simplicity & Maintainability

  • Load architecture-paradigm-layered - Simple, well-understood separation

For Rich Business Rules

  • Load architecture-paradigm-domain-driven - Models the business in its own language. Pair it with whichever structural paradigm you picked above; it does not replace one. Skip it when the domain is CRUD over a form, where the model would just be the schema under a new name.

For Real-time Event Processing

  • Load architecture-paradigm-event-driven - Scalable, decoupled processing
  • Load architecture-paradigm-space-based - In-memory data grids for linear scalability

For Legacy Integration

  • Load architecture-paradigm-microkernel - Plugin architecture for extensible platforms
  • Load architecture-paradigm-hexagonal - Adapters for external systems

Step 3: Load Paradigm Skill for Implementation

Once you've selected your paradigm(s), load the specific skill for detailed guidance:

bash
# Example: You selected Hexagonal Architecture
Skill(archetypes:architecture-paradigm-hexagonal)

The individual paradigm skill provides:

  • ✅ Complete implementation guide
  • ✅ ADR templates
  • ✅ Migration checklist
  • ✅ Code examples
  • ✅ Testing strategies
  • ✅ Risk assessments

Available Paradigm Skills

ParadigmComplexityTeam SizeBest ForSkill Name
Functional CoreMediumSmall-LargeComplex business logicarchitecture-paradigm-functional-core
HexagonalMediumSmall-LargeInfrastructure changesarchitecture-paradigm-hexagonal
LayeredLowSmall-MediumSimple domainsarchitecture-paradigm-layered
Modular MonolithMediumMedium-LargeEvolving systemsarchitecture-paradigm-modular-monolith
MicroservicesHighLargeComplex domainsarchitecture-paradigm-microservices
Event-DrivenHighMedium-LargeReal-time processingarchitecture-paradigm-event-driven
CQRS and ESHighMedium-LargeAudit trailsarchitecture-paradigm-cqrs-es
Service-BasedMediumMediumCoarse-grained servicesarchitecture-paradigm-service-based
ServerlessMediumSmall-MediumCloud-native/burstyarchitecture-paradigm-serverless
MicrokernelMediumSmall-MediumPlugin systemsarchitecture-paradigm-microkernel
Space-BasedHighLargeLinear scalabilityarchitecture-paradigm-space-based
PipelineLowSmall-MediumETL workflowsarchitecture-paradigm-pipeline
Client-ServerLowSmallTraditional appsarchitecture-paradigm-client-server
Domain-Driven DesignMediumSmall-LargeRich business rules (composes with the above)architecture-paradigm-domain-driven

Integration with Other Skills

  • Architecture Review: Use this skill first to select paradigms, then /architecture-review for evaluation
  • Implementation Planning: Select paradigms here, then /writing-plans for detailed task breakdown
  • Refactoring: Identify target paradigms here, then use paradigm-specific skills for migration strategies

Exit Criteria

  • At least one paradigm is selected with clear rationale
  • Specific paradigm skill has been loaded for detailed guidance
  • Ready to create ADR or implementation plan

Next Steps

  1. Load the specific paradigm skill - Use Skill(archetypes:architecture-paradigm-NAME)
  2. Generate an ADR - Use the paradigm's ADR templates
  3. Create implementation plan - Use paradigm's migration checklist
  4. Set up monitoring - Track success metrics from paradigm guidance

Frequently asked questions

What does the Architecture Paradigms AI skill do?

Selects and routes to the right architecture paradigm. Use when choosing patterns for a new system or comparing trade-offs before making architecture decisions.

Why use Architecture Paradigms on TypingMind?

Because you install it once and use it with any model. Architecture Paradigms is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Architecture Paradigms in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/athola/claude-night-market/tree/master/plugins/archetypes/skills/architecture-paradigms. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Architecture Paradigms?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Architecture Paradigms?

As many as you like. As long as a model supports skills, you can use Architecture Paradigms with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Architecture Paradigms AI skill free?

Yes. It is published on GitHub by athola under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇