Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
The English summary is being prepared. Showing the original description.
Selects and routes to the right architecture paradigm. Use when choosing patterns for a new system or comparing trade-offs before making architecture decisions.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
pensive:architecture-review)This skill helps you select the right architecture paradigm(s) for your system, then routes you to the specific paradigm skill for implementation details.
Match your needs to the recommended paradigm:
| Your Scenario | Primary Paradigm | Load Skill |
|---|---|---|
| Enterprise app with multiple teams | Microservices or Modular Monolith | architecture-paradigm-microservices or architecture-paradigm-modular-monolith |
| Complex business rules & testing | Functional Core, Imperative Shell | architecture-paradigm-functional-core |
| Real-time/event processing | Event-Driven Architecture | architecture-paradigm-event-driven |
| Legacy system modernization | Hexagonal (Ports & Adapters) | architecture-paradigm-hexagonal |
| Cloud-native/bursty workloads | Serverless | architecture-paradigm-serverless |
| ETL/data processing pipeline | Pipeline Architecture | architecture-paradigm-pipeline |
| Simple CRUD app | Layered Architecture | architecture-paradigm-layered |
| Command/query separation | CQRS and Event Sourcing | architecture-paradigm-cqrs-es |
| Rich business rules to model | Domain-Driven Design | architecture-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.
Primary Concerns (select all that apply):
functional-core or hexagonalmicroservices or modular-monolithhexagonalevent-driven or space-basedlayered or modular-monolithhexagonal or microkernelSystem Context:
< 5 → Layered/Functional Core | 5-15 → Modular Monolith | 15-50 → Microservices | 50+ → Microservices/Space-BasedSimple → Layered | Moderate → Hexagonal/Modular Monolith | Complex → Functional Core/CQRS | Highly Complex → Microservices/Event-DrivenBased on your needs from Step 1, review these options:
For Testability & Business Logic
architecture-paradigm-functional-core - Isolates business logic from infrastructurearchitecture-paradigm-hexagonal - Clear domain/infrastructure boundariesFor Team Autonomy
architecture-paradigm-microservices - Independent deployment and scalingarchitecture-paradigm-modular-monolith - Team autonomy without distributed complexityFor Infrastructure Flexibility
architecture-paradigm-hexagonal - Swap infrastructure without domain changesFor Simplicity & Maintainability
architecture-paradigm-layered - Simple, well-understood separationFor Rich Business Rules
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
architecture-paradigm-event-driven - Scalable, decoupled processingarchitecture-paradigm-space-based - In-memory data grids for linear scalabilityFor Legacy Integration
architecture-paradigm-microkernel - Plugin architecture for extensible platformsarchitecture-paradigm-hexagonal - Adapters for external systemsOnce you've selected your paradigm(s), load the specific skill for detailed guidance:
# Example: You selected Hexagonal Architecture
Skill(archetypes:architecture-paradigm-hexagonal)
The individual paradigm skill provides:
| Paradigm | Complexity | Team Size | Best For | Skill Name |
|---|---|---|---|---|
| Functional Core | Medium | Small-Large | Complex business logic | architecture-paradigm-functional-core |
| Hexagonal | Medium | Small-Large | Infrastructure changes | architecture-paradigm-hexagonal |
| Layered | Low | Small-Medium | Simple domains | architecture-paradigm-layered |
| Modular Monolith | Medium | Medium-Large | Evolving systems | architecture-paradigm-modular-monolith |
| Microservices | High | Large | Complex domains | architecture-paradigm-microservices |
| Event-Driven | High | Medium-Large | Real-time processing | architecture-paradigm-event-driven |
| CQRS and ES | High | Medium-Large | Audit trails | architecture-paradigm-cqrs-es |
| Service-Based | Medium | Medium | Coarse-grained services | architecture-paradigm-service-based |
| Serverless | Medium | Small-Medium | Cloud-native/bursty | architecture-paradigm-serverless |
| Microkernel | Medium | Small-Medium | Plugin systems | architecture-paradigm-microkernel |
| Space-Based | High | Large | Linear scalability | architecture-paradigm-space-based |
| Pipeline | Low | Small-Medium | ETL workflows | architecture-paradigm-pipeline |
| Client-Server | Low | Small | Traditional apps | architecture-paradigm-client-server |
| Domain-Driven Design | Medium | Small-Large | Rich business rules (composes with the above) | architecture-paradigm-domain-driven |
/architecture-review for evaluation/writing-plans for detailed task breakdownSkill(archetypes:architecture-paradigm-NAME)No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
The English summary is being prepared. Showing the original description.
Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.
The English summary is being prepared. Showing the original description.
Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.
The English summary is being prepared. Showing the original description.
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
The English summary is being prepared. Showing the original description.
Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.
The English summary is being prepared. Showing the original description.
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
The English summary is being prepared. Showing the original description.