Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-architecture-patterns
Comprehensive architecture patterns, methodologies, quality frameworks, and evaluation methods for solution architects. Load when designing system architecture or selecting patterns.
Passed 20 of 23 test cases with the skill, and 18 of 23 without it.
2 fixed18 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are choosing an open-source library for a proprietary commercial application. The team is considering packages licensed under MIT, AGPL v3, and Apache 2.0. Rank these three licenses in terms of suitability for commercial proprietary software, from most preferred to least preferred.
| Checked | Without skill | With skill |
|---|---|---|
| Ranks MIT license as the most preferred option. | Missed | Passed |
| Ranks AGPL v3 license as the least preferred option. | Passed | Passed |
The instructions your model reads when the skill loads.
Four levels for different audiences:
Notation/tooling independent. Reduces communication overhead, shared visual language across stakeholders.
Isolate business logic from infrastructure through ports (interfaces) and adapters (implementations).
Benefits: testability (isolated core) | flexibility (swap infrastructure) | technology independence | maintainability
Testing: unit tests through driving ports, mock driven ports | integration tests with real infrastructure | acceptance tests end-to-end through primary ports
Horizontal layers with defined dependencies. Use for: traditional enterprise apps, clear separation. Trade-off: familiar but potential overhead, layer coupling.
Independent deployable services per capability. Use for: large teams, component scaling, tech diversity. Trade-off: scalability vs operational complexity. 2025 consensus: "start monolith, evolve when needed." Modular monolith = valid middle ground.
Components communicate via events through broker. Use for: real-time, complex processes, loose coupling. Trade-off: scalability/decoupling vs event ordering, debugging.
Separate read/write models; store events not state. Use for: financial, audit, temporal queries. Trade-off: complete history + independent scaling vs eventual consistency + complexity. NOT for: simple CRUD, strong consistency, inexperienced teams.
test cases passed, vs 18 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.