All skills
layered-architecture-design
FoundationJIT onlyanalysis-agent/task-agent: use when presentation, application, domain, or infrastructure ownership/dependencies change; skip without a layering decision.
- Group
- Architecture & design
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- design presentation application domain infrastructure and persistence layering
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local layered architecture design decision is required
Required inputs
What must be supplied before this skill can decide anything
- current task contract
- selected primary Professional Skill
- task-local trigger evidence
Output contract
What this skill owes the next role
- layered-architecture decision with responsibilities, dependency direction, domain and orchestration boundary, adapters, cross-cutting placement, evidence, proof limits, and residual owners
Escalation signals
When this skill must hand the decision back
- Layer violations hide business rules and make testing expensive
Loaded by
This skill never owns a task. These professionals may pull it in as Layer 3.
Targeted references
Each reference carries its own load condition. None of them enter context by default.
| Reference | Load when | Do not load when | Required by |
|---|---|---|---|
| benchmarks-and-patterns.mdbenchmark-pattern | placement transaction or failure translation has competing layer choices | current dependency direction and ownership select one layer placement | AnalysisTask |
| checklist.mddecision-checklist | change crosses presentation application domain infrastructure or adapter boundaries | owner-internal change preserves all established layer contracts | AnalysisTask |
| evidence-patterns.mdevidence-pattern | layer dependency transaction or exception claims need current proof | post-edit imports tests and architecture checks prove each claim | AnalysisTask |