All skills
model-boundary-mapping
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when API/DTO, domain, persistence, event, generated, null/default, or mapper boundaries may leak; skip when models stay isolated.
- Group
- Data & API contracts
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- model boundary mapping API DTO command query domain object value object persistence model ORM event payload view model mapper assembler null default optional schema version serialization validation generated handwritten leakage
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local model boundary mapping 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
- Return a Model Boundary Map: identify source, target, mapping and validation owners, null/default semantics, compatibility, generated/handwritten boundary, tests, and rejected leakage
Escalation signals
When this skill must hand the decision back
- Model leakage couples API persistence domain and generated boundaries causing semantic drift validation ambiguity and consumer breakage
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 | transport domain persistence event or provider models invite competing mappings | one owned mapper preserves every semantic and visibility boundary | TaskReviewAnalysis |
| checklist.mddecision-checklist | mapping changes fields defaults null semantics ownership or generated boundaries | source and target models remain unchanged and isolated | TaskReviewAnalysis |
| evidence-patterns.mdevidence-pattern | no-leak compatibility or semantic-preservation claims need fresh proof | current schemas consumers generated outputs and tests prove each claim | TaskReviewAnalysis |