All skills
architecture-impact-reviewer
ProfessionalRuntime top levelUse analysis-agent for module-boundary or dependency-direction analysis, or review-agent for independent assessment of a bounded architecture artifact. Skip isolated owner-internal edits with no structural impact.
- Group
- Impact, domain and architecture
- Routing mode
- evidence-only
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- module boundary change
- dependency direction risk
- owner-internal implementation structure reuse or deliberate separation remains unresolved
Do not use when
Anti-triggers — as binding as the triggers above
- isolated owner internal edit after placement is fixed
- no structural impact
Required inputs
What must be supplied before this skill can decide anything
- desired behavior
- module and dependency boundary
Output contract
What this skill owes the next role
- placement decision
- architecture verdict
- structural risk
Escalation signals
When this skill must hand the decision back
- scope, authority, or material risk exceeds the selected task contract
Related expertise
12 Layer 3 candidates may be loaded behind this skill. A single task loads at most three, and only when the current evidence justifies them.
- module-boundary-design
- implementation-structure-design
- design-pattern-selection
- architecture-tradeoff-analysis
- consumer-impact-analysis
- architecture-enforcement-tooling
- architecture-style-selection
- event-driven-architecture
- extensibility-design
- layered-architecture-design
- microservice-splitting
- technology-stack-selection
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 |
|---|---|---|---|
| placement-and-ownership.mdtargeted | Structure responsibility ownership reuse or placement remains open | Owner public/private surface and smallest viable placement are fixed by current evidence | AnalysisReview |
| consumer-and-data-impact.mdtargeted | Public or indirect consumer or authoritative-data impact remains open | No consumer contract compatibility versioning migration or data-owner boundary changes | AnalysisReview |
| dependency-topology-and-enforcement.mdtargeted | Dependency direction topology or durable enforcement remains open | Current source edges topology owner and enforcement evidence already fix the boundary | AnalysisReview |
| reversibility-evolution-and-proof-limits.mdtargeted | Reversal coexistence migration evolution or architecture proof limits remain open | Current evidence fixes reversibility evolution residual risk and next owner | AnalysisReview |
| checklist.mddecision-checklist | A bounded L2 mode needs compact checks for its triggered placement, ownership, dependency, consumer, data, topology, or reversibility risk | The root contract is enough or targeted proof fields are required | AnalysisReview |
| index.mdindex | competing architecture impact reviewer references require dependency, conflict, or output-fragment selection | the architecture impact reviewer root or a task-named reference already resolves selection | AnalysisReview |
| solution-optimality.mdtargeted | An architecture boundary, ownership, dependency, topology, or operational-responsibility decision has a material alternative | The change is owner-internal with no structural impact or current evidence already fixes placement | AnalysisReview |