메뉴
Designs event-driven systems with asynchronous flows, brokers, producers, consumers and contracts. Use when architecting asynchronous, decoupled, or event-first systems, including order status updates and domain event flows.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Governs AI models through inventory, purpose, risk tier, approval, monitoring, drift, kill-switch and retirement. Use when introducing, changing or operating models in production or agent workflows.
Applies an Asimov-inspired hierarchy of AI safety laws when material AI or instruction risk is present. Use when harm, unlawful requests, authority conflicts, or safety trade-offs need an explicit law hierarchy. Also known as apply_laws_of_AI.
Use when implementing input validation, output filtering, tool restrictions, policy enforcement, secure coding controls, destructive-tool guardrails, approval gates, or safe agent behaviour.
Use when starting a session or deciding which local skill applies; acts as the meta-skill for discovering and loading the smallest relevant skill.
Use when measuring coding-agent quality, RAG evaluation, regression risk, latency, cost, reliability, safety, or production performance for agent systems.
Designs ontology-driven knowledge graphs for explainable KG-RAG. Use when modelling semantic graphs, ontologies, or graph schemas for retrieval.
| name | event-driven-architecture |
| description | Designs event-driven systems with asynchronous flows, brokers, producers, consumers and contracts. Use when architecting asynchronous, decoupled, or event-first systems, including order status updates and domain event flows. |
| aliases | ["event-driven","event-first-architecture","order-status-updates","order-status-events","asynchronous-event-architecture"] |
Use when designing asynchronous integration or event-first systems.
Produce a practical, concise, traceable architecture artefact that a coding agent can use to guide implementation or review.
Apply event-driven best practice: business event semantics, producer/consumer ownership, schema contracts, compatibility, ordering, partitioning, idempotency, replay, retention, lineage, observability and operational SLOs.
Use open standards where they fit: CloudEvents for a common event envelope and metadata (id, source, type, time, dataschema), and AsyncAPI for application-level channel, operation and message contracts. CloudEvents and AsyncAPI are complementary (envelope vs interface).
Do not use events to disguise tight coupling.
Choose event-driven architecture when producers and consumers can evolve independently, consumers need replay, or business facts must be observed by multiple domains. Prefer request/response when the caller needs an immediate answer and no other consumer benefits. For each event, record owner, contract, idempotency key, ordering assumption, retry policy and observable failure path.
