AI Agent Workflow Collection

Use when the user mentions existing systems, legacy, migration, brownfield, "we already have", "starting from", "current state", or asks how to adopt MD-DDL into an environment with existing data assets. Also use when the user asks about maturity levels, adoption timelines, or how to plan an MD-DDL rollout.

Use when the user asks "what is [concept]", "how does [feature] work", "explain [section]", "compare MD-DDL to [tool]", "why does MD-DDL [design choice]", or any question about a specific part of the standard. Also use when the user wants to understand the reasoning behind a design decision or the trade-offs between alternatives (entity vs enum, canonical vs bounded context, etc.). Also use when the user asks about "linting", "validation", "conformance checking", "why no linter", "how do I check my model", "is there a validator", or any question about how MD-DDL enforces or checks correctness. Also use for eventual consistency, strong consistency, consistency posture, propagation lag, freshness SLA, convergence, null handling, partial rows, NOT NULL constraints under eventual consistency, storage format null semantics (Parquet, Avro, Protobuf), transport protocol null handling, how to model or validate eventual consistency in MD-DDL. Also use when the user asks about synthetic data generation, Faker factories, test data, enterprise profiles, demographic weights, product catalogues, how to generate realistic or tailored test data, or how to make synthetic data reflect a specific industry, geography, customer mix, or product portfolio.

Use when the user asks to review, audit, validate, or quality-check an existing MD-DDL domain and its detail files. Also use before declaring a domain “complete” or production-ready. This skill performs both structural conformance checks and decision-quality checks for relationship granularity, temporal tracking, existence, mutability, conceptual-to-logical realization, standards alignment, and regulatory posture.

Use when starting a new domain model, when the user says "model this domain" or describes a business area from scratch, when scoping or boundary questions arise, or when choosing between canonical and domain-driven modelling strategies. Also use when the user asks who should own a concept or whether two concepts are the same thing across different domains.

Use when modelling entities or their attributes, when the user says "types of" or "kinds of" something, when inheritance questions arise, or when deciding whether a concept should be a first-class entity, an enum, an attribute, or a relationship attribute. Also use when the user is unsure whether two similar concepts are the same entity or separate ones.

Use when the user asks for a normalized operational model, practical/pragmatic 3NF, OLTP schema design, or non-dimensional physical outputs. Also use when producing database DDL, JSON Schema, or Parquet-oriented schema contracts from MD-DDL.

Use this skill on first contact, when the user asks "what is MD-DDL", "where do I start", "what can I do here", or describes their role and goals. Also use when the user asks for a general overview of the standard, the agent ecosystem, or the workflow.

Use when connecting entities with relationships, when modelling what happens when something changes (business events), when cardinality or ownership questions arise, when the user asks "what happens when X" or "who initiates Y", or when deciding whether something is a relationship attribute vs. an entity attribute. Also use when the user asks about event payloads, downstream impacts, or temporal sequencing of business state changes.

Use when the user wants to get from an existing database schema to a draft MD-DDL domain. This is the PRIMARY brownfield adoption path. Triggers include "import schema", "reverse engineer", "I have a database", "here's my DDL", "start from existing tables", "convert my schema", "paste DDL", "brownfield", "existing schema", or when the user provides CREATE TABLE statements, dbt schema.yml, or similar structured schema definitions expecting a canonical domain as output.

Use when the user asks to see an example, says "walk me through", "show me how [concept] looks in practice", mentions the Simple Customer or Financial Crime example, or wants to understand how a complete MD-DDL model is structured. Also use when a user asks for a concrete demonstration of a concept after it has been explained.