Use when the user proposes — or the agent detects — a deviation from constitutional defaults that requires an Architecture Decision Record. Triggered by proposals to extract microservices, drop foreign keys, denormalize without measured evidence, store transactional truth in Neo4j, skip Row Level Security, skip the transactional outbox, run destructive migrations, use database-per-service, or any explicit override of a constitutional principle. Drafts a structured ADR with context, decision, consequences, alternatives rejected, migration path, validation criteria, and constitutional sections affected — and refuses to proceed with the underlying work until the ADR is at least Proposed status.

Use when designing or reviewing database architecture for high-demand multi-tenant commerce platforms — including PostgreSQL schema design, foreign keys, indexes, JSONB usage, multi-tenant isolation with Row Level Security, transactional outbox, Neo4j GraphRAG projections, event sourcing decisions, audit logging, partitioning, expand/contract migrations, and product/inventory/order modeling for restaurants, boutiques, drugstores, retailers, distributors, grocery, hardware, or appliance businesses. Triggered by any request to design tables, design schemas, create migrations, model products/variants/inventory/orders/payments, choose between monolith and microservices, choose between PostgreSQL and Neo4j as source of truth, model multi-tenant data, design event flows, or review an ER diagram.

Use when reviewing or designing how Neo4j and GraphRAG interact with PostgreSQL transactional truth — including any feature involving recommendations, semantic product search, ingredient relationships, substitution suggestions, complementary products, AI-assisted discovery, vector search combined with graph traversal, or any proposal that puts orders, inventory, payments, prices, or tenant access rules into Neo4j. Evaluates architectural proposals for data boundary violations, identifies sync pattern errors between Neo4j and PostgreSQL, produces structured design review feedback with severity-ranked findings, counter-proposals with Mermaid diagrams, eventing changes, and re-projection plans. Triggered by mentions of GraphRAG, Neo4j, knowledge graph, recommendations engine, semantic search, vector + graph hybrid search, AI product discovery, or any design that crosses the PostgreSQL ↔ Neo4j boundary.

Writes MySQL 8.4 stored procedures and the sequelize-cli migration that creates them, for Node backends on Sequelize 6 and mysql2. Covers a .sql script that also runs with the mysql client through DELIMITER, a migration that sends DROP and only the CREATE PROCEDURE block in separate queries, a JSON parameter read with JSON_TABLE for header-plus-lines data such as a sale and its items, an EXIT HANDLER with ROLLBACK and RESIGNAL, SIGNAL SQLSTATE 45000 for business rules, totals computed in SQL as DECIMAL(10,2), and exactly one final SELECT. Use when asked to create or change a stored procedure, to save a sale with its items (or any header with lines) in one call, when a migration fails with ER_PARSE_ERROR 1064 near DELIMITER, when deciding between docker-entrypoint-initdb.d and migrations, or when a procedure must validate input and roll back.

Calls MySQL stored procedures from Node with Sequelize 6 and mysql2 and turns their errors into HTTP responses in Express. Covers CALL with named replacements and JSON.stringify for lists, reading rows[0], why QueryTypes.SELECT, OUT parameters and sequelize.transaction() break a CALL, errno mapping (1644, 1452, 3140, 1062) to 422, 404, 400 and 409, money kept as DECIMAL strings, and safe name or barcode search with Op symbols. Use when writing a service or route that runs CALL, when a CALL returns nested arrays, objects with numeric keys or undefined, when adding status codes for procedure errors, when someone wants to wrap a procedure call in a transaction, or when searching products by name or barcode.

Creates Postgres triggers that fire database webhooks to Edge Functions or external endpoints on INSERT/UPDATE/DELETE events. Configures pg_net for HTTP callouts and payload serialization. Use when implementing event-driven workflows, database webhooks, trigger-based notifications, or automated pipelines on table changes.

Audits an already-written use case (UC-XXX) or test case (TC-XXX) against its specification and reports a coverage matrix: which main success scenario steps, alternative flows, business rules, preconditions, and postconditions have code and tests behind them, which are still open, and which code or tests have drifted away from the specification. Use when the user asks to "check coverage", "run a coverage check", "is UC-001 fully implemented", "is UC-001 completely tested", "audit the use case", "show me the coverage matrix", "do a traceability check", "what is still missing for UC-001", or "can I set the status to Tested". This is specification coverage, not line coverage from a coverage report. It reports only — it writes no code, no tests, and no files. When the user wants the gaps closed rather than listed, use /implement, /spring-boot-test, /vitest-test, or /playwright-test instead.

Creates versioned Flyway database migration scripts (V*.sql) with sequences, tables, constraints, and foreign keys from the entity model. Use when the user asks to "create a migration", "generate SQL scripts", "set up database tables", "write a Flyway migration", or mentions schema migration, DB migration, database versioning, or SQL migration files.

Implements use cases across a Spring Boot + Spring Data JPA backend (flat single-module or hexagonal/ports-and-adapters multi-module) and an Angular frontend wired to that API. Use when the user asks to "implement a use case", "build the API", "create a REST endpoint", "write the data access layer", "build the Angular page/component", or mentions Spring Boot, JPA/Hibernate entities, hexagonal architecture, ports and adapters, or an Angular frontend calling a Java backend.

Creates Vaadin Browserless server-side unit tests for Vaadin views covering navigation, component interactions, form validation, grid operations, and notifications. Use when the user asks to "write Browserless tests", "write Vaadin UI unit tests", "unit test a Vaadin view without a browser", "create view tests with the official Vaadin testing framework", or mentions Browserless testing, SpringBrowserlessTest, browserless-test-junit6, UI Unit Testing, or server-side Vaadin testing.

Audits an already-written use case (UC-XXX) or test case (TC-XXX) against its specification and reports a coverage matrix: which main success scenario steps, alternative flows, business rules, preconditions, and postconditions have code and tests behind them, which are still open, and which code or tests have drifted away from the specification. Use when the user asks to "check coverage", "run a coverage check", "is UC-001 fully implemented", "is UC-001 completely tested", "audit the use case", "show me the coverage matrix", "do a traceability check", "what is still missing for UC-001", or "can I set the status to Tested". This is specification coverage, not line coverage from a coverage report. It reports only — it writes no code, no tests, and no files. When the user wants the gaps closed rather than listed, use /implement, /implement-hilla, /browserless-test, /hilla-test, /karibu-test, or /playwright-test instead.

Creates versioned Flyway database migration scripts (V*.sql) with sequences, tables, constraints, and foreign keys from the entity model. Use when the user asks to "create a migration", "generate SQL scripts", "set up database tables", "write a Flyway migration", or mentions schema migration, DB migration, database versioning, or SQL migration files.

Generates bUnit component tests for Blazor components (.razor): renders the page, fills and submits its forms, asserts the rendered markup and the validation and error messages the use case states, and replaces the handlers and services it injects with test doubles, one test per scenario and business rule tagged with [UseCase]. Use when the user asks to "write bUnit tests", "test a Blazor component", "test the Razor page of UC-001", "create UI tests for Blazor", or mentions bUnit or xUnit rendering tests. Backend tests are /dotnet-test, browser tests /playwright-test.

Generates C# backend unit and integration tests for EF Core DbContext repositories, domain services, and vertical slice handlers using xUnit or NUnit against SQLite in-memory or Testcontainers databases, one test per scenario and business rule, each tagged with [UseCase]. Use when the user asks to "write backend tests for C#", "write .NET tests for this handler", "test ef core context", "write integration tests for dotnet", or mentions xUnit or NUnit handler tests. Blazor component tests are /bunit-test, browser tests /playwright-test.

Builds the data layer of a C# / .NET project from docs/entity_model.md with Entity Framework Core: generates the entity classes, writes IEntityTypeConfiguration Fluent API mappings (table names, decimal precision, enum conversions, foreign keys, unique indexes, binary columns), registers them in the DbContext, and adds a native C# migration with dotnet ef migrations add. Use when the user asks to "create an EF Core migration", "add ef migration", "update the schema with ef core", "map the entities in the DbContext", "generate a db migration for .net", or mentions EF Core, DbContext, Fluent API, or dotnet ef in a Blazor .NET project.

Inspects database health by analyzing slow queries, identifying bottlenecks, and checking Postgres performance indicators. Use when diagnosing database issues, checking slow queries, inspecting DB health, finding performance bottlenecks, or troubleshooting Supabase Postgres problems.

Creates Drizzle ORM schema definitions and generated SQL migrations for PostgreSQL from the entity model. Use when the user asks to "create a migration", "generate SQL", "set up database tables", "update the schema", or mentions Drizzle, drizzle-kit, pg-core, schema.ts, or database versioning for a NestJS project.

Implements use cases across a NestJS backend with Drizzle ORM over PostgreSQL and a Next.js App Router frontend wired to that API. Use when the user asks to "implement a use case", "build the API", "create a REST endpoint", "write the data access layer", "build the page", or mentions NestJS modules, controllers, providers, Drizzle queries, repositories, or a Next.js frontend calling a NestJS backend.

Creates NestJS backend tests with Vitest — unit specs with stubbed repositories, and Supertest end-to-end specs that boot the application against a real PostgreSQL database in Testcontainers. Use when the user asks to "write backend tests", "test the API", "write an e2e test", "test the endpoint", or mentions Supertest, Testcontainers, NestJS testing, or Vitest for a NestJS project.

Creates Postgres INSERT triggers that fire Edge Functions for document chunking and embedding generation. Configures the ingestion pipeline from raw document insert to vector storage. Use when building RAG ingestion, embed-on-insert pipelines, database-driven document ingestion, or automated embedding workflows.

Creates Postgres functions to validate storage path payloads and prevent directory traversal. Enforces tenant-safe file paths via storage RLS bucket policies. Use when configuring Supabase storage buckets, writing storage RLS policies, or implementing tenant-scoped file uploads.

Sets up Prometheus scrape jobs targeting the Supabase metrics endpoint and configures log drain pipelines. Establishes monitoring dashboards and alerting baselines. Use when configuring Supabase monitoring, setting up Prometheus metrics, implementing log drains, or establishing observability for production Supabase deployments.

Creates RLS policies enforcing tenant_id isolation on shared-schema tables. Verifies ALTER TABLE ENABLE ROW LEVEL SECURITY before policy creation. Requires tenant_id column and custom-access-token-hook JWT claims. Use when implementing multi-tenant data isolation, tenant-safe queries, shared schema RLS, or tenant_id policy creation.

Scaffolds a complete A2A agent specifically configured for Gemini Enterprise compatibility, including the JSON-RPC root path and a health check.

Implements the persistence layer of a use case (UC-XXX) with Spring Data JPA and Hibernate: @Entity classes mapped onto the Flyway schema (ddl-auto=validate, never create or update), Spring Data JpaRepository interfaces, derived and @Query queries, interface and record projections, attribute converters, fetch joins and entity graphs against N+1 selects, and @Version optimistic locking. Detects a flat single-module or a hexagonal multi-module backend; in the hexagonal case it writes the persistence adapter and the outbound port it implements. No Lombok. Use when the user asks to "write the JPA entities", "create the repository for UC-001", "implement the persistence layer", "map the table to an entity", "fix the N+1 query", or mentions Spring Data JPA, Hibernate, @Entity, JpaRepository, or a persistence adapter. Normally run by /use-case-implement as the Persistence layer; it can also be run directly.

Writes the persistence tests of a use case (UC-XXX) for Spring Data JPA: @DataJpaTest classes against a real database in a Testcontainers container (never H2 unless the project already tests on it), test data from Flyway test migrations, one UC<id><Name>RepositoryTest class per use case with @UseCase annotations. Tests only queries with logic of their own — filters, joins, projections, paging, fetch joins, custom @Query and Specification queries, attribute converters — and says so when the use case has none. In a hexagonal backend it tests through the persistence adapter in the adapter module. Use when the user asks to "test the repository", "write a @DataJpaTest", "test the JPA query of UC-001", "write persistence tests", or mentions DataJpaTest, repository tests, or Testcontainers for Spring Data JPA. /use-case-test runs it only to reconcile existing tests, for queries the integration layer cannot reach, or when the persistence layer is named; it can also be run directly.

Builds the persistence layer of a use case (UC-XXX) with jOOQ: one @Repository per aggregate with an injected DSLContext, type-safe queries against the classes jOOQ generates from the Flyway migrations, projections into Java records with Records.mapping, MULTISET for nested collections, paging and dynamic filters, optimistic locking when the entity has a version, and UC-XXX BR-YYY markers on the query conditions that enforce a business rule. Transactions stay with the service layer. Hands the repository method signatures and record types to the service layer. Normally run by /use-case-implement after the migration layer; can be run directly. Use when the user asks to "write the jOOQ repository", "implement the data access for UC-001", "add a jOOQ query", "map the result into a record", "set up jOOQ code generation", or mentions jOOQ, DSLContext, Records.mapping, multiset, or a repository in a project that combines layer plugins.

Writes the persistence layer tests of a use case (UC-XXX) for jOOQ repositories: integration tests against a real database (Testcontainers PostgreSQL or the project's database) with @SpringBootTest or @JooqTest, test data from Flyway test migrations, expected values from the specification and the test data, classes named UC<id><Name>RepositoryTest and every method annotated @UseCase. Tests only queries with logic of their own — filters, joins, projections, MULTISET, paging, optimistic locking — not what the integration layer's tests already cover. /use-case-test runs it only to reconcile existing tests, for queries the integration layer cannot reach, or when the persistence layer is named; can be run directly. Use when the user asks to "test the jOOQ repository", "write repository tests for UC-001", "test this query against the database", or mentions jOOQ repository tests, @JooqTest, DSLContext tests, or Testcontainers tests of the data access in a project that combines layer plugins.

Create or update a CONSTITUTION.md that defines project governance — establishes coding standards, quality gates, TDD policy, review requirements, and non-negotiable development principles with versioned amendment tracking. Use when defining project rules, setting up coding standards, establishing quality gates, configuring TDD requirements, or creating non-negotiable development principles.

Create a feature specification from a natural language description — generates user stories with Given/When/Then scenarios, functional requirements (FR-XXX), success criteria, and a quality checklist. Use when starting a new feature, writing a PRD, defining user stories, capturing acceptance criteria, or documenting requirements for a product idea.

Generate a technical design document from a feature spec — selects frameworks, defines data models, produces API contracts, and creates a dependency-ordered implementation strategy. Use when planning how to build a feature, writing a technical design doc, choosing libraries, defining database schemas, or setting up Tessl tiles for runtime library knowledge.

Demo skill two used to verify global vs project install behavior across agents

Creates PL/pgSQL RPC implementing Reciprocal Rank Fusion (score = 1/(k+rank)) to fuse semantic pgvector results with full-text tsvector results. Use when implementing hybrid search, RRF search, semantic plus keyword search, exact SKU and conceptual queries, or vector and full-text fusion.

Demo skill one used to verify global vs project install behavior across agents