ai-unified-process/aiup-core

Creates or updates BPMN 2.0 business process models (docs/processes/BP-XXX-*.bpmn) from the requirements catalog and the use case diagram: one pool per process, one lane per actor, every activity one use case, gateways for the decisions between them, and a diagram layout a modeler such as bpmn.io can open. Every process gets a BP-XXX id for communication and traceability; run it with that id (e.g. /business-process BP-001) to update one process. Use when the user asks to "model the business process", "create a BPMN", "draw the process", "connect the use cases into a process", "update BP-001", or mentions a business process, process model, BPMN, swimlanes, or a .bpmn file. Also trigger when a review or the use case skills report a summary use case whose parts hand over to another role, wait for an event or deadline, or run in parallel — that flow is a business process. The resulting model is what /test-case BP-XXX derives end-to-end test cases from.

Creates entity model documents with Mermaid.js ER diagrams and attribute tables defining entities, relationships, data types, and validation rules. Use when the user asks to "create an entity model", "design a data model", "draw an ERD", "define database schema", "model entities", or mentions entity-relationship diagram, ER diagram, database design, or data modeling. Also trigger whenever the task is to produce, write, or design an entity model or data model document (e.g. docs/entity_model.md) from a requirements catalog — including phrasings like "data model design", "the team needs an entity model before development", or a request to document entities with attributes, data types, precision, and validation or cross-attribute constraints.

Gathers, organizes, and documents software requirements into structured catalogs with functional requirements (user stories), non-functional requirements (measurable quality attributes), and constraints. Use when the user asks to "write requirements", "create a PRD", "gather requirements", "document feature specs", "write user stories", "define NFRs", "list constraints", "write a glossary", "define domain terms", or mentions requirements catalog, requirements analysis, product requirements document, feature specification, or glossary.

Reverse-engineers an existing software project into AI Unified Process artifacts: a PlantUML use case diagram, per-use-case specification documents, and an entity model with a Mermaid ER diagram. Use when the user asks to "reverse engineer this codebase", "extract use cases from existing code", "document the system we already have", "generate use case specs from controllers", "derive an entity model from the database", "create AI Unified Process artifacts from a legacy project", or mentions reverse engineering, legacy documentation, or onboarding an inherited codebase. Trigger this skill whenever a user wants to produce use cases, an ER diagram, or a use case diagram from code that already exists rather than from a fresh vision document — even if they don't say "reverse engineer" explicitly.

Reviews the specification artifacts in docs/ (requirements, use case diagram, use case specifications, test cases, BPMN process models, entity model, glossary) against each other in two parts: a deterministic lint that can block a build (missing specifications, duplicate or unresolved ids, uncovered FRs, unmapped BPMN activities, actor mismatches, weak words, glossary synonyms) and an advisory semantic review (contradicting or duplicated rules, wrong level of detail, missing alternative flows, untestable rules, ambiguity, actors, NFRs and constraints, entity model consistency), plus a traceability matrix and requirement coverage on request, also as HTML. Use when the user asks to "review the specs", "lint the use cases", "find contradictions", "is this use case ready", "show the traceability matrix", "which use cases realize FR-014", "are all requirements covered", "HTML report", or wants a spec quality gate in CI. It reports only, never edits a specification; checking code against specs is /coverage-check.

Creates end-to-end test case documents (TC-*.md) that chain several use cases into one user journey with a step-by-step Flow table, concrete test data, and final validations. Use when the user asks to "create a test case", "write a test case", "define an end-to-end scenario", "document a user journey for testing", "chain use cases into a test", or mentions a test case document, TC-001, journey test, or end-to-end test scenario. Also trigger whenever the user lists several use case IDs (UC-*) and wants one test definition spanning them, or wants test cases derived from a business process (BP-001), a BPMN process model, or a .bpmn file (one test case per path through the process) — the resulting TC-* document is what e2e test skills (e.g. /playwright-test TC-001) automate.

Creates or updates PlantUML use case diagrams defining actors, use cases, and their relationships from requirements. Use when the user asks to "create a use case diagram", "draw a UML diagram", "map actors to use cases", "generate a .puml file", or mentions PlantUML, use case overview, actor diagram, or system use cases.

Creates detailed use case specification documents with actors, preconditions, main success scenarios, alternative flows, postconditions, and business rules. Use when the user asks to "write a use case", "specify a use case", "document system behavior", "define scenarios", "write a functional spec", or mentions use case specification, acceptance criteria, or user scenarios. Also trigger whenever the task is to write use case specification documents for the use cases in a use case diagram (e.g. docs/use_cases.puml) — including phrasings like "detailed use case specifications before writing any code", "one file per use case", or a request to cover the happy path, alternative flows, postconditions, and business rules for each use case.