create-data-model

Generate Mermaid ERDs and JSON Schema from project architecture documents.

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/bbolek-ap/new-ai-native --skill create-data-model-bbolek-ap
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-data-model
Source: https://github.com/bbolek-ap/new-ai-native/tree/main/.claude/skills/create-data-model
Command: npx skills add https://github.com/bbolek-ap/new-ai-native --skill create-data-model-bbolek-ap

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Produce a conceptual data model that captures the project's core entities, their relationships, and ownership boundaries. The model serves two audiences: Mermaid ERDs for human designers and a JSON Schema for AI tool consumption.

Core Features & Use Cases

  • Generate Mermaid ERDs that visualize entities and relationships.
  • Produce a JSON Schema suitable for integration tools and UI generation.
  • Support ADRs, integration assessments, and external system models to keep the data model aligned with architecture.

Quick Start

Provide the required project context (proposals, architecture, ADRs) to generate or update the data model.

Frequently Asked Questions about create-data-model

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a data model from architecture documents and ADRs?

To generate a data model, provide architecture documents, proposals, and ADRs with data-impact tags as context. The tool identifies domain entities and relationships, then outputs Mermaid ERDs and JSON Schema files saved under .project/data-model/.

What is the best way to create a JSON Schema for integration tools from project context?

Creating a JSON Schema for integration tools requires feeding proposals and integration assessments into a data modeling workflow. This process extracts domain entities and ownership boundaries, producing a machine-readable JSON Schema suitable for AI design consumption.

How do I visualize domain entities and relationships for human designers?

Visualizing domain entities and relationships is achieved by generating Mermaid ERDs. The data modeling workflow parses project context to map entities and ownership boundaries, outputting Mermaid diagrams alongside a machine-readable JSON Schema.

Do I need external system models and integration assessments to update a data model?

External system models and integration assessments are required to accurately define or update entities and their ownership. Providing sufficient context from these sources ensures the generated JSON Schema and Mermaid ERDs align with architecture.

When do I need to update my project's JSON Schema and Mermaid ERDs?

You need to update your JSON Schema and Mermaid ERDs when architecture changes occur or new ADRs with data-impact tags are introduced. This keeps the conceptual data model aligned with the latest project domain entities and relationships.