• Never create without approval: Always present the full data model proposal and get explicit user confirmation before making any Dataverse changes.
• Use TaskCreate/TaskUpdate: Track all progress throughout all phases — create the todo list upfront with all phases before starting any work.
• Resilient execution: Refresh tokens proactively, check for existing tables before creating, and report failures without automated rollback.

1. Create todo list with all 8 phases (see Progress Tracking table)
2. Follow the prerequisite steps in

   ${CLAUDE_PLUGIN_ROOT}/references/dataverse-prerequisites.md

   to verify PAC CLI auth, acquire an Azure CLI token, and confirm API access. Store the environment URL as

   $envUrl

   .

$envUrl

1. Ask the user how they want to define the data model using the

   AskUserQuestion

   tool:
   Question: "How would you like to define the data model for your site?"

   Option	Description
   Upload an existing ER diagram	Provide an image (PNG/JPG) or Mermaid diagram of your existing data model
   Let the Data Model Architect figure it out	The Data Model Architect will analyze your site's source code and propose a data model automatically

2. Route to the appropriate path:

1. Ask the user to provide their ER diagram. Supported formats:
   • Image file (PNG, JPG) — Use the

     Read

     tool to view the image and extract tables, columns, relationships, and cardinalities from it
   • Mermaid syntax — The user can paste Mermaid ER diagram text directly in chat
   • Text description — A structured list of tables, columns, and relationships
2. Parse the diagram into the same structured format used by the data-model-architect agent:
   • Publisher prefix (ask the user, or retrieve from the environment via

     pac env who

     )
   • Table definitions:

     logicalName

     ,

     displayName

     ,

     status

     (new/modified/reused),

     columns

     ,

     relationships

   • Column definitions:

     logicalName

     ,

     displayName

     ,

     type

     ,

     required

   • Relationship definitions: type (1:N or M:N), referenced/referencing tables
3. Query existing Dataverse tables (same as Phase 3 would) to mark each table as

   new

   ,

   modified

   , or

   reused

   .
4. Generate a Mermaid ER diagram from the parsed data (if the user provided an image or text) for visual confirmation.
5. Proceed directly to Phase 4: Review Proposal with the parsed data model.

1. Use the

   Task

   tool to spawn the

   data-model-architect

   agent. This agent autonomously:
   • Analyzes the site's source code to infer data requirements
   • Queries existing Dataverse tables via OData GET requests
   • Identifies reuse opportunities (reuse, extend, or create new)
   • Proposes a complete data model with an ER diagram
2. Spawn the agent:

   Task tool:
     subagent_type: general-purpose
     prompt: |
       You are the data-model-architect agent. Follow the instructions in
       the agent definition file at:
       ${CLAUDE_PLUGIN_ROOT}/agents/data-model-architect.md
   
       Analyze the current project and Dataverse environment, then propose
       a complete data model. Return:
       1. Publisher prefix
       2. Table definitions (logicalName, displayName, status, columns, relationships)
       3. Mermaid ER diagram

3. Wait for the agent to return its structured proposal before proceeding.

• Publisher prefix
• All proposed tables with columns (logical names + display names)
• Relationship descriptions
• Mermaid ER diagram
• Which tables are new vs. modified vs. reused

AskUserQuestion

• If "Approve and create tables (Recommended)": Proceed to Phase 5
• If "Request changes": Ask what they want changed, modify the proposal, and re-present for approval
• If "Cancel": Stop the skill

new

node "${CLAUDE_PLUGIN_ROOT}/scripts/dataverse-request.js" <envUrl> GET "api/data/v9.2/EntityDefinitions(LogicalName='<table_logical_name>')"

• If 404: Table does not exist, proceed to create it
• If 200: Table already exists — skip creation, warn the user

modified

• Tables to create (new tables that don't exist yet)
• Columns to add (new columns on existing/modified tables)
• Relationships to create
• Tables/columns to skip (already exist)

Reference:

${CLAUDE_PLUGIN_ROOT}/references/skill-tracking-reference.md

--skillName "SetupDatamodel"

cr123_project

contact

cr123_task

• Total tables created/modified/reused/failed
• Total columns created/skipped/failed
• Total relationships created/failed
• Any errors encountered with details
• Location of the manifest file (

  .datamodel-manifest.json

  )

• Review created tables in the Power Pages maker portal
• Populate tables with sample data for testing:

  /add-sample-data

• Integrate tables with your site's frontend via Web API:

  /integrate-webapi

• If the site is not yet built:

  /create-site

• If the site is ready to deploy:

  /deploy-site

• Use TaskCreate/TaskUpdate to track progress at every phase
• Ask for user confirmation at key decision points (see list below)
• Token refresh is automatic — the

  dataverse-request.js

  script handles 401 token refresh and 429/5xx retry internally
• Report failures without rollback — track each creation attempt and continue with remaining items on failure

1. After Phase 2: Data model source chosen (upload vs. AI)
2. After Phase 4: Approve data model proposal before any creation
3. After Phase 5: Acknowledge any skipped items before proceeding
4. After Phase 8: Review summary and choose next steps