semantic-model-authoring

Create, edit, deploy, and optimize Power BI semantic models across Desktop, PBIP, and Fabric.

Updated Jul 14, 2026
One-click install
npx skills add https://github.com/9vantage/skills-for-fabric-clone --skill semantic-model-authoring-9vantage
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: semantic-model-authoring
Source: https://github.com/9vantage/skills-for-fabric-clone/tree/main/plugins/powerbi-authoring/skills/semantic-model-authoring
Command: npx skills add https://github.com/9vantage/skills-for-fabric-clone --skill semantic-model-authoring-9vantage

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Building and maintaining Power BI semantic models requires juggling TMDL files, DAX code, PBIP project structures, and Fabric REST APIs, which is error-prone and slow when done manually. This Skill guides an AI assistant through the full authoring lifecycle so models are created, modified, deployed, and optimized correctly. ## Core Features & Use Cases - Model Creation & Editing: Create new semantic models (Import, DirectQuery, Direct Lake) with star schema design, or edit existing measures, tables, columns, and relationships via the powerbi-modeling-mcp MCP server or direct TMDL edits. - Deployment & Management: Deploy models to Fabric workspaces via REST APIs, refresh models, configure data sources and permissions, and bind models to Fabric connections. - DAX Performance Optimization: Diagnose slow queries with trace analysis and apply a tiered catalog of optimization patterns while validating semantic equivalence. - Use Case: Ask the assistant to add base measures for all aggregable columns in the Sales model of the Marketing workspace; it resolves the workspace and model IDs, connects via MCP, applies the changes following modeling guidelines, and validates the results. ## Quick Start Ask the assistant to create a new Direct Lake semantic model from your lakehouse tables and deploy it to your Fabric workspace.

Frequently Asked Questions about semantic-model-authoring

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

FAQPage Schema
How do I create a new Power BI semantic model with this skill?

Describe the model purpose, data source, and key business entities, and the skill designs a star schema, picks a storage mode (Direct Lake for OneLake, Import otherwise), builds tables and measures, then deploys to Fabric or exports to a PBIP project.

How do I edit measures and relationships in an existing semantic model?

The skill connects to the model via the powerbi-modeling-mcp MCP server when available, or edits TMDL files directly in a PBIP folder. Changes follow modeling and DAX guidelines and are validated with test queries after saving.

Can I deploy a PBIP semantic model to a Fabric workspace?

Yes. PBIP or TMDL files on disk are deployed through the Fabric REST API using createItemWithDefinition or updateDefinition via az rest. The skill explicitly avoids routing file-based deployments through MCP.

Does the skill support Direct Lake semantic models?

Yes. It loads dedicated Direct Lake guidelines when the model connects to OneLake, creates shared expressions with the AzureStorage.DataLake connector, and uses EntityPartitionSource mappings to lakehouse tables.

Why can't the skill manage RLS role membership?

Managing RLS/OLS role membership is explicitly out of scope by design. The skill refuses to add or remove users from security roles and redirects you to the Power BI portal for those operations.

How does the skill optimize slow DAX queries?

It captures server timing traces, establishes a measured baseline, then applies tiered optimization patterns from a decision guide while checking semantic equivalence after each change. Query structure or model changes require your explicit approval.