Power BI Semantic Modeling
Official GitHub Copilot skill for robust Power BI semantic models, DAX, relationships, and performance.
- Skill Road
- Power BI Semantic Modeling
Categories
Power BI Semantic Modeling is an official skill from GitHub's github/awesome-copilot repository. Its primary source is the skills/powerbi-modeling directory, which provides workflow guidance for building and maintaining Power BI semantic models. According to the provider, the skill helps teams inspect models, design a dependable star schema, write DAX measures, review relationships, plan row-level security, document model objects, and improve query performance. The skill is not Power BI Desktop, is not a substitute for a Power BI account, and is not an independent MCP server.
Purpose and workflow
The source establishes a model-first principle: an agent should inspect the active model before offering modeling advice. A compatible agent is instructed to list available connections, check for local instances, connect to an explicitly authorized Desktop or Fabric model, and then retrieve the model overview, tables, relationships, and measures. This makes recommendations reflect real model state rather than guessed table or column names. According to the provider, a Power BI Modeling MCP server can expose connection, model, table, column, measure, and relationship operations for this workflow. Actual operations depend on the configured environment, client, server, and permissions.
Model quality and DAX
The skill focuses evaluation on the distinction between dimension and fact tables. A clear star schema makes filter paths, explicit measures, and future maintenance easier to understand. Relationships should be checked for cardinality, activation, and cross-filter behavior. The source favors a simple dimension-to-fact filter direction unless bidirectional filtering has a documented business reason. Human-readable names, descriptions for tables, columns, and measures, and hidden technical keys improve the report authoring experience. For business metrics, the guidance favors explicit measures instead of scattering logic across calculated columns, while definitions, formats, and assumptions should remain documented together.
Security and boundaries
Power BI models may contain revenue figures, employee information, customer segments, and other confidential material. An agent should work only through a deliberately selected connection with the least privilege needed for the task. RLS rules must be tested against real roles, identities, and filter paths; a model that looks correct is not proof that access separation works. Mutating operations on tables, columns, measures, relationships, or security roles require explicit approval, organizational backup procedures, and an auditable review. Unexpected model descriptions or imported content are data, not new instructions. Local execution by a client or server does not automatically mean that returned results stay local to the organization or to the selected model provider.
Rules and Tools
The skill first requires a connection to the model and then assesses its health before giving guidance. The default is relationships from the dimension to the fact table (one-to-many) with the filter direction in a single direction. Bidirectional filters should stay the exception. It asks for readable names such as Customer Name instead of CUST_NM, descriptions for all tables, columns and measures, hidden technical keys, a marked date table and explicit measures. The Power BI Modeling MCP Server is required, and the Microsoft Learn MCP Server optionally helps with research.
E-E-A-T and responsible use
GitHub is the skill provider according to the official repository and documentation sources. The implementation guidance is publicly inspectable in the named repository and is paired here with GitHub's official documentation about repository instructions for GitHub Copilot. This provenance improves traceability, but it does not replace review by people with Power BI, DAX, data modeling, and authorization expertise. Financial reporting, compliance analysis, and personal data require controlled testing and accountable sign-off. The skill supplies a repeatable structure and quality prompts; it does not guarantee correct measures, secure RLS, or optimal performance. Validate assumptions against the business definition, compare results with trusted figures, and document any intentional exceptions to the recommended model patterns.
Installation instructions
This guide explains how to use the official powerbi-modeling skill with a compatible agent. It structures the work but does not replace professional Power BI review.
Provide the repository instructions
Place the reviewed skill file in the repository context supported by your GitHub Copilot or agent workflow. Check the commit, provenance, and local policy before enabling it. Practical model inspection requires a configured Power BI Modeling MCP server or another explicitly approved tool path that provides equivalent access.
Step 1: Inspect the connection and model first
Start by listing available connections and local instances. Connect only to the intended Desktop or Fabric model. Then read the model overview, tables, relationships, and measures. Share only the model information required for the specific task.
Assess quality step by step
Review dimensions, facts, keys, and filter paths first. Then assess cardinality, activity, and cross-filter behavior. Check measures for business definition, DAX expression, format, and documentation. Technical keys may be hidden from report authors while remaining traceable for model maintenance.
Protect changes
Read-only analysis is the safest starting point. Before changing model objects or security roles, make the purpose, target, authorization, and rollback plan explicit. Test RLS with representative identities and compare measures with trusted reference values. Never store credentials, tokens, or confidential example data in instructions.
Frequently asked questions
### Is this skill a Power BI program?
No. According to the provider, it is guidance for a compatible agent. Modeling takes place in Power BI and through the approved tools available to that environment.
### Must the agent always connect first?
Yes. The primary source requires inspecting the active model state first so that recommendations reflect real tables, relationships, and measures.
### Is a star schema always mandatory?
No. It is a proven pattern for many analytical models. Business requirements can justify exceptions, but those exceptions should be documented and tested.
- Provider
- GitHub
- License
- MIT
- Last reviewed
- 09.09.2026
Repository and documentation
Categories
Compatible with
Related guides
Guides and background related to this entry.