Power BI Semantic Modeling
Guide users in building optimized, well-documented Power BI semantic models following Microsoft best practices.
When to Use This Skill
Use this skill when users ask about:
- Creating or optimizing Power BI semantic models
- Designing star schemas (dimension/fact tables)
- Writing DAX measures or calculated columns
- Configuring table relationships (cardinality, cross-filter)
- Implementing row-level security (RLS)
- Naming conventions for tables, columns, measures
- Adding descriptions and documentation to models
- Performance tuning and optimization
- Calculation groups and field parameters
- Model validation and best practice checks
Trigger phrases: "create a measure", "add relationship", "star schema", "optimize model", "DAX formula", "RLS", "naming convention", "model documentation", "cardinality", "cross-filter"
Prerequisites
Required Tools
- Power BI Modeling MCP Server: Required for connecting to and modifying semantic models
- Enables: connection_operations, table_operations, measure_operations, relationship_operations, etc.
- Must be configured and running to interact with models
Optional Dependencies
- Microsoft Learn MCP Server: Recommended for researching latest best practices
- Enables: microsoft_docs_search, microsoft_docs_fetch
- Use for complex scenarios, new features, and official documentation
Workflow
1. Connect and Analyze First
Before providing any modeling guidance, always examine the current model state:
1. List connections: connection_operations(operation: "ListConnections")
2. If no connection, check for local instances: connection_operations(operation: "ListLocalInstances")
3. Connect to the model (Desktop or Fabric)
4. Get model overview: model_operations(operation: "Get")
5. List tables: table_operations(operation: "List")
6. List relationships: relationship_operations(operation: "List")
7. List measures: measure_operations(operation: "List")
2. Evaluate Model Health
After connecting, assess the model against best practices:
- Star Schema: Are tables properly classified as dimension or fact?
- Relationships: Correct cardinality? Minimal bidirectional filters?
- Naming: Human-readable, consistent naming conventions?
- Documentation: Do tables, columns, measures have descriptions?
- Measures: Explicit measures for key calculations?
- Hidden Fields: Are technical columns hidden from report view?
3. Provide Targeted Guidance
Based on analysis, guide improvements using references:
- Star schema design: See STAR-SCHEMA.md
- Relationship configuration: See RELATIONSHIPS.md
- DAX measures and naming: See MEASURES-DAX.md
- Performance optimization: See PERFORMANCE.md
- Row-level security: See RLS.md
Quick Reference: Model Quality Checklist
| Area |
Best Practice |
| Tables |
Clear dimension vs fact classification |
| Naming |
Human-readable: Customer Name not CUST_NM |
| Descriptions |
All tables, columns, measures documented |
| Measures |
Explicit DAX measures for business metrics |
| Relationships |
One-to-many from dimension to fact |
| Cross-filter |
Single direction unless specifically needed |
| Hidden fields |
Hide technical keys, IDs from report view |
| Date table |
Dedicated marked date table |
MCP Tools Reference
Use these Power BI Modeling MCP operations:
| Operation Category |
Key Operations |
connection_operations |
Connect, ListConnections, ListLocalInstances, ConnectFabric |
model_operations |
Get, GetStats, ExportTMDL |
table_operations |
List, Get, Create, Update, GetSchema |
column_operations |
List, Get, Create, Update (descriptions, hidden, format) |
measure_operations |
List, Get, Create, Update, Move |
relationship_operations |
List, Get, Create, Update, Activate, Deactivate |
dax_query_operations |
Execute, Validate |
calculation_group_operations |
List, Create, Update |
security_role_operations |
List, Create, Update, GetEffectivePermissions |
Common Tasks
Add Measure with Description
measure_operations(
operation: "Create",
definitions: [{
name: "Total Sales",
tableName: "Sales",
expression: "SUM(Sales[Amount])",
formatString: "$#,##0",
description: "Sum of all sales amounts"
}]
)
Update Column Description
column_operations(
operation: "Update",
definitions: [{
tableName: "Customer",
name: "CustomerKey",
description: "Unique identifier for customer dimension",
isHidden: true
}]
)
Create Relationship
relationship_operations(
operation: "Create",
definitions: [{
fromTable: "Sales",
fromColumn: "CustomerKey",
toTable: "Customer",
toColumn: "CustomerKey",
crossFilteringBehavior: "OneDirection"
}]
)
When to Use Microsoft Learn MCP
Research current best practices using microsoft_docs_search for:
- Latest DAX function documentation
- New Power BI features and capabilities
- Complex modeling scenarios (SCD Type 2, many-to-many)
- Performance optimization techniques
- Security implementation patterns
1---2name: powerbi-modeling3description: Power BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimizing model performance. Triggers on queries about DAX calculations, table relationships, dimension/fact table design, naming conventions, model documentation, cardinality, cross-filter direction, calculation groups, and data model best practices. Always connects to the active model first using power-bi-modeling MCP tools to understand the data structure before providing guidance.4---5
6# Power BI Semantic Modeling
7
8Guide users in building optimized, well-documented Power BI semantic models following Microsoft best practices.
9
10## When to Use This Skill
11
12Use this skill when users ask about:
13- Creating or optimizing Power BI semantic models
14- Designing star schemas (dimension/fact tables)
15- Writing DAX measures or calculated columns
16- Configuring table relationships (cardinality, cross-filter)
17- Implementing row-level security (RLS)
18- Naming conventions for tables, columns, measures
19- Adding descriptions and documentation to models
20- Performance tuning and optimization
21- Calculation groups and field parameters
22- Model validation and best practice checks
23
24**Trigger phrases:** "create a measure", "add relationship", "star schema", "optimize model", "DAX formula", "RLS", "naming convention", "model documentation", "cardinality", "cross-filter"
25
26## Prerequisites
27
28### Required Tools
29- **Power BI Modeling MCP Server**: Required for connecting to and modifying semantic models
30 - Enables: connection_operations, table_operations, measure_operations, relationship_operations, etc.
31 - Must be configured and running to interact with models
32
33### Optional Dependencies
34- **Microsoft Learn MCP Server**: Recommended for researching latest best practices
35 - Enables: microsoft_docs_search, microsoft_docs_fetch
36 - Use for complex scenarios, new features, and official documentation
37
38## Workflow
39
40### 1. Connect and Analyze First
41
42Before providing any modeling guidance, always examine the current model state:
43
44```
451. List connections: connection_operations(operation: "ListConnections")
462. If no connection, check for local instances: connection_operations(operation: "ListLocalInstances")
473. Connect to the model (Desktop or Fabric)
484. Get model overview: model_operations(operation: "Get")
495. List tables: table_operations(operation: "List")
506. List relationships: relationship_operations(operation: "List")
517. List measures: measure_operations(operation: "List")
52```
53
54### 2. Evaluate Model Health
55
56After connecting, assess the model against best practices:
57
58- **Star Schema**: Are tables properly classified as dimension or fact?
59- **Relationships**: Correct cardinality? Minimal bidirectional filters?
60- **Naming**: Human-readable, consistent naming conventions?
61- **Documentation**: Do tables, columns, measures have descriptions?
62- **Measures**: Explicit measures for key calculations?
63- **Hidden Fields**: Are technical columns hidden from report view?
64
65### 3. Provide Targeted Guidance
66
67Based on analysis, guide improvements using references:
68- Star schema design: See [STAR-SCHEMA.md](references/STAR-SCHEMA.md)
69- Relationship configuration: See [RELATIONSHIPS.md](references/RELATIONSHIPS.md)
70- DAX measures and naming: See [MEASURES-DAX.md](references/MEASURES-DAX.md)
71- Performance optimization: See [PERFORMANCE.md](references/PERFORMANCE.md)
72- Row-level security: See [RLS.md](references/RLS.md)
73
74## Quick Reference: Model Quality Checklist
75
76| Area | Best Practice |
77|------|--------------|
78| Tables | Clear dimension vs fact classification |
79| Naming | Human-readable: `Customer Name` not `CUST_NM` |
80| Descriptions | All tables, columns, measures documented |
81| Measures | Explicit DAX measures for business metrics |
82| Relationships | One-to-many from dimension to fact |
83| Cross-filter | Single direction unless specifically needed |
84| Hidden fields | Hide technical keys, IDs from report view |
85| Date table | Dedicated marked date table |
86
87## MCP Tools Reference
88
89Use these Power BI Modeling MCP operations:
90
91| Operation Category | Key Operations |
92|-------------------|----------------|
93| `connection_operations` | Connect, ListConnections, ListLocalInstances, ConnectFabric |
94| `model_operations` | Get, GetStats, ExportTMDL |
95| `table_operations` | List, Get, Create, Update, GetSchema |
96| `column_operations` | List, Get, Create, Update (descriptions, hidden, format) |
97| `measure_operations` | List, Get, Create, Update, Move |
98| `relationship_operations` | List, Get, Create, Update, Activate, Deactivate |
99| `dax_query_operations` | Execute, Validate |
100| `calculation_group_operations` | List, Create, Update |
101| `security_role_operations` | List, Create, Update, GetEffectivePermissions |
102
103## Common Tasks
104
105### Add Measure with Description
106```
107measure_operations(
108 operation: "Create",
109 definitions: [{
110 name: "Total Sales",
111 tableName: "Sales",
112 expression: "SUM(Sales[Amount])",
113 formatString: "$#,##0",
114 description: "Sum of all sales amounts"
115 }]
116)
117```
118
119### Update Column Description
120```
121column_operations(
122 operation: "Update",
123 definitions: [{
124 tableName: "Customer",
125 name: "CustomerKey",
126 description: "Unique identifier for customer dimension",
127 isHidden: true
128 }]
129)
130```
131
132### Create Relationship
133```
134relationship_operations(
135 operation: "Create",
136 definitions: [{
137 fromTable: "Sales",
138 fromColumn: "CustomerKey",
139 toTable: "Customer",
140 toColumn: "CustomerKey",
141 crossFilteringBehavior: "OneDirection"
142 }]
143)
144```
145
146## When to Use Microsoft Learn MCP
147
148Research current best practices using `microsoft_docs_search` for:
149- Latest DAX function documentation
150- New Power BI features and capabilities
151- Complex modeling scenarios (SCD Type 2, many-to-many)
152- Performance optimization techniques
153- Security implementation patterns
gabrielmoreira