power-bi-semantic-model

Stars4

Forks1

UpdatedJune 29, 2026 at 06:37

Design and build Power BI semantic models using star schema principles and the PowerBI Modeling MCP tools. Use this skill whenever the user wants to build a semantic model, create a data model, design a star schema, add tables or columns, create or modify relationships, configure storage modes (Import, DirectQuery, DirectLake, Composite), implement RLS (Row-Level Security), optimize model performance, or explore existing data sources for modeling. Triggers include: "build semantic model", "create data model", "star schema", "add table", "create relationship", "storage mode", "DirectLake", "composite model", "RLS", "optimize model", "model review", "explore data", "connect to gold layer", "extend model", "add dimension", "add fact table". Do NOT use for DAX measure creation (use power-bi-dax-development) or report generation (use power-bi-report-authoring).

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

datacoolie

datacoolie/powerbi-skills

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

21 files

SKILL.md

readonly

More from this repository

same repository

power-bi-report-authoring

datacoolie/powerbi-skills

Create and modify Power BI report files in PBIR/PBIP format using the `powerbi-report-author` and `powerbi-desktop` CLIs. Use when the user wants to: (1) implement an approved report spec or design brief, (2) add or edit pages, visuals, filters, slicers, bookmarks, themes, or formatting, (3) validate PBIR and verify rendering in Power BI Desktop. For open-ended visual design, use `power-bi-report-design` first. For end-to-end requirements and approval workflow, use `powerbi-report-planning` first. Triggers: "edit PBIR", "create Power BI report page", "add visual to PBIP", "format report visual", "validate Power BI report", "reload Desktop screenshot", "implement an approved PBIP report spec", "edit PBIR pages/visuals".

2026-07-104

power-bi-business-analysis

datacoolie/powerbi-skills

Analyze business requirements and define BI strategy for Power BI projects. Use this skill whenever the user wants to analyze business requirements, identify KPIs, define what insights a report should deliver, propose dashboard structure for a business domain, or gather requirements before building a Power BI report or semantic model. Triggers include: "analyze business requirements", "what KPIs should we track", "what insights can we get", "business domain analysis", "requirements gathering", "what should we measure", "what problems can we solve", "propose a dashboard", "what reports do we need", "BI strategy", "define metrics". Do NOT use for actual model building (use power-bi-semantic-model), DAX writing (use power-bi-dax-development), or report generation (use power-bi-report-authoring).

2026-06-294

power-bi-feedback-iteration

datacoolie/powerbi-skills

Reference kit for the feedback and iteration phase of a Power BI project. Provides classification taxonomy, prioritization matrix, intake template, change-impact scoping, post-change validation checklist, A/B variant testing workflow, formal UAT workflow, PBIP Git diff guide, changelog template, and a performance quick-check pointer. Use this skill whenever the user provides feedback on an existing Power BI report, requests iteration, wants to run UAT, or needs to document changes. Routing (feedback → correct downstream skill) is owned by the power-bi-developer agent, not by this skill. Triggers include: "user feedback", "improve report", "fix report", "iterate on the report", "report review", "rebuild report", "UAT", "changelog", "release notes", "users are complaining", "performance issue", "add/remove/modify a page/measure/visual on an existing report". Do NOT use this skill for brand-new projects (use power-bi-business-analysis to start from scratch).

2026-06-294

power-bi-performance-troubleshooting

datacoolie/powerbi-skills

Diagnose and resolve Power BI performance issues across models, DAX queries, report visuals, and data refresh. Use this skill whenever the user reports slow report loading, slow visual interactions, long refresh times, high memory usage, query timeouts, or capacity bottlenecks. Triggers include: "report is slow", "performance issue", "optimize report", "slow loading", "query timeout", "refresh takes too long", "high memory", "report performance", "visual is slow", "optimize model", "reduce model size", "aggregation table", "incremental refresh", "Performance Analyzer", "DAX Studio", "server timings", "capacity metrics". Do NOT use for initial model design (use power-bi-semantic-model), initial DAX development (use power-bi-dax-development), or report design decisions (use power-bi-report-design). This skill is for diagnosing and fixing performance problems in existing solutions.

2026-06-294

power-bi-report-design

datacoolie/powerbi-skills

Design Power BI report layouts, select chart types, plan page structures, choose themes, and apply data storytelling principles BEFORE generating PBIR JSON files. Use this skill whenever the user asks to design a report, plan a dashboard layout, choose visualizations, decide on chart types, apply storytelling to data, select a theme or color palette, plan page navigation, or structure report pages for a Power BI project. Also use when the user provides requirements and needs a report design spec before generation, or when reviewing/improving an existing report's visual design, layout, or UX. This skill produces a Design Spec — a structured plan of pages, visuals, layout, theme, and navigation — that feeds into the `power-bi-report-authoring` skill for JSON generation. Do NOT use for generating PBIR JSON files, validating report structure, or building the semantic model. For JSON generation, use `power-bi-report-authoring`.

2026-06-294

power-bi-dax-development

datacoolie/powerbi-skills

Develop, optimize, and validate DAX measures, calculation groups, visual calculations, field parameters, dynamic format strings, time intelligence, semi-additive logic, virtual relationships with TREATAS, DAX window functions, and user-defined functions for Power BI semantic models. Use for requests to write or optimize DAX, create measures, explain CALCULATE or evaluation context, build YTD/YoY/WTD logic, use RUNNINGSUM or MOVINGAVERAGE, rank with RANK/ROWNUMBER/OFFSET/INDEX/WINDOW, or apply advanced DAX patterns. Research Microsoft Learn MCP before recommending patterns.

2026-06-024

name

power-bi-semantic-model

description

Power BI Semantic Model Builder

Design and build Power BI semantic models following star schema best practices, using PowerBI Modeling MCP tools for all model operations.

Always search Microsoft Learn (microsoft-learn-mcp/microsoft_docs_search) for the latest modeling guidance before making design decisions.

Use PowerBI Modeling MCP (powerbi-modeling-mcp/*) for all model operations — exploring tables, creating relationships, configuring columns, testing queries. Read references/mcp-tool-reference.md for the complete tool mapping.

Quick Reference

Task	Approach	Reference
Explore existing model	`model_operations` → get model info, `table_operations` → list tables	—
Discover model metadata	INFO.VIEW.* queries for tables, columns, measures, relationships	`references/discovery-queries.md`
Connect to gold layer	`connection_operations` → configure data source	`references/connection-binding.md`
Design star schema	Run Star Schema Checklist	`references/star-schema-checklist.md`
Naming conventions	Tables, columns, measures, hierarchies naming rules	`references/naming-conventions.md`
Choose storage mode	Use Decision Matrix	`references/storage-mode-decision.md`
Direct Lake guide	Framing, guardrails, fallback, composite	`references/directlake-guide.md`
Build relationships	`relationship_operations` → create with proper cardinality	`references/advanced-relationships.md`
Optimize columns	`column_operations` → set data types, remove unused, hide keys	`references/vertipaq-optimization.md`
DAX coding standards	Variables, comments, query syntax, best practices	`references/dax-guidelines.md`
DAX performance	Optimization framework (21 patterns, tier 1–4)	`references/dax-perf-decision-guide.md` + `references/dax-perf-patterns.md`
Power Query / ETL	M language, query folding, transformations	`references/power-query-reference.md`
Implement RLS	Dynamic RLS, OLS, DirectLake RLS patterns	`references/rls-patterns.md`
TMDL / PBIP structure	Tables, columns, measures, relationships, roles	`references/tmdl-reference.md` + `references/pbip.md`
Deploy to workspace	Git integration, CI/CD, Fabric pipelines	`references/deployment-alm-guide.md`
Gateway & refresh	On-prem gateway, scheduled/incremental refresh	`references/gateway-refresh-guide.md`
Fabric REST API	TMDL CRUD, refresh, data sources, permissions	`references/semantic-model-rest-api.md`
Prepare for AI/Copilot	Descriptions, synonyms, AI instructions, verified answers	`references/semantic-model-ai-readiness.md`
Test the model	`dax_query_operations` → run EVALUATE queries	`references/discovery-queries.md`

Tool Selection Priority

When multiple tools can perform the same operation, follow this priority:

Tier 1 — MCP (powerbi-modeling-mcp): Use MCP tools for all authoring operations when connected to the target model. Fastest, least-error-prone, no file I/O.

Tier 2 — TMDL files + az rest: Use when MCP is unavailable. Edit TMDL files directly and deploy via Fabric REST API. See references/tmdl-reference.md for syntax and references/semantic-model-rest-api.md for API endpoints.

Tier 3 — Fallback: If neither MCP nor TMDL access is available, guide the user to save as PBIP or install MCP.

Must / Prefer / Avoid

MUST

Understand data source schema before designing the model
Follow star schema principles (references/star-schema-checklist.md)
Follow naming conventions (references/naming-conventions.md)
Follow tool selection priority (MCP → TMDL → Fallback)
Validate model with DAX queries after structural changes

PREFER

Star schema over flat/denormalized tables
Explicit measures over implicit aggregation
TMDL format for version-controlled model definitions
INT keys over TEXT keys for relationships

AVOID

Hardcoded workspace/item IDs — resolve dynamically
Reading TMDL files when MCP is connected (use MCP operations instead)
Calculated columns on fact tables (use measures or Power Query)
Auto Date/Time (use dedicated date dimension)

Workflow

Step 1: Explore Available Data

Before designing, understand what exists:

Exploration Checklist:
□ Use powerbi-modeling-mcp/model_operations to get current model state
□ Use powerbi-modeling-mcp/table_operations to list all tables and columns
□ Use powerbi-modeling-mcp/relationship_operations to see existing relationships
□ Identify which tables are facts (transactions, events) vs. dimensions (descriptive)
□ Check column data types and cardinality
□ Note any existing measures (powerbi-modeling-mcp/measure_operations)
□ Check connection/partition info (powerbi-modeling-mcp/partition_operations)

If connecting to a gold layer or lakehouse:

Data Source Exploration:
□ Use fabric-notebook-mcp/list_artifacts to find available tables
□ Use fabric-notebook-mcp/get_lakehouse_detail for lakehouse schema
□ Use fabric-notebook-mcp/preview_lakehouse_table to inspect data
□ Use fabric-notebook-mcp/get_table_column_stats for column statistics
□ Use ms-mssql.mssql tools to query SQL-based gold layers

Step 2: Design Star Schema

Classify tables then validate with references/star-schema-checklist.md:

Type	Role	Examples
Fact	Measurable events, FK to dims, numeric aggregates	Sales, Orders, Production
Dimension	Descriptive context, surrogate key, filtering/grouping	Date, Product, Customer
Bridge	M:N link, key columns only	CustomerProduct, EmployeeProject
Measure Table	No data rows, organizes DAX measures	_Measures, _KPIs

Full design rules and validation → references/star-schema-checklist.md

Step 3: Configure Storage Modes

Scenario	Recommended Mode
Historical data, < 1GB	Import
Historical data, > 1GB with Fabric	Direct Lake
Direct Lake + external reference data	Composite (DL + Import)
Real-time operational data	DirectQuery
Mix of real-time + historical	Composite (DQ + Import)
Dimension tables in composite model	Dual
Aggregation tables	Import

Full decision matrix → references/storage-mode-decision.md

Step 4: Build Relationships

Use powerbi-modeling-mcp/relationship_operations:

□ Cardinality: One-to-Many (dimension → fact) is standard
□ Cross-filter: Single direction (dimension filters fact) is default
□ Active: Only one active relationship between any two tables
□ Inactive: Use USERELATIONSHIP() for role-playing dimensions
□ Referential integrity: Enable for Import mode (performance boost)

Advanced patterns (M:M, weak, role-playing, ambiguity) → references/advanced-relationships.md

Step 5: Optimize the Model

Prioritize in this order (biggest compression impact first):

Remove unused columns — hidden columns still consume memory
Reduce cardinality — bin dates, round decimals, group rare values
Use INT keys over TEXT — value encoding vs hash encoding
No calculated columns on fact tables — use measures or Power Query

Model-level:

Dedicated date dimension (disable Auto Date/Time)
Remove auto-generated LocalDateTable_* tables
Aggregation tables for >100M row facts
Incremental refresh for growing tables
Target < 1GB model size (Import mode)

Full optimization guide → references/vertipaq-optimization.md

Step 6: Implement Security

RLS Implementation Steps:
1. Define roles → powerbi-modeling-mcp/security_role_operations
2. Write DAX filter expressions per role
3. Test with dax_query_operations (EVALUATE with role context)

All patterns (static, dynamic, hierarchy, time-based, OLS) → references/rls-patterns.md

Step 7: Validate the Model

Use powerbi-modeling-mcp/dax_query_operations to validate:

EVALUATE INFO.VIEW.RELATIONSHIPS() — verify relationship structure
Orphaned records check — ISBLANK(RELATED(...)) pattern
Row count spot-check — COUNTROWS() per table
RLS propagation test — CALCULATETABLE with role context

Full discovery query catalog → references/discovery-queries.md

Step 8: Prepare for AI (Copilot Readiness)

Optimize the model for Power BI Copilot and Fabric Data Agent:

Prep for AI Checklist:
□ Use descriptive, human-readable names for all tables, columns, measures
□ Add descriptions to tables, columns, and measures (Copilot uses metadata)
□ Hide relationship key columns and unused technical fields
□ Avoid duplicate field names across tables (e.g., "Name" in Customer vs Store)
□ Remove unused objects — fewer objects = less AI ambiguity
□ Configure AI Data Schema (Prep data for AI → Simplify data schema)
□ Add AI Instructions (business context, terminology, domain logic)
□ Set up Verified Answers for common questions
□ Mark model as "Prepped for AI" in semantic model settings
□ Test with Copilot pane → validate responses against expected answers

Copilot folder structure in PBIP → references/tmdl-reference.md §Copilot Folder Full AI readiness guide → references/semantic-model-ai-readiness.md

Common Modeling Scenarios

Slowly Changing Dimensions (SCD)

Type 1 (overwrite): Update dimension row directly. No special modeling.

Type 2 (history): Surrogate key per version + ValidFrom/ValidTo/IsCurrent. Relationship uses surrogate key (not natural key).

Date Table Requirements

Every model MUST have a proper date table — time intelligence fails without it:

5 Non-Negotiable Requirements:
1. Contiguous dates — one row per calendar date, NO gaps
2. Covers full range of all fact table dates (plus buffer year)
3. Date column is DATE type — no time component
4. DateKey column is INT (YYYYMMDD) — use as relationship key
5. Marked as Date Table via powerbi-modeling-mcp/calendar_operations

Note: Calendar-based time intelligence (preview, Sep 2025) relaxes the contiguity requirement for custom calendars (fiscal, 4-5-4, 13-month, lunar). Defines calendars on tables via Column Category mappings. New DAX functions: TOTALWTD, PREVIOUSWEEK, TOTALYTD('CalendarName'). Enable via Preview Features.

Full column requirements → references/star-schema-checklist.md (Section 3)

PBIP / TMDL File Structure

For complete PBIP folder layout, file schemas, and TMDL syntax → read references/tmdl-reference.md and references/pbip.md.

Related Skills

Skill	Relationship	When
`power-bi-business-analysis`	Upstream (Phase 1)	Requirements doc defines tables, data sources, and RLS needs
`power-bi-dax-development`	Downstream (Phase 3)	Model schema feeds into measure creation
`power-bi-performance-troubleshooting`	Cross-cutting	VertiPaq optimization, storage mode tuning, cardinality reduction
`power-bi-report-authoring`	Downstream (Phase 4b)	Model schema used during PBIR generation for queryState bindings