model-change

Orchestrates end-to-end semantic model changes in local PBIP projects via TMDL edits and validation.

6|3|Updated Jul 4, 2026
One-click install
npx skills add https://github.com/InsightfulAnalytics/PBI_Agentic_Dev --skill model-change-insightfulanalytics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-change
Source: https://github.com/InsightfulAnalytics/PBI_Agentic_Dev/tree/main/plugins/semantic-models/skills/model-change
Command: npx skills add https://github.com/InsightfulAnalytics/PBI_Agentic_Dev --skill model-change-insightfulanalytics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Changing a Power BI semantic model involves many failure points: authoring DAX against columns that don't exist, breaking Desktop's file-open with malformed TMDL, and shipping measures that return wrong numbers. This Skill sequences the full pipeline so each change is confirmed, authored, landed, validated offline, and proven against real data. ## Core Features & Use Cases - Five-step change pipeline: Confirm the model shape via a live Desktop connection, author with the right sub-skill (DAX, Power Query, relationships, date tables), land edits in TMDL, validate offline with TmdlSerializer, then prove correctness with DEFINE MEASURE queries against real data. - Desktop-breaking gotcha prevention: Enforces rules like requiring discourageImplicitMeasures for calculation groups and never leaving blank lines after /// description comments. - Use Case: When a user says "this measure is wrong" or "add a calculation group", the Skill coordinates connect-pbid, dax-standard, tmdl, and refresh-semantic-model so the .tmdl change opens cleanly in Desktop and returns correct numbers. ## Quick Start Change the model by adding a new measure to the Sales table in my local PBIP project and verify it returns the correct value.

Frequently Asked Questions about model-change

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

FAQPage Schema
How do I safely change a Power BI semantic model in a PBIP project?▼

Follow a five-step pipeline: confirm the field exists via a live Desktop connection, author the change with the matching skill, land it in TMDL with the Edit tool, validate offline with TmdlSerializer, then prove it against real data using DEFINE MEASURE queries.

How do I test a DAX measure fix without reopening Power BI Desktop?▼

Redefine the measure inside the query with DEFINE MEASURE and select the old and new versions side by side in one ROW(). This proves the fix against real data with zero risk to the model on disk.

Why does Power BI Desktop refuse to open my project after a TMDL edit?▼

Common causes are a calculation group without discourageImplicitMeasures in model.tmdl, or a blank line after a /// description comment, which produces an 'Unexpected line type: Empty!' parse error.

Can I validate TMDL files offline before opening Desktop?▼

Yes. Use TmdlSerializer::DeserializeDatabaseFromFolder via DAX Studio's Microsoft.AnalysisServices.Tabular.dll to parse the definition folder. Note that offline validation checks parse and bind only; it cannot run DAX queries.

What are the limitations of editing a model while Desktop is open?▼

Desktop keeps its own in-memory copy and re-serialises on save, which clobbers disk edits. Coordinate with the user first, and re-read files from disk at task start rather than trusting earlier conversation state.