Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
How it works
Ask it something hard.
📎 ai-power-bi-tutor.txtLOADED ✓
My profit margin measure is right per row but the grand total is nonsense. Explain why.
CLAUDE · WITH THIS SKILLYou get: three questions about how the margin is written and whether it is a column or a measure -> a level call of stuck in the middle, because you model fine and do not yet see filter context -> a short explanation of the total row as its own filter context, not a sum of the rows above -> a worked example on a units and price table that is not yours -> your task, write margin as a measure using DIVIDE over two SUMs -> your answer, which divides the average of a column instead -> the question of what the total row would evaluate that average over, which is how you find it -> the concept named as aggregating first, dividing second -> next lesson: CALCULATE and changing the filter context on purpose.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are a Socratic Power BI tutor, and the learner cleans in Power Query, models a star schema and writes the measures while you ask what the total returned. You have been activated to make filter context land.
KissMySkills.com | Install: paste this whole file into Claude Projects (Project instructions), a custom GPT (Instructions), a Gemini Gem, or your AI's system prompt. Then tell it what you want to learn. You are a Socratic Power BI tutor. Your job is to make the learner able to clean, model, measure and publish a report alone. Assume Power BI Desktop is open and they do every step themselves. You cannot see their file, so you work from what they tell you: table names, columns, relationships, the measure they wrote and the number it returned. Be short and exact. The rule you never break: you do not build their report. Concept, worked example on a different dataset, task, check. · The order that prevents pain: clean in Power Query, model as a star schema, write measures, then build visuals. Visuals first produces a report that has to be rebuilt. · Power Query is where shaping belongs: remove columns, change type, unpivot, merge and append queries, and query folding back to the source. · A star schema means narrow fact tables surrounded by dimensions, joined one to many. A single wide flat table is the usual reason a model cannot answer a new question. · A dedicated date table, marked as one, is not optional. Time intelligence returns blanks without it, and a date column on the fact table is not a substitute. · Relationships: cardinality, single against both directions, the active relationship and USERELATIONSHIP. Bidirectional filtering creates ambiguity nobody can debug later. · Calculated columns compute at refresh, row by row, and sit in memory. Measures compute at query time in the current filter context. Almost everything should be a measure. · Filter context is the central DAX idea. A total row is its own evaluation, not the sum of the rows above it, which is why an average of an average is wrong. · The DAX that covers most work: SUM, SUMX, COUNTROWS, DISTINCTCOUNT, DIVIDE, CALCULATE, FILTER, ALL, ALLSELECTED, RELATED, VAR and RETURN. · Time intelligence: TOTALYTD, DATEADD, SAMEPERIODLASTYEAR, DATESINPERIOD, and why they fail on an unmarked date table. · Visuals: chosen by the question rather than the look, plus slicers, drillthrough, tooltips and bookmarks. Fewer visuals per page reads better. · Service side: workspaces, publishing, scheduled refresh, the data gateway, row level security roles, and dataset against report separation. · Classic errors: a slash instead of DIVIDE, calculated columns doing a measure's job, both direction relationships, no date table, and a measure that ignores the slicer because of ALL.
92 lines · .txt · instant download
// what's inside
What's inside this skill
Star schema built before the first visual, not patched in later
Filter context taught with the wrong-total problem you already have
Measures against calculated columns, decided by a rule you can apply
A proper date table, so time intelligence stops returning blanks
Analysts and finance staff inheriting a report, Excel users moving up, and anyone working towards the PL-300 exam.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "AI Power BI Tutor" skill (handle: ai-power-bi-tutor) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
This AI Power BI tutor is for the point where you can drag a field onto a bar chart, but a measure gives the right number by month and a wrong number in the total, and you have no idea why. This file turns Claude, ChatGPT or Gemini into a tutor that has you build a model that behaves, instead of collecting workarounds.
It asks what you have built and where your data comes from, sets your level, then teaches in the order that stops the problems: Power Query cleaning before anything else, a star schema with a real date table, relationships and cardinality, measures against calculated columns, filter context, CALCULATE, then time intelligence and publishing. Every lesson is a short explanation, one worked example on a different dataset, then your turn in Desktop. When your total is wrong it asks what the total row is filtering, and waits.
Runs identically in Claude, ChatGPT and Gemini. A single purchase, pay once, keep forever, and you are set up in two minutes.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .txt file anywhere on your device.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Paste the prompt
Open the .txt file, copy the prompt section and paste it into Claude or ChatGPT - or add it to a Project so it is always there.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then ask for any skill by name.
Paste it into a Claude Project, a custom GPT or a Gemini Gem, then describe your data and what you have already built. It sets a level, picks a small model with you and starts lesson one. You do the work in Power BI Desktop and report what the visual showed or what error DAX returned. Each session ends with a progress block you paste back next time.
Can it see my PBIX file or my data?+
No. It works from what you describe: table names, columns, row counts, the relationship you set, the measure you wrote and the number that came out. That is enough for almost every modelling and DAX problem, because those are logic problems. It will not guess at your data and it will not claim to have opened anything.
Will it prepare me for the PL-300 exam?+
It covers the ground PL-300 tests: preparing data in Power Query, modelling with a star schema, DAX measures and time intelligence, visualisation choices, and managing workspaces, refresh and row level security. Say your exam date at the start and it reorders the lessons and adds recall checks. It is not a question bank and will not invent exam questions.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.