Write DAX by describing what you want, not how
Describe a measure in plain English — "percentage of total revenue by product category" — and get correct DAX with an explanation of evaluation context, filter propagation, and common pitfalls. Also debugs existing DAX that's returning wrong results.
Create a skill called "DAX Decoder". I'll either (A) describe a measure in plain English, or (B) paste existing DAX that's returning wrong results. For case A: Generate the correct DAX formula and explain step by step how evaluation context works — what's the row context, what filters are active, how CALCULATE modifies context, and how the measure behaves in different visual contexts (table, matrix, card). For case B: Analyze the DAX, identify why it's returning unexpected results, explain the context issue, and provide a corrected version. In both cases, show a small example with sample data to illustrate the behavior. If I provide my data model (table names, relationships, column types), use it for accurate results. Support translation from SQL logic to equivalent DAX.
DAX evaluation context is the steepest learning curve in the BI world.
Row context, filter context, CALCULATE, context transition — most Power BI
users spend months or years struggling with it. This skill translates between
plain English and DAX, with explanations that actually make sense.
Get the right window function without the headache
Describe what you want in plain English — "running total by region, resetting each quarter" — and get the exact window function syntax with an explanation of every clause. No more guessing at PARTITION BY, ORDER BY, and frame specs.
Find out which dashboards are actually earning their keep
Audits your BI platform's usage data to identify unused dashboards, duplicate reports, conflicting metrics, and orphaned data sources. Generates a cleanup plan with recommendations for archival, consolidation, and maintenance.
Keep up with what matters, ignore the hype
Set up a lightweight weekly digest around your stack and interests. A nice starter automation because it shows OpenClaw doing recurring research without requiring a huge workflow or lots of context.
Wikipedia-grade AI pattern removal
Comprehensive AI writing cleanup based on Wikipedia's WikiProject AI Cleanup guidelines. Catches 24+ distinct patterns including inflated symbolism, em dash overuse, rule of three, copula avoidance, and sycophantic tone.