writing-dax-measures
This skill should be used when the user asks to "write DAX measures", "create Power BI calculations", "help with DAX formulas", "write time intelligence", or mentions aggregations, filters, or DAX performance. Ensures correct syntax, optimal performance, and best practices on the first attempt.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at trigger term coverage and distinctiveness, with clear 'when to use' guidance featuring quoted user phrases. Its main weakness is that the 'what it does' portion is somewhat vague—it focuses on quality outcomes ('correct syntax, optimal performance, best practices') rather than listing specific concrete capabilities like creating calculated columns, building iterator functions, or writing CALCULATE patterns.
Suggestions
Add specific concrete actions as a 'what it does' clause, e.g., 'Creates DAX measures, calculated columns, time intelligence patterns, and CALCULATE expressions for Power BI models.'
Replace the vague outcome statement ('Ensures correct syntax, optimal performance, and best practices') with specific capabilities like 'optimizes filter context, builds iterator vs. aggregator patterns, implements row-level security'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some actions like 'write DAX measures', 'create Power BI calculations', 'write time intelligence', and references aggregations, filters, and performance. However, these are mostly embedded in the trigger clause rather than stated as concrete capabilities. The actual capability statement ('Ensures correct syntax, optimal performance, and best practices') is vague and outcome-oriented rather than listing specific concrete actions like 'create calculated columns, build time intelligence patterns, optimize CALCULATE filters'. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (writes DAX measures, creates Power BI calculations, ensures correct syntax and optimal performance) and 'when' (with a clear 'Use when' equivalent listing specific trigger phrases). The 'when' is particularly well-articulated with quoted user phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'DAX measures', 'Power BI calculations', 'DAX formulas', 'time intelligence', 'aggregations', 'filters', 'DAX performance'. These are terms users would naturally use when seeking help with DAX in Power BI. | 3 / 3 |
Distinctiveness Conflict Risk | DAX and Power BI are a very specific niche. The trigger terms like 'DAX measures', 'DAX formulas', 'Power BI calculations', and 'time intelligence' are highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides highly actionable DAX guidance with clear workflows and good progressive disclosure. Its main weakness is moderate verbosity — some conceptual explanations (context transition mechanics, BLANK behavior, Measure vs Calculated Column) could be trimmed since Claude already understands these concepts. The anti-pattern tables, executable examples, and validation checklist are excellent and make this skill highly effective for first-try DAX generation.
Suggestions
Trim conceptual explanations that Claude already knows (e.g., 'Context transition is expensive — In each iteration, the model is re-filtered' and 'BLANK is NOT the same as SQL NULL') to reduce token usage while keeping the actionable rules.
Consider condensing the Measure vs Calculated Column section to just the decision rule ('Default: use Measures; use Calculated Columns only for slicers, row-level filtering, or static RELATED lookups') without the full comparison table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes some unnecessary explanations (e.g., explaining what context transition is, how BLANK works conceptually, Measure vs Calculated Column comparison table). Some sections like BLANK handling and context transition rules explain concepts Claude likely already knows. However, the anti-pattern tables and quick reference are efficient. | 2 / 3 |
Actionability | Excellent actionability throughout — concrete DAX code examples with ✅/❌ patterns, executable snippets for every time intelligence pattern, specific function alternatives in tables, and a copy-paste-ready quick reference table. The forbidden functions table with exact replacements is highly actionable. | 3 / 3 |
Workflow Clarity | The mandatory pre-generation workflow is clearly sequenced (5 numbered steps), and the pre-submission validation checklist provides an explicit verification gate before delivering code. The workflow includes schema verification, requirement classification, and a comprehensive checklist — forming a clear validate-before-output feedback loop. | 3 / 3 |
Progressive Disclosure | The skill provides a comprehensive overview with well-signaled one-level-deep references to patterns.md and debugging.md for advanced topics. Content is appropriately split — core patterns inline, advanced patterns and debugging tools referenced externally. Section headers enable easy navigation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- back1ply/LLM-Skills
- Commit
b573078
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.