power-bi-model-design-review
Comprehensive Power BI data model design review prompt for evaluating model architecture, relationships, and optimization opportunities.
48
22%
Does it follow best practices?
Impact
89%
1.08xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/power-bi-development/skills/power-bi-model-design-review/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies the Power BI domain and broadly names review areas (architecture, relationships, optimization), but lacks concrete specific actions and has no explicit trigger guidance ('Use when...'). It reads more like a title than a functional description that would help Claude reliably select this skill from a large pool.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'Power BI model review', 'data model optimization', 'DAX performance', '.pbix file', or 'star schema'.
List specific concrete actions such as 'evaluate star schema compliance, review relationship cardinality, identify redundant columns, assess DAX measure performance, and recommend partitioning strategies'.
Include common user-facing variations and file types (e.g., 'Power BI Desktop', '.pbix', 'slow dashboard', 'report performance') to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Power BI data model design) and some actions (evaluating model architecture, relationships, optimization opportunities), but these are fairly high-level and not concrete specific actions like 'check star schema compliance' or 'identify missing indexes'. | 2 / 3 |
Completeness | It describes what the skill does (review Power BI data model design) but has no explicit 'Use when...' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also somewhat vague, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'Power BI', 'data model', 'relationships', and 'optimization' which are relevant keywords, but misses common user variations like 'DAX', 'measures', 'star schema', 'performance', 'slow report', or '.pbix'. | 2 / 3 |
Distinctiveness Conflict Risk | Power BI is a specific enough domain to reduce conflicts with generic data skills, but 'data model design review' and 'optimization opportunities' could overlap with general database design or other BI tool skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose, generic consulting-style framework that provides no Power BI-specific executable guidance. It consists entirely of abstract checklists and templates that Claude already knows, adding no unique technical knowledge. The content would be far more valuable if condensed to ~50 lines with specific DAX examples, concrete Power BI Desktop/Service commands, and actual technical patterns to look for.
Suggestions
Replace abstract checklists with concrete, executable examples: include specific DAX patterns to look for (e.g., bad vs. good measure patterns), actual Power BI metadata queries (e.g., DMV queries to inspect model size), and specific VPAX/Tabular Editor commands for model analysis.
Reduce the content by 80%+ by removing generic advice Claude already knows (e.g., 'meaningful names', 'consistent conventions') and focus only on Power BI-specific, non-obvious guidance.
Add concrete code examples: DAX queries for identifying performance issues (e.g., EVALUATE INFO.STORAGETABLECOLUMNS()), Tabular Editor C# scripts for bulk model inspection, and specific Best Practice Analyzer rules.
Restructure with progressive disclosure: put a concise quick-start review checklist (10-15 lines) at the top, then reference separate files for detailed review areas (performance.md, security.md, etc.).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines, mostly consisting of generic checklists and templates that Claude already knows. The content reads like a consulting framework document rather than a skill that adds new knowledge. Almost every section restates obvious best practices (e.g., 'Meaningful table and column names', 'Consistent naming conventions') without providing any Power BI-specific technical commands, code, or non-obvious guidance. | 1 / 3 |
Actionability | The skill contains zero executable code, no DAX examples, no specific Power BI commands, and no concrete technical guidance. It is entirely composed of abstract checklists and vague descriptions like 'Evaluate Model Structure' and 'Query performance analysis' without showing how to actually perform any of these tasks. Everything is descriptive rather than instructive. | 1 / 3 |
Workflow Clarity | There is a phased structure (Phase 1-3) and time-boxed checklists (30-minute vs 4-8 hour review), which provides some sequential clarity. However, there are no validation checkpoints, no feedback loops for error recovery, and no concrete steps—just categories of things to check. The phases are organizational headers rather than actionable workflows. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no layered structure. Everything is inlined in a single massive document. The 30-minute quick checklist is buried deep in the file rather than being surfaced early, and there's no separation of overview from detailed reference material. | 1 / 3 |
Total | 5 / 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
- github/awesome-copilot
- Commit
9b74459
- 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.