databricks-metric-views
Unity Catalog metric views: define, create, query, and manage governed business metrics in YAML. Use when building standardized KPIs, revenue metrics, order analytics, or any reusable business metrics that need consistent definitions across teams and tools.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is a strong skill description that clearly identifies the domain (Unity Catalog metric views), lists concrete actions (define, create, query, manage), specifies the format (YAML), and includes an explicit 'Use when' clause with natural trigger terms like KPIs, revenue metrics, and order analytics. It is distinctive enough to avoid conflicts with broader data or analytics skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'define, create, query, and manage governed business metrics in YAML.' Also specifies the domain clearly (Unity Catalog metric views) and the format (YAML). | 3 / 3 |
Completeness | Clearly answers both 'what' (define, create, query, and manage governed business metrics in YAML) and 'when' (explicit 'Use when' clause covering building standardized KPIs, revenue metrics, order analytics, or reusable business metrics needing consistent definitions). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'KPIs', 'revenue metrics', 'order analytics', 'business metrics', 'metric views', 'Unity Catalog', 'YAML', 'reusable', 'consistent definitions'. Good coverage of terms a user working with governed metrics would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the specific combination of 'Unity Catalog metric views' and 'YAML' format. Unlikely to conflict with general data analytics or BI skills due to the narrow focus on governed metric definitions in a specific platform. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong actionability and good progressive disclosure. Its main weaknesses are moderate verbosity from explanatory tables that teach concepts Claude already understands, and a lack of explicit validation steps in the workflow (e.g., verifying a metric view was created correctly before querying it). Trimming the conceptual comparison tables and adding a validation checkpoint would elevate this skill significantly.
Suggestions
Remove or significantly condense the 'Dimensions vs Measures' and 'Why Metric Views vs Standard Views' comparison tables — Claude understands these concepts and they consume tokens without adding actionable guidance.
Add an explicit validation step after creation, e.g., 'After creating, run `manage_metric_views(action="describe", ...)` to verify the definition, then test with a simple query before sharing with consumers.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes some content Claude already knows (e.g., the 'Dimensions vs Measures' and 'Why Metric Views vs Standard Views' comparison tables explain basic concepts). The Integrations section is also low-value filler. The YAML quick reference duplicates information already shown in the full example above it. | 2 / 3 |
Actionability | Provides fully executable SQL and MCP tool examples that are copy-paste ready. The CREATE, query, describe, and grant examples are concrete with specific parameters, and the `get_table_stats_and_schema` prerequisite step is actionable. | 3 / 3 |
Workflow Clarity | The workflow follows a logical sequence (inspect schema → create → query), but there are no explicit validation checkpoints. After creating a metric view, there's no step to verify it was created correctly (e.g., describe it) before querying. For a skill involving DDL operations, a validate-then-proceed pattern would strengthen this. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in the main file and well-signaled one-level-deep references to yaml-reference.md and patterns.md. The reference table clearly describes what each linked file contains, and external documentation links are organized in a dedicated Resources section. | 3 / 3 |
Total | 10 / 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
- databricks-solutions/ai-dev-kit
- Commit
b4071a0
- 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.