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.
68
82%
Does it follow best practices?
Impact
—
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 its domain (Unity Catalog metric views), lists concrete actions (define, create, query, manage), and provides explicit trigger guidance with natural keywords like KPIs, revenue metrics, and order analytics. The description is concise, uses third-person voice, and is highly distinctive with minimal conflict risk.
| 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' (Use when building standardized KPIs, revenue metrics, order analytics, or any reusable business metrics that need consistent definitions across teams and tools). Explicit 'Use when' clause is present. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'KPIs', 'revenue metrics', 'order analytics', 'business metrics', 'YAML', 'Unity Catalog', 'metric views', 'reusable', 'consistent definitions'. Good coverage of terms a user working with governed metrics would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Unity Catalog metric views in YAML format. The combination of 'Unity Catalog', 'metric views', 'YAML', and 'governed business metrics' creates a very specific trigger profile unlikely to conflict with general data or analytics skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent concrete examples for both SQL and MCP tool usage. Its main weaknesses are moderate verbosity from explanatory tables that Claude doesn't need (dimensions vs measures, metric views vs standard views) and a lack of explicit workflow sequencing with validation checkpoints. The progressive disclosure structure is reasonable but the main file carries too much inline reference material.
Suggestions
Add an explicit numbered workflow with validation steps, e.g.: 1) Inspect schema, 2) Create metric view, 3) Describe to verify, 4) Query to test, 5) Grant access — with a checkpoint after step 3.
Move the 'Dimensions vs Measures', 'Why Metric Views vs Standard Views', and 'YAML Spec Quick Reference' sections into the referenced yaml-reference.md to reduce the main file's token footprint.
Remove or significantly condense the 'Integrations' section — it's a list of product names that doesn't provide actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some sections that could be trimmed. The 'Dimensions vs Measures' and 'Why Metric Views vs Standard Views' tables explain concepts Claude likely already understands. The 'Integrations' section is a simple list that adds little actionable value. The YAML spec quick reference partially duplicates the full example above it. | 2 / 3 |
Actionability | The skill provides fully executable SQL and MCP tool examples that are copy-paste ready. The create, query, describe, and grant operations all have concrete, complete code examples with realistic parameters. The initial step to inspect the source table schema is a practical, actionable starting point. | 3 / 3 |
Workflow Clarity | There's a reasonable implicit workflow (inspect schema → create → query → grant), but it lacks explicit sequencing as a numbered workflow with validation checkpoints. There's no validation step after creation (e.g., 'describe to verify the definition was applied correctly') or error recovery guidance for failed creates/alters. | 2 / 3 |
Progressive Disclosure | The skill references yaml-reference.md and patterns.md in a clear table, which is good progressive disclosure. However, no bundle files were provided, so these references cannot be verified. The SKILL.md itself is quite long (~180 lines of content) and inlines material like the YAML spec quick reference and comparison tables that could be offloaded to reference files. | 2 / 3 |
Total | 9 / 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
93cb4e3
- 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.