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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body with lean executable examples, but it loses points on workflow clarity (no validation/verification steps around destructive operations) and progressive disclosure (referenced reference files are missing from the bundle while overlapping content is inlined).

Suggestions

Add explicit validation/verification steps to the workflows — e.g., after `create` or `alter`, call `describe` to confirm the definition, and require confirmation before the destructive `drop` action — to establish feedback loops.

Add the missing bundle files referenced in the Reference Files table (yaml-reference.md, patterns.md) or remove those links and decide whether the full YAML spec lives inline or in the reference, so the split is real rather than duplicated.

Dimension	Reasoning	Score
Conciseness	Lean and action-oriented throughout: it jumps straight into executable SQL, MCP calls, and a YAML spec without explaining concepts Claude already knows (no 'what is a metric' filler). The tables (Dimensions vs Measures, Common Issues) earn their tokens as dense reference.	3 / 3
Actionability	Provides fully executable, copy-paste-ready SQL, Python MCP calls, and a YAML block with concrete names, expressions, and parameters — matching the level-3 'fully executable code, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Sections are sequenced (inspect schema -> create -> query -> grant), but there are no explicit validation checkpoints or error-feedback loops, and the destructive `drop` action has no confirm/verify step — capping workflow clarity at 2 per the feedback-loops guideline.	2 / 3
Progressive Disclosure	The body signals two one-level-deep references (yaml-reference.md, patterns.md) and organizes content into clear sections, but those referenced files are absent from the bundle and the inlined 'YAML Spec Quick Reference' overlaps the supposed reference content, leaving structure present but not cleanly split.	2 / 3
	Total	10 / 12 Passed

Description

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.

A strong, third-person description that states concrete capabilities and gives explicit 'Use when' triggers with natural user vocabulary. It answers both what and when without vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "define, create, query, and manage governed business metrics in YAML" — directly paralleling the level-3 anchor of several specific concrete actions.	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...") with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Covers natural user terms — "KPIs, revenue metrics, order analytics, standardized KPIs" — that a user would actually say, with strong coverage across variations.	3 / 3
Distinctiveness Conflict Risk	The Unity Catalog metric-view niche with YAML governance triggers is distinct and unlikely to collide with other skills; it reads as a clear specialized domain.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Commit: 1c43c21

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.