databricks-unity-catalog

Unity Catalog system tables and volumes. Use when querying system tables (audit, lineage, billing) or working with volume file operations (upload, download, list files in /Volumes/).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

The body is highly actionable with executable SQL and MCP tool examples, but loses points for duplicated query examples and missing reference bundle files that the body links to. No validation/feedback loops are present for the batch SQL operations.

Suggestions

Create the referenced bundle files (5-system-tables.md, 6-volumes.md, 7-data-profiling.md) in a references/ directory, or remove the broken links and inline the necessary detail.

De-duplicate the lineage query that appears in both 'Common Queries' and 'MCP Tool Integration' to tighten token usage.

Add a brief validate-then-proceed checkpoint (e.g. confirm row counts or test grants on a small query before running batch/system-table queries) to strengthen workflow clarity for batch SQL operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly token-efficient with tables and code, but lineage-query patterns are repeated across the 'Common Queries' and 'MCP Tool Integration' sections and could be tightened, matching the 'mostly efficient but could be tightened' anchor rather than fully lean.	2 / 3
Actionability	Provides fully executable SQL, concrete MCP tool signatures with arguments (e.g. list_volume_files(volume_path=...)), and copy-paste-ready examples rather than pseudocode, matching the top anchor.	3 / 3
Workflow Clarity	Structure and 'When to Use' triggers are clear, but there are no explicit validation checkpoints or feedback loops for the SQL/batch operations, capping it at the 'sequence present but checkpoints missing' anchor.	2 / 3
Progressive Disclosure	A Reference Files table signals one-level-deep links to 5-system-tables.md, 6-volumes.md, and 7-data-profiling.md, but those bundle files do not exist in the skill directory, so detail that should be offloaded stays inline and navigation is broken.	2 / 3
	Total	9 / 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 well-crafted description that states concrete capabilities, includes natural trigger terms, and explicitly signals when to use the skill, all in a distinct niche. No first/second-person voice issues are present.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — 'querying system tables (audit, lineage, billing)' and 'volume file operations (upload, download, list files in /Volumes/)' — matching the anchor for multiple specific concrete actions, not merely naming a domain.	3 / 3
Completeness	Explicitly answers both 'what' (Unity Catalog system tables and volumes) and 'when' via a 'Use when querying system tables... or working with volume file operations' clause, matching the top anchor.	3 / 3
Trigger Term Quality	Covers natural user-facing terms such as audit logs, lineage, billing, volumes, upload/download, and the /Volumes/ path, giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche — Unity Catalog system tables and volumes — with distinct triggers unlikely to fire for unrelated Databricks skills.	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: 3 missing, 4 suspicious	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.