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/).
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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, well-crafted description that concisely covers specific capabilities, includes natural trigger terms, and clearly delineates both what the skill does and when to use it. The domain-specific terminology (Unity Catalog, system tables, /Volumes/) provides excellent distinctiveness. Uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: querying system tables (audit, lineage, billing) and volume file operations (upload, download, list files). These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (Unity Catalog system tables and volumes operations) and when ('Use when querying system tables... or working with volume file operations') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'system tables', 'audit', 'lineage', 'billing', 'volume', 'upload', 'download', 'list files', '/Volumes/'. Good coverage of terms a Databricks user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Unity Catalog system tables and /Volumes/ operations. The specific domain (Databricks Unity Catalog) and concrete triggers (audit, lineage, billing, /Volumes/) make it unlikely to conflict with other skills. | 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 that excels at progressive disclosure and actionability, providing concrete SQL examples and MCP tool signatures that are immediately usable. Its main weaknesses are some verbosity in the introductory sections and a lack of validation/verification steps in workflows, particularly around permission grants and system table access setup.
Suggestions
Trim the 'When to Use This Skill' section to 3-4 key bullets or remove it entirely since the reference table already communicates scope clearly.
Add a verification step after the GRANT statements (e.g., 'Verify access: SELECT * FROM system.access.audit LIMIT 1') to improve workflow clarity.
Remove or significantly condense the 'Best Practices' section—these are generic guidelines Claude already knows, not skill-specific operational knowledge.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'When to Use This Skill' section is somewhat verbose—listing 8 bullet points that largely restate what the reference files cover. The 'Best Practices' section contains generic advice Claude already knows (e.g., 'grant minimal access'). However, the quick start and query examples are reasonably lean. | 2 / 3 |
Actionability | Provides fully executable SQL queries for lineage, audit, and billing; concrete MCP tool invocations with exact function signatures and parameters; and copy-paste ready GRANT statements. The tool usage table is specific and immediately usable. | 3 / 3 |
Workflow Clarity | The skill presents individual operations clearly but lacks sequenced multi-step workflows with validation checkpoints. For example, granting system table access has no verification step (e.g., confirming the grant succeeded), and there's no error recovery guidance for failed queries or permission issues. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, a well-organized reference table pointing to one-level-deep files (system tables, volumes, data profiling), and related skills clearly linked. Content is appropriately split between the overview and detailed reference files. | 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.