Create Databricks resources that agents connect to as tools. Use when: (1) User needs to create a Genie space, vector search index, UC function, or UC connection, (2) User says 'create tool', 'set up genie', 'create vector search', 'register MCP server', (3) Before add-tools when the resource doesn't exist yet, (4) User asks 'what do I need to create before adding this tool'.
68
82%
Does it follow best practices?
Impact
—
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 skill description that clearly defines its scope within the Databricks ecosystem, lists specific resource types it handles, and provides explicit trigger conditions. The inclusion of relationship to the 'add-tools' skill helps Claude understand the workflow ordering. The description uses proper third-person voice and is well-structured with numbered trigger scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create Genie space, vector search index, UC function, UC connection. Also mentions registering MCP server. These are concrete, specific resource types rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both 'what' (create Databricks resources like Genie spaces, vector search indexes, UC functions, UC connections) and 'when' with an explicit 'Use when:' clause covering four distinct trigger scenarios including relationship to other skills ('Before add-tools when the resource doesn't exist yet'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'create tool', 'set up genie', 'create vector search', 'register MCP server', plus specific resource names like 'Genie space', 'vector search index', 'UC function', 'UC connection'. Good coverage of natural terms within the Databricks domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: creating Databricks resources as agent tools. The description explicitly differentiates itself from a related 'add-tools' skill by noting this is for when 'the resource doesn't exist yet.' The specific resource types (Genie space, vector search index, UC function) make it unlikely to conflict with other 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 well-structured routing/index skill that efficiently directs users to the right resource creation guide. Its main strength is the concise decision table and clear workflow overview. However, it lacks any concrete, executable guidance of its own—all actionable content is delegated to example files that aren't available in the bundle—and the workflow is missing validation checkpoints after resource creation.
Suggestions
Add at least one inline concrete example (e.g., a minimal UC function creation snippet) so the skill has standalone actionable value even without the referenced files.
Add a validation step after step 2 in the workflow, such as 'Verify: re-run `uv run discover-tools` to confirm the resource appears before proceeding to add-tools.'
Include the bundle files (examples/*.md) or at minimum confirm their existence, since the skill's value depends entirely on those references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. The table is an efficient decision matrix, the workflow is minimal, and there's no explanation of concepts Claude already knows. The introductory blockquote is brief and contextual. | 3 / 3 |
Actionability | The skill provides a clear decision table and references to detailed guides, but contains no executable code or concrete commands beyond `uv run discover-tools`. The actual creation steps are entirely delegated to example files which are not provided in the bundle. | 2 / 3 |
Workflow Clarity | The 4-step workflow is clearly sequenced and provides a good high-level overview, but lacks validation checkpoints. There's no verification step after resource creation (e.g., confirming the resource exists before proceeding to add-tools), which is important for operations that create infrastructure resources. | 2 / 3 |
Progressive Disclosure | The skill appropriately uses a table to point to five separate example files and references three other skills, which is good structure. However, since no bundle files are provided, we cannot verify that the referenced paths (e.g., `examples/genie-space.md`) actually exist, and the skill itself contains almost no substantive content beyond the routing table—it's essentially hollow without the referenced 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.
1c88215
Table of Contents
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.