databricks-genie
Create and query Databricks Genie Spaces for natural language SQL exploration. Use when building Genie Spaces, exporting and importing Genie Spaces, migrating Genie Spaces between workspaces or environments, or asking questions via the Genie Conversation API.
71
86%
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 (Databricks Genie Spaces), lists specific actions (create, query, export, import, migrate), and provides an explicit 'Use when...' clause with well-defined trigger scenarios. The description is concise, uses third person voice, and is highly distinctive due to its specific technology focus.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create Genie Spaces, query them, export/import, migrate between workspaces/environments, and ask questions via the Genie Conversation API. These are clearly defined operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (create and query Databricks Genie Spaces for natural language SQL exploration) and 'when' (explicit 'Use when...' clause listing building, exporting, importing, migrating, and querying via the Genie Conversation API). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Databricks', 'Genie Spaces', 'natural language SQL', 'export', 'import', 'migrating', 'workspaces', 'environments', 'Genie Conversation API'. Good coverage of domain-specific terms a user working with this technology would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Databricks Genie Spaces specifically. The combination of 'Databricks', 'Genie Spaces', and 'Genie Conversation API' makes it very 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 with strong actionability — concrete MCP tool calls with realistic parameters make it immediately usable. The main weaknesses are some redundancy between the MCP Tools reference section and the Quick Start walkthrough, and the lack of validation/verification steps in workflows, particularly for the migration use case. Progressive disclosure is handled well with clear pointers to supporting files.
Suggestions
Remove duplicate tool call examples — keep the detailed examples in Quick Start and make the MCP Tools section a concise reference table only, or vice versa.
Add validation steps after import/clone operations (e.g., verify the imported space with a `get` call, then test with an `ask_genie` query to confirm it works).
Trim the 'When to Use This Skill' and 'Overview' sections — Claude doesn't need to be told what Genie Spaces are or when to use the skill; the tool descriptions and examples convey this implicitly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the tool call examples appear twice (once in the MCP Tools section and again in Quick Start), and the 'When to Use This Skill' section is somewhat verbose with information Claude could infer. The 'Overview' paragraph explains what Genie Spaces are, which is context Claude likely doesn't need. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready MCP tool calls with specific parameters, return values, and realistic examples for every operation (create, get, list, export, import, ask). The examples include actual parameter names and expected return structures. | 3 / 3 |
Workflow Clarity | The Quick Start provides a clear 4-step sequence (inspect → create → query → export/import), but there are no validation checkpoints or error recovery steps. For operations like cross-workspace migration (which is destructive/complex), there's no feedback loop — just a pointer to an external file. The export/import workflow lacks verification that the import succeeded. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to spaces.md and conversation.md for detailed content, plus cross-references to related skills. The content is appropriately split between the overview here and detailed guides in referenced 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
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.