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.
94
92%
Does it follow best practices?
Impact
Pending
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 the specific Databricks Genie Spaces domain, lists concrete actions (create, query, export, import, migrate), and provides an explicit 'Use when...' clause with natural trigger terms. It uses proper third-person voice and is concise without being vague. The description is well-suited for disambiguation among many skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create Genie Spaces, query them, export/import, migrate between workspaces, and ask questions via the Genie Conversation API. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create and query Databricks Genie Spaces for natural language SQL exploration) and 'when' (explicit 'Use when...' clause covering building, exporting, importing, migrating, and querying via the 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 terms a Databricks user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Databricks Genie Spaces' and 'Genie Conversation API' are very specific product features that are unlikely to conflict with other skills. The niche is clearly defined. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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 and progressive disclosure. The tool call examples are concrete and executable, and the workflow is clearly sequenced. The main weakness is some redundancy between the tool reference examples and the Quick Start section, plus a slightly verbose 'When to Use' section that could be tightened.
Suggestions
Consolidate the tool call examples in the 'manage_genie' section with the Quick Start to eliminate redundancy — either keep detailed examples in one place and reference from the other, or merge them into a single walkthrough.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'When to Use This Skill' section is somewhat verbose and could be trimmed. The 'Overview' paragraph explains what Genie Spaces are, which Claude could infer. However, the tool reference tables and examples are reasonably efficient. Some redundancy exists between the tool call examples and the Quick Start section. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready MCP tool calls for every operation (create, get, list, export, import, ask). Parameters are clearly specified with realistic values, and return values are documented. The Quick Start walks through a complete end-to-end workflow with executable examples. | 3 / 3 |
Workflow Clarity | The Quick Start provides a clear 4-step sequence (inspect → create → query → export/import) that logically builds on each step. The cross-workspace migration workflow is clearly explained with the constraint about catalog-only remapping. For a non-destructive API-based workflow, the sequencing is appropriate and clear. | 3 / 3 |
Progressive Disclosure | The skill provides a concise overview with well-signaled one-level-deep references to spaces.md and conversation.md for detailed content. Troubleshooting is appropriately delegated to spaces.md. Related skills are clearly linked. The main file stays focused on quick-start and tool usage without becoming monolithic. | 3 / 3 |
Total | 11 / 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
02aac8c
- 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.