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.
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 skill description that clearly identifies the specific Databricks Genie Spaces domain, lists concrete actions (create, query, export, import, migrate), and includes an explicit 'Use when...' clause with well-chosen trigger scenarios. The description is concise, uses third person voice, and is highly distinctive due to the specificity of the product feature it targets.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create and query Databricks Genie Spaces', 'building Genie Spaces', 'exporting and importing Genie Spaces', 'migrating Genie Spaces between workspaces or environments', and 'asking questions via the Genie Conversation API'. | 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 Genie Conversation API). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Databricks', 'Genie Spaces', 'natural language SQL', 'exporting', 'importing', 'migrating', 'workspaces', 'environments', 'Genie Conversation API'. These cover the domain-specific terms a user working with this feature would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around 'Databricks Genie Spaces' and the 'Genie Conversation API'. These are very specific product features 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 and progressive disclosure. The code examples are concrete and executable, and the reference file organization is clean. The main weaknesses are some verbosity in the introductory sections and missing validation/verification steps in the workflows, particularly for migration and space creation operations.
Suggestions
Add validation checkpoints after key operations (e.g., verify space creation with get_genie, validate export payload before importing to a new workspace)
Trim the 'When to Use This Skill' and 'Overview' sections - the bullet list largely restates what the tool tables already convey, and Claude doesn't need an explanation of what Genie Spaces are
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'When to Use This Skill' section is somewhat verbose and could be trimmed. The overview explains what Genie Spaces are, which Claude could infer. However, the MCP tool tables and code examples are efficient and well-structured. | 2 / 3 |
Actionability | The Quick Start section provides fully executable, copy-paste ready code examples for each major workflow: inspecting tables, creating spaces, asking questions, and exporting/importing. Tool parameters and return values are clearly shown. | 3 / 3 |
Workflow Clarity | The Quick Start provides a clear numbered sequence (inspect → create → query → export/import), but there are no validation checkpoints or error recovery steps. For operations like migration and space creation, there should be verification steps (e.g., confirm space was created, validate export before import). | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, quick start, and well-signaled one-level-deep references to spaces.md and conversation.md. Related skills and prerequisites are clearly organized. Content is appropriately split between the SKILL.md overview and 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.