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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable with strong executable examples and a clear quick-start sequence, but it is weakened by duplicated tool-call sections and references to missing bundle files.

Suggestions

Consolidate the manage_genie examples so they appear once (either in 'MCP Tools' or 'Quick Start') to reduce token redundancy.

Add explicit validation/checkpoint steps for destructive and migration operations (e.g. verify import succeeded before deleting the source space).

Provide the missing referenced files (spaces.md, conversation.md) or remove the broken cross-reference links so progressive disclosure resolves to real content.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable examples, but the manage_genie call patterns are duplicated between the 'MCP Tools' and 'Quick Start' sections, and the Overview explains what Genie Spaces are — tightening the duplication would reach the top anchor.	2 / 3
Actionability	Provides concrete, executable MCP tool calls with parameters, return shapes, and copy-paste-ready examples for create, get, list, export, import, and query.	3 / 3
Workflow Clarity	The Quick Start is clearly sequenced (1-4), but destructive/batch operations (delete, import overwrite, cross-workspace migration) lack explicit validation checkpoints and feedback loops, capping the score per the rubric.	2 / 3
Progressive Disclosure	References are one level deep and clearly signaled, but the referenced files (spaces.md, conversation.md) and the deep-link anchors do not exist in the bundle, so navigation is broken rather than clean.	2 / 3
	Total	9 / 12 Passed

Description

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.

The description is specific, complete, and distinctive, with explicit 'Use when' triggers covering the main workflows. It avoids fluff and uses third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create and query Databricks Genie Spaces', 'exporting and importing Genie Spaces', 'migrating Genie Spaces between workspaces or environments' — matching the top anchor for naming specific actions.	3 / 3
Completeness	Explicitly answers 'what' (create/query Genie Spaces) and 'when' via the 'Use when building Genie Spaces, exporting and importing... or asking questions via the Genie Conversation API' clause.	3 / 3
Trigger Term Quality	Uses natural terms a user would say — 'Genie Spaces', 'natural language SQL exploration', 'Conversation API', 'exporting...importing...migrating' — giving good coverage rather than jargon-only language.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Databricks Genie Spaces) with distinct, product-specific triggers unlikely to overlap with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing, 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Path: databricks-skills/databricks-genie/SKILL.md
Commit: a7e1d51

Reviewed: about 4 hours ago

Table of Contents

Discovery Implementation Validation

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.