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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 and well-structured with executable examples and a clear quick-start sequence, but it is held back by duplicated examples, no validation checkpoints on the destructive migration/import flow, and two referenced detail files (spaces.md, conversation.md) that do not exist.

Suggestions

Deduplicate the example calls: keep the full examples in one section and reference them from the other, or slim one set to essentials, to improve token efficiency.

Add an explicit verification step to the import/migration workflow (e.g., call manage_genie(action='get') after import to confirm the new space and validate table mapping before discarding or relying on the source).

Create the referenced spaces.md and conversation.md files (or correct the links) so the progressive-disclosure pointers resolve to real content.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — tool tables and tight example calls with no padding about SQL/warehouses — but the create_or_update, export, and import examples are repeated near-verbatim across the 'MCP Tools' and 'Quick Start' sections, which could be tightened. Not a 3 due to this duplication; not a 1 because it never explains concepts Claude already knows.	2 / 3
Actionability	Provides concrete, copy-paste-ready MCP tool calls with real parameters and documented return shapes (e.g. 'Returns: {question, conversation_id, message_id, status, sql, columns, data, row_count}'). Fully executable examples, matching the top anchor.	3 / 3
Workflow Clarity	The 'Quick Start' gives a clear 1-2-3-4 sequence, but the migration/import workflow can overwrite or replace spaces with no explicit validation or verification step before discarding the source. Per the scoring notes, missing feedback loops for destructive/batch operations caps this at 2. Not a 3 because checkpoints are absent; not a 1 because the sequence is clear.	2 / 3
Progressive Disclosure	The body is well-structured and signals one-level-deep references to spaces.md (Migration, Troubleshooting) and conversation.md, but both referenced files are missing — no references/ directory exists, so the links are dead. Not a 3 because broken references break easy navigation; not a 1 because the structure and signaling intent are genuinely good rather than monolithic.	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 strong: it names a clear niche, lists several concrete actions, and provides an explicit 'Use when...' trigger clause covering the main scenarios. It is concise and free of fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create and query', 'building', 'exporting and importing', 'migrating', 'asking questions' — matching the anchor that enumerates several specific actions. Not a 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both 'what' ('Create and query Databricks Genie Spaces for natural language SQL exploration') and 'when' via a 'Use when...' clause enumerating scenarios. Not a 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes natural domain phrasing a user would say — 'building Genie Spaces', 'exporting and importing', 'migrating Genie Spaces between workspaces', 'Genie Conversation API' — with good coverage of common variations. Not a 2 because it covers the main usage scenarios rather than just one keyword.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche ('Databricks Genie Spaces') with distinct triggers unlikely to fire for unrelated skills. Not a 2 because the domain-specific scope makes overlap with similar skills minimal.	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
Commit: 1c43c21

Reviewed: 3 days 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.