CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

databricks-data-discovery

Discover, explore, and query Databricks data via Genie — the CLI equivalent of the Genie One MCP. MUST be invoked whenever the user asks to find or locate data ('what tables are in X', 'where does X live', 'which catalog/schema has Y'), answer a natural-language question about the data, or write a SQL query.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

The body is highly actionable with concrete copy-paste commands and a clear routing workflow including a verification checkpoint. It is slightly verbose in its rationale/positioning sections, which keeps conciseness just below the top anchor.

Suggestions

Tighten the "Why prefer Genie for data questions" and "Relationship to the Genie One MCP" sections to the essential routing rationale — the naming-history footnote can collapse to one line.

Make the manual-fallback branch's sequence more explicit as a numbered checklist (verify availability → fall back to information_schema/discover-schema/tools query) to lift workflow_clarity toward 5.

Consider moving the extended flag reference (--raw, --warehouse-id, parallelism rules) into a short reference subsection or sibling file so the main flow stays lean.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence, but sections like "Why prefer Genie for data questions", "Relationship to the Genie One MCP", and the naming history add prose that could be trimmed — fitting the score-4 anchor rather than 5.

4 / 5

Actionability

Copy-paste-ready commands ("databricks genie ask -s trips \"How many bookings were there last week?\"") cover session reuse, --include-sql, --output json with a sample payload, and the older-CLI fallback — fully executable and matching the score-5 anchor.

5 / 5

Workflow Clarity

A clear routing decision tree precedes an explicit verification checkpoint ("first verify with databricks genie ask --help") before fallback, with minor validation gaps; the destructive-cap does not apply since discovery is read-only.

4 / 5

Progressive Disclosure

Well-sectioned body (~136 lines) with clearly signaled one-level-deep links to the parent/sibling ("../databricks-core/manual-data-exploration.md") and no nested references, but it is over 50 lines so the simple-skill score-5 exception does not apply.

4 / 5

Total

17

/

20

Passed

Description

96%Weight 40%Scale 1-5

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, trigger-rich, and explicitly answers both what and when with concrete user-facing phrases. Its only soft spot is minor overlap risk with the closely related databricks-genie-agents skill sharing the Genie name.

DimensionReasoningScore

Specificity

"Discover, explore, and query Databricks data via Genie" lists multiple concrete actions (discover, explore, query) plus find/locate data, answer natural-language questions, and write SQL — comprehensive coverage matching the score-5 anchor.

5 / 5

Completeness

Clearly states what ("Discover, explore, and query Databricks data via Genie") and explicitly when ("MUST be invoked whenever the user asks to find or locate data...") with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say — "what tables are in X", "where does X live", "which catalog/schema has Y", "find or locate data", "write a SQL query" — covering synonyms and variations like the score-5 anchor.

5 / 5

Distinctiveness Conflict Risk

A clear Databricks-data-discovery niche with distinct triggers, but the shared "Genie" naming with the sibling databricks-genie-agents skill carries minor overlap risk, fitting the score-4 anchor better than 5.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

databricks/databricks-agent-skills

Path

plugins/databricks/claude/skills/databricks-data-discovery/SKILL.md

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.