CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-core

Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.databricks/aitools/skills/databricks-core/SKILL.md

The canonical home for this skill is databricks-core in databricks/databricks-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 a highly actionable, concise CLI reference with strong command coverage and preventive gotchas, but it lacks an explicit validation checkpoint sequence for destructive bundle operations and its referenced detail files are missing from the bundle.

Suggestions

Frame the bundle workflow as an explicit validated sequence, e.g. '1. `databricks bundle validate -t <TARGET>` 2. Review errors and fix 3. Only when valid: `databricks bundle deploy -t <TARGET>` 4. `databricks bundle run <RESOURCE> -t <TARGET>`'.

Add the missing referenced files (databricks-cli-install.md, databricks-cli-auth.md, data-exploration.md) to a references/ directory, or inline their essential content and drop the dead links.

De-duplicate the reference listings by consolidating 'Required Reading by Task' and 'Reference Guides' into a single table.

DimensionReasoningScore

Conciseness

The body is lean and command-driven, assuming CLI competence without explaining basic concepts; only minor redundancy (the reference guides are listed in both 'Required Reading by Task' and 'Reference Guides') keeps it from a 5.

4 / 5

Actionability

Provides copy-paste-ready commands with clearly marked placeholders across all common cases (list/get/bundles), plus concrete gotchas like the Unity Catalog positional-argument requirement and the Claude Code shell-session pattern.

5 / 5

Workflow Clarity

Prerequisites and Profile Selection have clear sequences with checkpoints (version check, STOP guard, never-auto-select), but the destructive `bundle deploy` operation is listed as flat commands without an explicit validate-then-deploy sequence, so workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep references and navigable task/reference tables, but the referenced files (databricks-cli-install.md, databricks-cli-auth.md, data-exploration.md) do not exist in the bundle, leaving the links broken.

4 / 5

Total

16

/

20

Passed

Description

66%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 clearly conveys the skill's domain and concrete operation areas with natural trigger terms, but it omits explicit "when to use" guidance, which caps its completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user needs to run Databricks CLI commands, manage auth profiles, explore catalogs/tables, or work with Databricks Asset Bundles.'

Include a few more natural synonyms/trigger phrases users actually say (e.g. 'Lakeflow jobs', 'Unity Catalog', 'Databricks SQL', 'warehouses') to broaden trigger coverage and reduce overlap ambiguity with the product-specific sibling skills.

DimensionReasoningScore

Specificity

Names the Databricks CLI domain and several concrete operation areas ("auth, profiles, data exploration, and bundles"), giving good coverage though the actions are category-level rather than granular.

4 / 5

Completeness

Clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("Databricks", "CLI", "auth", "profiles", "data exploration", "bundles") with good coverage, though some common synonyms (e.g. Lakeflow, jobs, pipelines, Unity Catalog) are absent.

4 / 5

Distinctiveness Conflict Risk

"Databricks CLI operations" carves a clear niche, but topics like "bundles" and "data exploration" overlap with closely related sibling skills (databricks-jobs, databricks-pipelines), creating minor conflict risk.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 9 missing

Warning

Total

15

/

16

Passed

Repository
databricks/devhub
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.