Name: databricks-core
Rating: 68 (1 reviews)
Author: databricks

databricks-core

Databricks CLI operations and the parent/entry-point skill for Databricks CLI use: authentication, profile selection, and bundles. Load this first for CLI, auth, profile, and bundle tasks, then load the matching product skill. For finding or exploring data, answering questions about the data, or generating SQL, load the databricks-data-discovery skill (it routes to Genie One). Contains up-to-date guidelines for Databricks-related CLI tasks.

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 highly actionable with concrete commands and helpful gotchas, but it repeats the data-discovery routing and lacks an explicit validate-before-deploy feedback loop. Referenced markdown files are signaled but missing from the bundle, weakening progressive disclosure.

Suggestions

Add the referenced files to ./references/ (databricks-cli-install.md, databricks-cli-auth.md, manual-data-exploration.md) or remove the dead links.

Sequence bundle deployment as an explicit validate-then-deploy feedback loop (e.g. `bundle validate` must pass before `bundle deploy`).

Consolidate the databricks-data-discovery routing guidance into one section to remove the three repetitions.

Dimension	Reasoning	Score
Conciseness	Mostly lean code/tables with little concept explanation, but the databricks-data-discovery routing is repeated in three sections and the "Names are literal" guidance is restated, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready, fully executable commands, calls out positional-vs-flag argument pitfalls with concrete examples, and includes a troubleshooting table mapping errors to fixes.	3 / 3
Workflow Clarity	Prerequisites and profile selection have clear numbered steps with a "STOP" checkpoint, but bundle deploy (a destructive/batch operation) lists `bundle validate` without an explicit validate-before-deploy feedback loop, capping clarity at 2.	2 / 3
Progressive Disclosure	References are well-signaled and one level deep with a tidy "Reference Guides" section, but the referenced files (databricks-cli-install.md, databricks-cli-auth.md, manual-data-exploration.md) are not present in the bundle (references/ is empty), so the structure does not fully resolve.	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.

A strong, third-person description that clearly states capabilities, gives explicit trigger guidance for when to load it versus product skills, and is well-differentiated as the entry-point skill. Minor verbosity from the closing "up-to-date guidelines" clause does not materially weaken it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "authentication, profile selection, and bundles" plus routing to data-discovery — rather than vague language.	3 / 3
Completeness	Answers both what (CLI operations, auth, profile, bundles) and when with explicit triggers: "Load this first for CLI, auth, profile, and bundle tasks" and "For finding or exploring data…".	3 / 3
Trigger Term Quality	Covers natural terms users would say: "Databricks CLI", "authentication", "profile selection", "bundles", "finding or exploring data", "answering questions about the data", "generating SQL".	3 / 3
Distinctiveness Conflict Risk	Positions itself as a parent/entry-point skill that routes to specific product skills, and explicitly delineates when to use databricks-data-discovery instead, minimizing conflict.	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: 11 missing	Warning

	Total	15 / 16 Passed

Repository: databricks/databricks-agent-skills
Path: skills/databricks-core/SKILL.md
Commit: 3d79814

Reviewed: 2 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.