Name: databricks-core
Rating: 67.2 (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

81%

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

78%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.

A highly actionable, well-structured reference dense with executable commands and useful pitfalls, with clear prerequisite and profile-selection workflows. Its main weakness is progressive disclosure: three referenced markdown files are missing from the bundle, breaking navigation to the deeper material.

Suggestions

Add the missing referenced files (databricks-cli-install.md, databricks-cli-auth.md, manual-data-exploration.md) to the bundle, or remove the links and inline the essential content.

Reference or remove the orphaned assets/databricks.png and databricks.svg so every bundle file is used and every link resolves.

Add an explicit validate-then-deploy checkpoint for bundle operations (e.g., 'bundle validate' must pass before 'bundle deploy') to push workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command tables and short procedural sections that assume Claude's competence; a few emphasis markers and the negative-example block in Quick Reference could be trimmed but are largely load-bearing.	4 / 5
Actionability	Provides copy-paste-ready, executable bash commands with --profile flags covering list/get/bundle operations, plus concrete pitfalls (positional vs flag args, literal naming, backtick quoting); examples cover the common cases.	5 / 5
Workflow Clarity	Prerequisites and Profile Selection give a clear numbered sequence with an explicit STOP checkpoint ('If the CLI is missing or outdated... STOP'), and the Troubleshooting table provides error-recovery feedback; minor validation gaps around bundle deploy keep it off the top anchor.	4 / 5
Progressive Disclosure	Sections are well organized with clearly signaled one-level references ([CLI Installation], [CLI Authentication], [Manual Data Exploration]), but those referenced .md files do not exist in the bundle, so the deeper content is unreachable; the only bundle files present (assets/databricks.png, databricks.svg) are not referenced from the body.	3 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong, third-person description that clearly states what the skill does and when to load it, with explicit routing to sibling skills to reduce conflict. Minor filler and slightly less-than-comprehensive action enumeration keep it just below the top anchor on specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ('authentication, profile selection, and bundles', 'Databricks CLI operations') and explicit routing to data-discovery; falls just short of fully comprehensive coverage and carries a mild filler line ('Contains up-to-date guidelines...').	4 / 5
Completeness	Clearly answers both 'what' (Databricks CLI operations, auth, profile selection, bundles) and 'when' ('Load this first for CLI, auth, profile, and bundle tasks') with concrete trigger phrases, plus explicit routing guidance for data tasks.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('CLI, auth, profile, and bundle tasks', 'finding or exploring data', 'answering questions about the data', 'generating SQL'); a few common synonyms/extensions are missing.	4 / 5
Distinctiveness Conflict Risk	Establishes a clear niche as the parent/entry-point skill and explicitly routes to product skills and data-discovery, but as a broad entry point it still has minor overlap risk with its child product skills.	4 / 5
	Total	17 / 20 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: 653db60

Reviewed: 5 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.