Name: databricks-core
Rating: 57.599999999999994 (1 reviews)
Author: databricks

databricks-core

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

Quality

66%

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

Fix and improve this skill with Tessl

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

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.

The content is highly actionable with executable commands and clear prerequisites/validation checkpoints, but progressive disclosure is undermined because the four referenced reference files do not exist in the bundle, and the workflow lacks an explicit validate-fix-retry loop for the bundle/deploy path.

Suggestions

Add the missing referenced files (databricks-cli-install.md, databricks-cli-auth.md, data-exploration.md, declarative-automation-bundles.md) to the references/ directory so the signaled navigation resolves.

Add an explicit validate->fix->retry feedback loop for bundle deploy (e.g. run `databricks bundle validate`, address errors, then `bundle deploy`) to raise workflow clarity for the destructive/batch deploy step.

Move the in-body Quick Reference command catalog into a reference file to keep SKILL.md as a true overview and tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is largely lean command-and-table reference material that assumes Claude's competence, with only minor padding (e.g. the WORKS/DOES NOT WORK shell-session framing could be trimmed), so it sits above the midpoint at 'efficient with minor over-explanation'.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands for the common cases (profile selection, data exploration via aitools, list/get commands, bundles) and explicitly flags which flags/commands do not exist, covering the common cases comprehensively.	5 / 5
Workflow Clarity	Prerequisites and Profile Selection are clearly sequenced with validation checkpoints ('STOP. Do not proceed...'), and the separate-shell guidance is explicit; however the bundle deploy/run flow and the troubleshooting feedback loop lack an explicit validate-then-fix-then-retry loop, so it is below the level-5 checklist anchor.	4 / 5
Progressive Disclosure	The body references four reference files (install, auth, data-exploration, bundles) one level deep with a task-oriented table, which is good signaling, but no referenced bundle files actually exist in references/scripts/assets, so the structure is incomplete and the in-body Quick Reference duplicates detail that belongs in those files.	3 / 5
	Total	16 / 20 Passed

Description

53%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 and well-scoped to Databricks CLI work but is missing an explicit 'Use when...' trigger clause, which caps completeness at 3, and it lists capability categories rather than a comprehensive set of natural trigger terms.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user needs to run Databricks CLI commands, manage auth profiles, explore Unity Catalog tables, or deploy bundles.'

Expand trigger terms with synonyms users naturally say, such as 'Unity Catalog', 'jobs', 'pipelines', 'SQL queries', and 'warehouses'.

Replace generic category labels ('data exploration', 'bundles') with concrete actions to lift specificity from categories to multiple discrete actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and a list of concrete capability areas ('auth, profiles, data exploration, and bundles'), but these are categories rather than the multiple discrete actions (e.g. 'authenticate', 'list catalogs', 'run SQL') that a 4-5 anchor expects.	3 / 5
Completeness	It clearly states what the skill does ('Databricks CLI operations...') but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	It includes some relevant natural terms ('Databricks', 'CLI', 'data exploration', 'bundles') but misses common variations and synonyms a user might say (e.g. 'Unity Catalog', 'jobs', 'pipelines', 'SQL', 'warehouses'), placing it at 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	It is tightly scoped to Databricks CLI tooling, which is a clear niche distinct from the sibling databricks-jobs/pipelines/apps skills, with only minor overlap risk on the term 'Databricks' itself.	4 / 5
	Total	13 / 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/devhub
Path: .agents/skills/databricks-core/SKILL.md
Commit: f83a74d

Reviewed: 4 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.