Name: databricks-dabs
Rating: 81.8 (1 reviews)
Author: databricks

databricks-dabs

Create, configure, validate, deploy, run, and manage DABs — Declarative Automation Bundles (formerly Databricks Asset Bundles) — for Databricks resources including dashboards, jobs, pipelines, alerts, volumes, and apps

2.06x

Quality

73%

Does it follow best practices?

Impact

93%

2.06x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

Quality

Content

65%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 excels at progressive disclosure — a tight overview routing to real, well-described reference files — and is reasonably concise, but its actionability and workflow clarity are limited because concrete examples and an ordered end-to-end sequence live in the references rather than the body.

Suggestions

Add a short numbered create→configure→validate→deploy→run workflow with the `bundle validate --strict --target <target>` checkpoint embedded between configure and deploy.

Include one minimal inline `databricks.yml` resource snippet so the body is actionable without forcing a reference hop for the common case.

Trim the opening sentence, which restates the frontmatter description and overlaps the "When to Use" list.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding or restated concepts, but the opening sentence ("Use this skill for any bundle-related request including creating, configuring, validating, deploying, running, and managing...") duplicates the description frontmatter and previews the "When to Use" list. It is not a 5 because of that minor redundancy; not a 3 because the rest is efficient.	4 / 5
Actionability	It includes one concrete executable command (`bundle validate --strict --target <target>`) and a concrete naming format (`<name>.<resource_type>.yml`), but most actionable detail is deferred to reference files, leaving the body incomplete as standalone executable guidance. It is not a 4 because there are no inline YAML examples or full command sequences; not a 2 because the command and format are genuinely concrete.	3 / 5
Workflow Clarity	A validation checkpoint is present (guideline 1, "Always validate after configuration changes"), but the body offers general rules rather than a sequenced create→configure→validate→deploy→run workflow. It is not a 4 because there is no explicit ordered sequence with embedded checkpoints; not a 2 because validation is at least called out.	3 / 5
Progressive Disclosure	The body is a clear overview with five well-signaled, one-level-deep reference links, each annotated with its scope, and all referenced files (alerts.md, bundle-structure.md, deploy-and-run.md, resource-permissions.md, sdp-pipelines.md) exist in references/. It is not a 4 because navigation and content split are clean with no nesting.	5 / 5
	Total	15 / 20 Passed

Description

82%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, well-targeted, and distinctive with strong synonym coverage of trigger terms, but it omits any explicit "Use when..." trigger guidance, which caps its completeness at 3. Adding a trigger clause would lift the weakest dimension.

Suggestions

Append a "Use when..." clause naming the natural trigger phrases (e.g. "Use when creating, configuring, validating, deploying, or managing Databricks bundles/DABs, or when editing databricks.yml").

Optionally surface the databricks.yml filename as a natural term users mention, since the body already emphasizes it.

Dimension	Reasoning	Score
Specificity	Lists six concrete actions ("Create, configure, validate, deploy, run, and manage") plus an enumerated set of resource types (dashboards, jobs, pipelines, alerts, volumes, apps), matching the comprehensive-coverage anchor. It is not a 4 because coverage of actions and resources is broad rather than having only minor gaps.	5 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline. It is not a 4 because "when" is entirely absent rather than merely weakly stated.	3 / 5
Trigger Term Quality	Covers the natural synonyms a user would say — "DABs", "Declarative Automation Bundles", and the deprecated "Databricks Asset Bundles" — alongside concrete resource-type names. It is not a 4 because synonym coverage is comprehensive, though no file extensions (e.g. databricks.yml) appear.	5 / 5
Distinctiveness Conflict Risk	DABs / Databricks bundle management is a clear, narrow niche with distinct triggers and minimal overlap risk with other skills. It is not a 4 because the domain is sharply specific rather than only "mostly distinct".	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/devhub
Path: .databricks/aitools/skills/databricks-dabs/SKILL.md
Commit: ade58e4

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.