databricks-bundles

Create and configure Declarative Automation Bundles (formerly Asset Bundles) with best practices for multi-environment deployments (CICD). Use when working with: (1) Creating new DAB projects, (2) Adding resources (dashboards, pipelines, jobs, alerts), (3) Configuring multi-environment deployments, (4) Setting up permissions, (5) Deploying or running bundle resources

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with executable bundle configs and commands, weakened by missing validation feedback loops around destructive operations and by broken references to bundle files that are not present.

Suggestions

Add a validate-before-deploy checkpoint and a validate-failure-retry loop to the deployment/destroy workflows so destructive operations have explicit feedback loops.

Either add the referenced SDP_guidance.md and alerts_guidance.md files to the bundle or remove the broken references so navigation is one level deep and real.

Remove the redundant 'Key Principles' section whose path-resolution and permission notes already appear inline, and tighten the verbose log-pattern listing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete YAML and CLI commands, but redundancy like the 'Key Principles' section restating path-resolution rules and a verbose log-pattern list could be tightened.	2 / 3
Actionability	Provides fully executable YAML configurations and copy-paste-ready 'databricks bundle validate/deploy/run/destroy' commands with specific flags and examples.	3 / 3
Workflow Clarity	Deployment and destroy steps are sequenced but destructive operations ('deploy --force', 'destroy') lack explicit validate-then-proceed checkpoints and fix/retry feedback loops, capping this dimension at 2 per the rubric.	2 / 3
Progressive Disclosure	The body signals references to SDP_guidance.md and alerts_guidance.md, but those files do not exist in the bundle, so navigation is broken and the structure is only partially effective.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 description that clearly states capabilities and gives explicit 'Use when...' trigger guidance. The main weakness is trigger-term quality, which leans on product jargon rather than the plain terms users would naturally say.

Suggestions

Add plain-language trigger terms a user would naturally say, e.g. 'Databricks bundle', 'deploy Databricks pipeline/job', alongside the formal 'Declarative Automation Bundles' name.

Consider trimming '(formerly Asset Bundles)' unless that legacy name is a common user trigger, since it adds length without strengthening natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'Create and configure', 'Adding resources (dashboards, pipelines, jobs, alerts)', and 'Setting up permissions', matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ('Create and configure Declarative Automation Bundles...') and when ('Use when working with: (1)...(5)') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Contains relevant keywords ('DAB projects', 'deploying', 'permissions') but leans on technical jargon ('Declarative Automation Bundles', 'Asset Bundles') and misses common variations like 'Databricks bundle' that a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	Clear niche around Databricks bundles with distinct triggers; unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: 4 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Commit: 1c43c21

Reviewed: 3 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.