CtrlK
BlogDocsLog inGet started
Tessl Logo

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

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 complete, executable configuration examples and clear command coverage, but it is somewhat verbose and monolithic and lacks an explicit validation feedback loop in the deploy workflow.

Suggestions

Add an explicit validate -> fix -> re-validate -> deploy feedback loop (e.g., 'Run databricks bundle validate; if errors, fix and re-validate; only deploy when validation passes') to lift workflow_clarity.

Remove the repeated path-resolution guidance, keeping it in one canonical place (the table) and referencing it from Common Issues / Key Principles to improve conciseness.

Either provide the referenced SDP_guidance.md and alerts_guidance.md as bundle files or inline their essential content, so signaled references resolve to real files and progressive disclosure is sound.

DimensionReasoningScore

Conciseness

Mostly efficient and dominated by executable YAML/CLI examples, but path resolution is repeated across three sections (detailed table, Common Issues row, Key Principles #1) and the apps section is lengthy, so it could be tightened.

2 / 3

Actionability

Provides complete, copy-paste-ready YAML for databricks.yml, dashboards, jobs, volumes, and apps plus concrete CLI commands (validate/deploy/run/destroy), fully executable rather than pseudocode.

3 / 3

Workflow Clarity

A validate-before-deploy sequence and an error-recovery Common Issues table exist, but there is no explicit validate -> fix -> re-validate feedback loop tying validation into the deploy workflow, which caps clarity given destructive operations (destroy --auto-approve).

2 / 3

Progressive Disclosure

References to SDP_guidance.md and alerts_guidance.md are clearly signaled and one level deep, but those files are not present in the bundle and the body inlines substantial detail (apps, volumes, jobs) that a leaner overview would split out.

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.

The description is specific, complete, and uses natural third-person voice with an explicit 'Use when' trigger clause covering five distinct scenarios. It is concise yet comprehensive, with no vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Create and configure", "Adding resources (dashboards, pipelines, jobs, alerts)", "Setting up permissions", "Deploying or running bundle resources" — matching the anchor for several specific concrete actions.

3 / 3

Completeness

Clearly answers both what ("Create and configure Declarative Automation Bundles ... with best practices for multi-environment deployments") and when via the explicit "Use when working with: (1)...(5)..." trigger clause.

3 / 3

Trigger Term Quality

Good coverage of natural terms a Databricks user would say: "Declarative Automation Bundles", "Asset Bundles", "dashboards, pipelines, jobs, alerts", "multi-environment deployments", "permissions", "CICD".

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (Declarative Automation Bundles / formerly Asset Bundles) with a specific numbered trigger list, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing, 4 suspicious

Warning

Total

15

/

16

Passed

Repository
databricks-solutions/ai-dev-kit
Reviewed

Table of Contents

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.