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
71
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong skill description that clearly defines its scope around Declarative Automation Bundles, lists concrete actions, and provides explicit trigger guidance via a numbered 'Use when' clause. It also helpfully includes the former name ('Asset Bundles') to catch users who may use the older terminology. The description is concise, well-structured, and highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating DAB projects, adding resources (dashboards, pipelines, jobs, alerts), configuring multi-environment deployments, setting up permissions, and deploying/running bundle resources. | 3 / 3 |
Completeness | Clearly answers both 'what' (create and configure DABs with best practices for multi-environment deployments) and 'when' (explicit 'Use when working with...' clause listing five specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Declarative Automation Bundles', 'Asset Bundles', 'DAB', 'dashboards', 'pipelines', 'jobs', 'alerts', 'CICD', 'multi-environment deployments', 'permissions', 'bundle'. Covers both the current and former naming conventions. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Declarative Automation Bundles / Asset Bundles specifically. The domain-specific terminology (DAB, bundle resources, multi-environment CICD) makes it unlikely to conflict with generic deployment or dashboard skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, comprehensive skill that provides actionable YAML configurations and CLI commands for Databricks Asset Bundles across multiple resource types. Its main weakness is the lack of an explicit end-to-end deployment workflow with validation checkpoints, and some sections (particularly Apps and logging) could be more concise. The progressive disclosure and reference structure are well-executed.
Suggestions
Add an explicit numbered deployment workflow (e.g., 1. Validate → 2. Deploy to dev → 3. Verify → 4. Deploy to prod) with validation checkpoints and error recovery steps
Trim the Apps section by removing the comparison table and condensing the logging section into a single 'debug with `databricks apps logs`' line with key error patterns
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete YAML examples and tables, but includes some unnecessary explanations (e.g., the Apps 'Key Differences from Other Resources' table, verbose log pattern descriptions, and the 'What logs show' section add bulk). The Apps section is particularly lengthy and could be tightened. | 2 / 3 |
Actionability | Provides fully executable YAML configurations, concrete CLI commands, and copy-paste ready examples for every resource type. Path resolution is explained with a clear table, and commands include specific flags and target options. | 3 / 3 |
Workflow Clarity | Commands are listed (validate, deploy, run, destroy) suggesting a sequence, but there's no explicit workflow tying them together with validation checkpoints. For a multi-environment deployment skill involving destructive operations (deploy --force, destroy), the lack of an explicit 'validate before deploy' workflow with feedback loops caps this at 2. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, well-signaled one-level-deep references to SDP_guidance.md and alerts_guidance.md, related skills section, and external documentation links. Content is appropriately split between the main file and referenced guides. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
93cb4e3
- 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.