databricks-dabs
Create, configure, validate, deploy, run, and manage Declarative Automation Bundles (DABs, formerly Databricks Asset Bundles). Use when working with Databricks resources via DABs including dashboards, jobs, pipelines, alerts, volumes, and apps.
62
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/databricks-dabs/SKILL.mdQuality
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 an excellent skill description that clearly communicates specific capabilities, includes natural trigger terms with both the current and former naming conventions, explicitly states both what the skill does and when to use it, and occupies a distinct niche. The description is concise yet comprehensive, covering the full lifecycle of DABs management and enumerating the specific resource types supported.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create, configure, validate, deploy, run, and manage' and specifies the target domain (Declarative Automation Bundles). Also enumerates specific resource types: dashboards, jobs, pipelines, alerts, volumes, and apps. | 3 / 3 |
Completeness | Clearly answers both 'what' (create, configure, validate, deploy, run, and manage DABs) and 'when' ('Use when working with Databricks resources via DABs including dashboards, jobs, pipelines, alerts, volumes, and apps'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'DABs', 'Databricks Asset Bundles', 'Databricks', 'dashboards', 'jobs', 'pipelines', 'alerts', 'volumes', 'apps', 'deploy', 'validate'. Also includes the former name for discoverability. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Databricks DABs specifically. The combination of 'Declarative Automation Bundles', 'DABs', and 'Databricks' creates a very specific trigger profile unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
44%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions well as a routing/index document with excellent progressive disclosure to reference files, but the body itself lacks actionable content and workflow clarity. It over-relies on references without providing a quick-start workflow or concrete examples that would make it immediately useful. The 'When to Use This Skill' section adds little value beyond what the reference list already communicates.
Suggestions
Add a 'Quick Start' section with a concrete, sequenced workflow: e.g., 1. Create bundle (`databricks bundle init`), 2. Configure databricks.yml (show minimal example), 3. Validate (`bundle validate --strict`), 4. Deploy (`bundle deploy --target dev`), 5. Run (`bundle run --target dev <resource>`).
Include a minimal executable databricks.yml example showing a simple resource definition so users can see the expected format without needing to open reference files.
Remove or condense the 'When to Use This Skill' section — the reference list and description already communicate scope, making this section redundant.
Add explicit validation checkpoints and error recovery steps to the workflow (e.g., 'If validate fails, check common issues in deploy-and-run.md#troubleshooting').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'When to Use This Skill' section is somewhat redundant given the description and reference links already make the scope clear. The general guidelines are reasonably concise but include some obvious advice like 'Use reference documentation' and 'Preserve existing structure' that Claude would already know. | 2 / 3 |
Actionability | The skill provides one concrete command (`bundle validate --strict --target <target>`) and mentions a naming convention pattern, but otherwise delegates all actionable content to reference files. There are no executable code examples, no sample YAML configurations, and no concrete workflows in the body itself. | 2 / 3 |
Workflow Clarity | There is no sequenced workflow for any multi-step process. The general guidelines mention validation but don't provide a clear create → configure → validate → deploy → run sequence with checkpoints. For a skill covering deployment and configuration of infrastructure resources, the absence of an explicit workflow with validation/feedback loops is a significant gap. | 1 / 3 |
Progressive Disclosure | The skill is well-structured as an overview with clear, one-level-deep references to five specific reference files. Each reference is clearly labeled with its scope, and the navigation is straightforward. The content is appropriately split between overview and detailed reference materials. | 3 / 3 |
Total | 8 / 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/databricks-agent-skills
- Commit
caf71f1
- 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.