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
76
63%
Does it follow best practices?
Impact
100%
2.63xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/content-moderator/template/.agents/skills/databricks-dabs/SKILL.mdQuality
Discovery
82%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 description with excellent specificity and distinctiveness, clearly enumerating both the actions and the Databricks resource types it covers. The inclusion of both the current name (DABs/Declarative Automation Bundles) and former name (Databricks Asset Bundles) is a smart touch for trigger term coverage. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Databricks bundles, DABs, deploying Databricks resources, or managing Databricks jobs/pipelines/dashboards.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions ('create, configure, validate, deploy, run, and manage') and enumerates specific resource types ('dashboards, jobs, pipelines, alerts, volumes, and apps'). Very detailed about what the skill does. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions and resource types, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'DABs', 'Declarative Automation Bundles', 'Databricks Asset Bundles', 'Databricks', 'dashboards', 'jobs', 'pipelines', 'deploy'. Also helpfully notes the former name, covering both old and new terminology users might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'DABs', 'Declarative Automation Bundles', and 'Databricks' are very specific domain terms that are unlikely to conflict with other skills. The enumeration of Databricks-specific resource types further narrows the niche. | 3 / 3 |
Total | 11 / 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 it lacks the actionable, concrete guidance and clear workflow sequencing needed to be a strong standalone skill. The body is mostly directional pointers rather than executable instructions, and the absence of a defined multi-step workflow for the core create-validate-deploy cycle is a notable weakness.
Suggestions
Add a concrete quick-start workflow with numbered steps (e.g., 1. Create bundle with `databricks bundle init`, 2. Configure databricks.yml, 3. Validate with `bundle validate --strict`, 4. Deploy with `bundle deploy --target dev`, 5. Run with `bundle run`) including validation checkpoints and error recovery guidance.
Include a minimal executable databricks.yml example showing a basic resource definition so Claude has a concrete starting template without needing to consult reference files.
Remove the 'When to Use This Skill' section — this is metadata for skill selection that Claude can infer from the description and opening line, saving token budget for more actionable content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'When to Use This Skill' section is somewhat redundant given the opening line already states the scope. The general guidelines are reasonably tight 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, but lacks executable code examples, specific YAML snippets, or copy-paste ready configurations. Most guidance is directional rather than concrete, deferring to reference files. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow defined. The general guidelines mention validation but don't sequence the full create → configure → validate → deploy → run workflow. For a skill covering deployment and configuration of infrastructure resources, the absence of an explicit workflow with validation checkpoints 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 labeled with its purpose, making navigation easy and content appropriately split between the overview and detailed guides. | 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/devhub
- Commit
0b6297e
- 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.