databricks-jobs
Use this skill proactively for ANY Databricks Jobs task - creating, listing, running, updating, or deleting jobs. Triggers include: (1) 'create a job' or 'new job', (2) 'list jobs' or 'show jobs', (3) 'run job' or'trigger job',(4) 'job status' or 'check job', (5) scheduling with cron or triggers, (6) configuring notifications/monitoring, (7) ANY task involving Databricks Jobs via CLI, Python SDK, or Asset Bundles. ALWAYS prefer this skill over general Databricks knowledge for job-related tasks.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%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 trigger term coverage and clear enumeration of both capabilities and when to use the skill. The main weakness is the use of second-person voice ('Use this skill') and the somewhat defensive positioning against other Databricks skills, which hints at potential overlap issues. The description is slightly verbose but compensates with high specificity and completeness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating, listing, running, updating, deleting jobs, scheduling with cron/triggers, configuring notifications/monitoring, and specifies tools (CLI, Python SDK, Asset Bundles). | 3 / 3 |
Completeness | Clearly answers both 'what' (creating, listing, running, updating, deleting Databricks Jobs, scheduling, notifications) and 'when' with explicit trigger phrases enumerated in a numbered list. The 'Use this skill proactively for ANY Databricks Jobs task' serves as a clear when-clause. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a job', 'new job', 'list jobs', 'show jobs', 'run job', 'trigger job', 'job status', 'check job', plus mentions of cron, notifications, monitoring, and Databricks Jobs. | 3 / 3 |
Distinctiveness Conflict Risk | While it carves out a clear niche around Databricks Jobs specifically, the final sentence 'ALWAYS prefer this skill over general Databricks knowledge' suggests there are overlapping skills, and the broad scope ('ANY task involving Databricks Jobs') could still conflict with other Databricks-related skills covering workflows, clusters, or notebooks that touch jobs. | 2 / 3 |
Total | 11 / 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 well-structured, highly actionable skill that covers Databricks Jobs comprehensively across three interfaces. Its progressive disclosure is exemplary with clear navigation to reference files. The main weaknesses are moderate verbosity (some inline content could be offloaded to reference files) and the lack of explicit validation/error-recovery steps in workflows.
Suggestions
Add a validation feedback loop for job creation workflows (e.g., verify job exists after creation, check run status after triggering, handle common errors)
Consider moving the Compute Configuration and Job Parameters sections to a separate reference file to reduce the main SKILL.md size, keeping only a brief summary with links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and code examples, but includes some content that could be trimmed—like the full task types and trigger types summary tables that essentially just duplicate what's in the referenced files. The compute configuration section and parameters section add bulk that could be offloaded to reference files. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples across all three interfaces (Python SDK, CLI, Asset Bundles). The Quick Start section is copy-paste ready, common operations provide complete working commands, and parameter usage shows both definition and access patterns. | 3 / 3 |
Workflow Clarity | The multi-task DAG workflow is clearly shown with dependency configuration and run_if conditions, and the Asset Bundle operations show a validate-deploy-run sequence. However, there are no explicit validation checkpoints or error recovery feedback loops for job creation/update workflows—e.g., no guidance on verifying a job was created correctly or handling deployment failures. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference files table at the top pointing to task-types.md, triggers-schedules.md, notifications-monitoring.md, and examples.md. Summary tables in the main file link to specific anchors in reference files, providing a well-structured one-level-deep navigation pattern. | 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.