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.
86
82%
Does it follow best practices?
Impact
Pending
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 skill description that clearly enumerates specific capabilities and provides extensive trigger terms users would naturally use. The explicit numbered trigger list is effective for skill selection. The main weakness is the use of second-person voice ('Use this skill') and the potential for overlap with other Databricks-related skills, which the description tries to address with a priority directive rather than clearer scoping.
| 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 with various tools) and 'when' (explicit trigger phrases and scenarios listed with numbered items). 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 other Databricks skills it could conflict with. The broad 'ANY task involving Databricks Jobs' could overlap with general Databricks skills. | 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 skill that excels in actionability and progressive disclosure, providing executable examples across three interfaces and clear navigation to detailed reference files. The main weaknesses are moderate verbosity (some sections like compute configuration and summary tables could be tighter) and missing validation/feedback loops in multi-step workflows like deployment and job management. The Common Issues table is a practical addition that adds real value.
Suggestions
Add explicit validation checkpoints to the Asset Bundle workflow (e.g., 'validate output before deploying, check deployment status before running') and a feedback loop for error recovery after 'bundle destroy'.
Condense the Compute Configuration section by showing only the recommended pattern (job clusters) inline and moving alternatives (autoscaling, existing cluster, serverless) to a reference file or collapsing them into a brief summary table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes some content that could be more concise. The task types and trigger types summary tables duplicate information that's already in the referenced files. The compute configuration section is fairly lengthy with multiple variants that could be condensed. However, it avoids explaining basic concepts Claude would already know. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples across three interfaces (Python SDK, CLI, Asset Bundles). The Quick Start section provides copy-paste ready examples, and the Common Operations section covers all CRUD operations with concrete, specific commands and parameters. | 3 / 3 |
Workflow Clarity | The multi-task DAG workflow is clearly explained with dependency conditions, and Asset Bundle operations show a logical sequence (validate → deploy → run). However, there are no explicit validation checkpoints or feedback loops for error recovery in the job creation/deployment workflows, which involve potentially destructive operations like 'bundle destroy'. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference table at the top pointing to one-level-deep files (task-types.md, triggers-schedules.md, notifications-monitoring.md, examples.md). The main file serves as a well-organized overview with summary tables that link to detailed sections in reference files, and inline content is appropriately scoped. | 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
b4071a0
- 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.