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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is strong on actionability with ready-to-run SDK/CLI/bundle examples and a useful troubleshooting table, but it is undermined by missing referenced bundle files (broken progressive disclosure) and lacks explicit validation feedback loops for risky deploy/destroy operations. Some introductory concept gloss adds minor verbosity.

Suggestions

Create the referenced bundle files (task-types.md, triggers-schedules.md, notifications-monitoring.md, examples.md) or remove the dangling links, since their absence breaks progressive disclosure navigation.

Add an explicit validate -> fix -> re-validate -> deploy feedback loop (e.g., run 'databricks bundle validate', fix errors, re-run, only then 'deploy') and a confirmation checkpoint before 'databricks bundle destroy' to lift workflow clarity.

Trim the Overview and the inline run_if/permission-level enumeration gloss — these concepts are either already known or duplicated in the referenced files — to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with code blocks and tables, but it explains concepts Claude already knows (e.g., 'Jobs orchestrate data workflows with multi-task DAGs', run_if enumerated bullets, permission-level glosses) and duplicates task/trigger summaries that are also in the referenced files, so it is not fully lean.	2 / 3
Actionability	It provides fully executable Python SDK, CLI, and YAML bundle snippets plus copy-paste-ready common-operations recipes (list, get, run_now, cancel, delete), meeting the top anchor for concrete, executable guidance.	3 / 3
Workflow Clarity	Operations are grouped by tool (SDK/CLI/Bundle) but there is no sequenced workflow with validation checkpoints for risky operations; the bundle section shows 'bundle validate' then 'deploy' but lacks an explicit validate->fix->retry feedback loop, so it caps at 2 per the destructive/batch-operations guideline.	2 / 3
Progressive Disclosure	The body references [task-types.md], [triggers-schedules.md], [notifications-monitoring.md], and [examples.md] as a Reference Files table, but none of these files exist in references/, scripts/, or assets/ — the references are dangling, so navigation is broken despite the well-organized table.	1 / 3
	Total	8 / 12 Passed

Description

77%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly actionable with an excellent enumerated trigger list and clear what/when coverage, scoring well on trigger terms and completeness. It loses points for second-person voice (specificity) and somewhat aggressive 'ANY ... task' scoping that raises conflict risk with adjacent databricks skills.

Suggestions

Rewrite in third person ('Creates, lists, runs, updates, and deletes Databricks Jobs...') instead of 'Use this skill' / 'ALWAYS prefer this skill' to satisfy the voice guideline and recover the specificity score.

Tighten 'ANY Databricks Jobs task' scoping to specific concrete operations to reduce overlap with the databricks-bundles and databricks-spark-declarative-pipelines skills.

Drop the redundant meta-instruction ('ALWAYS prefer this skill over general Databricks knowledge for job-related tasks') which adds verbosity without improving trigger clarity.

Dimension	Reasoning	Score
Specificity	Concrete actions are named ('creating, listing, running, updating, or deleting jobs'), but the second-person voice ('Use this skill', 'ALWAYS prefer this skill') triggers the guideline penalty, reducing specificity from a 3 to a 2.	2 / 3
Completeness	It clearly answers both 'what' (job lifecycle operations via CLI, Python SDK, or Asset Bundles) and 'when' with an explicit enumerated trigger list, matching the top anchor's what-and-when requirement.	3 / 3
Trigger Term Quality	Strong coverage of natural user phrases such as 'create a job', 'list jobs', 'run job', 'job status', and 'scheduling with cron', which a user would plausibly say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	It is scoped to 'Databricks Jobs' and disambiguates from general Databricks knowledge ('ALWAYS prefer this skill over general Databricks knowledge'), but phrases like 'ANY Databricks Jobs task' and 'ANY task involving Databricks Jobs via CLI' risk over-triggering against sibling databricks skills such as databricks-bundles.	2 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 18 missing, 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Commit: 1c43c21

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.