Name: databricks-jobs
Rating: 67.2 (1 reviews)
Author: databricks

databricks-jobs

Develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or the CLI. Use when creating data engineering jobs with notebooks, Python wheels, SQL, dbt, or pipelines. Invoke BEFORE starting implementation.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 body is highly actionable and well-structured with one-level-deep references, but it is somewhat long with mild redundancy and lacks an explicit error-recovery feedback loop in the deploy workflow. Overall a solid, executable skill body.

Suggestions

Add an explicit validate→fix→re-validate feedback loop in the Development Workflow so deploy/destroy operations have a recovery checkpoint.

De-duplicate job-creation examples between the Quick Start and Common Operations sections, or cross-reference one from the other, to tighten the token budget.

Consider condensing the inline CLAUDE.md/AGENTS.md template or moving it into a reference file to reduce body length.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with code and tables earning their place, but job-creation examples recur across Quick Start and Common Operations and the CLAUDE.md/AGENTS.md scaffolding template is lengthy. It is not 3 because it could be tightened, and not 1 because it avoids explaining concepts Claude already knows.	2 / 3
Actionability	Executable YAML, Python SDK, and bash CLI snippets are copy-paste ready, with concrete values for spark_version, node_type_id, parameters, and permissions. Not below 3 because guidance is specific and complete rather than pseudocode.	3 / 3
Workflow Clarity	The Development Workflow lists Validate → Deploy → Run → Check status, a clear sequence with a validation step, but there is no explicit validate→fix→retry feedback loop for destructive/batch operations like deploy and destroy. Per the rubric this caps it at 2 rather than 3.	2 / 3
Progressive Disclosure	A Reference Files table plus task-type and trigger summary tables link one level deep to real files (references/task-types.md, triggers-schedules.md, notifications-monitoring.md, examples.md), splitting detail appropriately. Not below 3 because navigation is clear and references are not nested.	3 / 3
	Total	10 / 12 Passed

Description

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.

The description is strong: it states concrete capabilities, includes natural trigger terms, explicitly covers both what and when, and occupies a distinct niche. Voice is correctly third person ("Develop and deploy").

Dimension	Reasoning	Score
Specificity	"Develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or the CLI" plus "creating data engineering jobs with notebooks, Python wheels, SQL, dbt, or pipelines" lists multiple concrete actions and specific task types. It is not below 3 because the actions are named concretely rather than vaguely, and not above since 3 is the cap.	3 / 3
Completeness	"Develop and deploy Lakeflow Jobs on Databricks" answers what, and "Use when creating data engineering jobs with notebooks, Python wheels, SQL, dbt, or pipelines. Invoke BEFORE starting implementation" gives explicit when triggers. Clearly answers both what AND when, so it is not capped at 2.	3 / 3
Trigger Term Quality	"data engineering jobs with notebooks, Python wheels, SQL, dbt, or pipelines" plus "DABs, Python SDK, or the CLI" are natural terms users would say when they need this skill. Good coverage of common variations; not below 3 because key user-facing terms are present.	3 / 3
Distinctiveness Conflict Risk	"Lakeflow Jobs on Databricks" is a clear niche with distinct triggers unlikely to fire for unrelated skills. Minor overlap with sibling pipeline skills via the word "pipelines", but the jobs framing keeps it distinguishable, so it stays at 3 rather than 2.	3 / 3
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: databricks/databricks-agent-skills
Path: skills/databricks-jobs/SKILL.md
Commit: 3d79814

Reviewed: 2 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.