CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is databricks-jobs in databricks/databricks-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-5

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

The content is highly actionable and well-organized with executable examples throughout, but workflow clarity is capped by missing validation for destructive bundle operations, and progressive disclosure is undermined by four referenced files that are absent from the bundle.

Suggestions

Add an explicit validation checkpoint and feedback loop before destructive/batch operations, e.g. verify "databricks bundle validate" passes and confirm the target before running "bundle destroy --auto-approve".

Create the missing referenced files (task-types.md, triggers-schedules.md, notifications-monitoring.md, examples.md) in a references/ directory, or remove the links and inline the essential content so navigation is not broken.

Trim minor redundant prose such as re-stated CLI basics and obvious explanatory sentences to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is code- and table-heavy with little conceptual padding and assumes Claude's competence, but a few prose sections (re-stating CLI basics, explanatory sentences) could be trimmed. Fits the "efficient; minor over-explanation" anchor above the midpoint.

4 / 5

Actionability

Provides copy-paste-ready executable examples in YAML, Python SDK, and CLI across scaffolding, compute, parameters, operations, and permissions, covering the common cases with specific code rather than pseudocode.

5 / 5

Workflow Clarity

The Development Workflow gives a clear Validate→Deploy→Run→Check sequence, but destructive/batch operations (e.g. "databricks bundle destroy --auto-approve") lack validation checkpoints and feedback loops; per the rubric this caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Structure and signaling are good (reference table plus inline anchor links), but the four referenced files (task-types.md, triggers-schedules.md, notifications-monitoring.md, examples.md) do not exist in the bundle, so navigation is broken and content promised at one level deep is missing.

3 / 5

Total

15

/

20

Passed

Description

88%Weight 40%Scale 1-5

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 specific, complete, and well-triggered, clearly stating both what the skill does and when to use it with concrete task-type examples. Minor gains are possible by adding common synonyms (ETL, scheduling) to widen natural trigger coverage.

DimensionReasoningScore

Specificity

Enumerates concrete actions ("Develop and deploy Lakeflow Jobs") across three concrete mechanisms (DABs, Python SDK, CLI) plus five task types (notebooks, Python wheels, SQL, dbt, pipelines), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (develop/deploy Lakeflow Jobs via three mechanisms) and when ("Use when creating data engineering jobs with..."), plus invocation guidance ("Invoke BEFORE starting implementation").

5 / 5

Trigger Term Quality

Includes natural terms users would say ("data engineering jobs", "notebooks", "SQL", "dbt") but leans product-technical and omits common synonyms like "ETL" or "scheduling"; good but not exhaustive coverage.

4 / 5

Distinctiveness Conflict Risk

A clear Databricks-specific niche with distinct product triggers; only minor overlap risk with the sibling databricks-pipelines skill, hence mostly distinct rather than fully isolated.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 18 missing

Warning

Total

14

/

16

Passed

Repository

databricks/devhub

Path

.databricks/aitools/skills/databricks-jobs/SKILL.md

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.