CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-jobs

Develop and deploy Lakeflow Jobs on Databricks. Use when creating data engineering jobs with notebooks, Python wheels, or SQL tasks. Invoke BEFORE starting implementation.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/databricks-jobs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A highly actionable, code-dense skill body that covers the full job lifecycle with executable examples. Its main weaknesses are repeated YAML scaffolding, an inlined project template that bloats token budget, and the absence of reference files for deeper material.

Suggestions

Extract the embedded CLAUDE.md/AGENTS.md template and the detailed task-type configuration reference into files under ./references/ and link to them one level deep to improve progressive disclosure and conciseness.

Reduce repeated YAML by showing the `resources: jobs:` skeleton once and only diffing the relevant field (parameters, trigger, depends_on) in subsequent sections.

Add an explicit feedback loop to the Development Workflow (e.g., "If `bundle validate` fails, fix the config and re-validate before deploying") to strengthen the validation checkpoint for the destructive deploy step.

DimensionReasoningScore

Conciseness

The body is mostly code with little prose padding, but the full `resources: jobs:` YAML skeleton is repeated across four sections and the embedded CLAUDE.md/AGENTS.md template is a chunk of content that could be tightened or externalized.

3 / 5

Actionability

It provides copy-paste-ready commands (`databricks bundle init ...`, `uv run pytest`) and complete YAML/Python examples covering scaffolding, task config, parameters, scheduling, dependencies, and the deploy workflow.

5 / 5

Workflow Clarity

The Development Workflow section gives a clear Validate → Deploy → Run → Check-status sequence with a validation checkpoint, but it lacks an explicit validate→fix→retry feedback loop for the risky deploy step.

4 / 5

Progressive Disclosure

Section headers organize the ~180-line body well, but no bundle/reference files exist and content that could be split out (the CLAUDE.md template, detailed task-config reference) is inlined rather than referenced one level deep.

3 / 5

Total

15

/

20

Passed

Description

78%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.

A strong, third-person description that clearly states both capability and trigger conditions with concrete task-type examples. It could broaden trigger-term synonyms and enumerate a few more actions for full comprehensiveness.

DimensionReasoningScore

Specificity

"Develop and deploy Lakeflow Jobs on Databricks" names the domain and two concrete actions, reinforced by task types (notebooks, Python wheels, SQL tasks), but coverage is not comprehensive (scheduling, parameters, monitoring absent).

3 / 5

Completeness

It explicitly answers both what ("Develop and deploy Lakeflow Jobs on Databricks") and when ("Use when creating data engineering jobs...") with concrete trigger phrases, plus an explicit invocation directive.

5 / 5

Trigger Term Quality

"Use when creating data engineering jobs with notebooks, Python wheels, or SQL tasks" provides good natural keyword coverage, though common synonyms like "scheduled workflows" or "ETL pipelines" are missing.

4 / 5

Distinctiveness Conflict Risk

"Lakeflow Jobs on Databricks" with specific task types is a clear niche with minimal conflict risk, though the stated parent databricks-core skill creates minor overlap with closely related skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
databricks/devhub
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.