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.
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/saas-tracker/template/.agents/skills/databricks-jobs/SKILL.mdQuality
Discovery
89%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 solid skill description that clearly identifies its niche (Lakeflow Jobs on Databricks), provides explicit trigger guidance with a 'Use when' clause, and includes distinctive terminology that minimizes conflict risk. The main weakness is that the specificity of concrete actions could be stronger—'develop and deploy' is somewhat general, and listing more specific capabilities (e.g., configuring job clusters, setting schedules, managing dependencies) would improve it.
Suggestions
Expand the concrete actions beyond 'develop and deploy' to include more specific capabilities like 'configure job clusters, set schedules, manage task dependencies, handle job parameters'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Lakeflow Jobs on Databricks) and some actions ('develop and deploy', 'creating data engineering jobs'), and mentions specific task types (notebooks, Python wheels, SQL tasks), but doesn't list multiple concrete actions beyond develop/deploy. | 2 / 3 |
Completeness | Clearly answers both 'what' (develop and deploy Lakeflow Jobs on Databricks) and 'when' (when creating data engineering jobs with notebooks, Python wheels, or SQL tasks), with an explicit 'Use when' clause and an additional timing directive ('BEFORE starting implementation'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lakeflow Jobs', 'Databricks', 'data engineering jobs', 'notebooks', 'Python wheels', 'SQL tasks'. These cover the main terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific triggers like 'Lakeflow Jobs', 'Databricks', and the combination of 'Python wheels' and 'SQL tasks' in a data engineering context. Unlikely to conflict with other skills due to the narrow, well-defined niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent concrete examples and executable commands for Lakeflow Jobs development. Its main weaknesses are the lack of error recovery/validation feedback loops in the deployment workflow and some redundancy in examples (e.g., task configuration shown twice in slightly different forms). The CLAUDE.md/AGENTS.md template content adds bulk that could potentially be handled differently.
Suggestions
Add explicit error recovery steps to the Development Workflow section (e.g., 'If validate fails: check YAML syntax and resource references; if deploy fails: verify profile permissions and target configuration').
Remove or consolidate the duplicate task configuration examples — the Multi-Task Jobs section largely repeats the Configuring Tasks section with minor additions.
Consider moving the CLAUDE.md/AGENTS.md template content to a separate reference file or generating it via a script, as it adds significant length without being core job development guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good YAML/code examples, but includes some unnecessary content like the full CLAUDE.md/AGENTS.md template (which is boilerplate), the project structure diagram that largely repeats what the scaffolding command creates, and the multi-task dependencies example which is very similar to the earlier task configuration example. The notebook code section explains basic Spark operations Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable commands (bundle init with config-file, bundle validate/deploy/run), complete YAML configurations for job definitions, scheduling, and dependencies, and working Python code for notebook tasks. All examples are copy-paste ready with clear parameter placeholders. | 3 / 3 |
Workflow Clarity | The Development Workflow section provides a clear 4-step sequence (validate → deploy → run → check status), but lacks explicit validation checkpoints and error recovery guidance. There's no feedback loop for what to do if validation fails, deployment errors occur, or job runs fail. For a workflow involving deployment operations, this gap is notable. | 2 / 3 |
Progressive Disclosure | The skill references a parent 'databricks-core' skill and links to external documentation, which is good. However, the content is somewhat monolithic — the CLAUDE.md template, multiple YAML examples, and notebook code could be better organized. No bundle files are provided to offload detailed reference material, and the inline content is lengthy for a single file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- databricks/devhub
- Commit
0b6297e
- 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.