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.
70
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong skill description that clearly identifies a specific domain (Databricks Lakeflow Jobs), lists concrete actions (develop and deploy), specifies multiple tools and methods, and provides explicit trigger guidance with a broad set of natural keywords. The additional instruction to invoke before starting implementation adds useful behavioral guidance. Minor improvement could include mentioning 'workflow' or 'orchestration' as additional trigger terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and technologies: 'Develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or the CLI' names the platform, the artifact type, and three distinct methods of interaction. | 3 / 3 |
Completeness | Clearly answers both 'what' (develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or CLI) and 'when' (when creating data engineering jobs with notebooks, Python wheels, SQL, dbt, or pipelines), plus includes an explicit invocation instruction ('Invoke BEFORE starting implementation'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lakeflow Jobs', 'Databricks', 'DABs', 'Python SDK', 'CLI', 'notebooks', 'Python wheels', 'SQL', 'dbt', 'pipelines', 'data engineering jobs'. These cover a wide range of terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Lakeflow Jobs on Databricks is a very specific domain. The combination of platform (Databricks), artifact (Lakeflow Jobs), and tooling (DABs, Python SDK, CLI) makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong actionability and progressive disclosure. It provides concrete, executable examples across multiple interfaces (DABs, SDK, CLI) and effectively uses reference files for detailed content. The main weaknesses are moderate verbosity in some sections (particularly the scaffolding template and duplicated summary tables) and a development workflow that lacks explicit error recovery and validation feedback loops.
Suggestions
Add explicit error recovery steps to the Development Workflow (e.g., 'If validate fails: review error output, fix YAML syntax, re-validate before proceeding').
Trim the task types and trigger types summary tables since they primarily duplicate navigation already provided in the Reference Files table at the top.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some content that could be tightened. The scaffolding section with the full CLAUDE.md/AGENTS.md template is borderline verbose, and the task/trigger summary tables duplicate what's already in the referenced files. However, most sections are reasonably efficient and the code examples are lean. | 2 / 3 |
Actionability | The skill provides fully executable code examples across three approaches (DABs YAML, Python SDK, CLI), with copy-paste ready commands for all common operations. Scaffolding commands, deployment workflows, and parameter access patterns are all concrete and specific. | 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 feedback loops. There's no 'if validation fails, do X' guidance, and the workflow for scaffolding a new project doesn't include verification steps after creation. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference files table at the top pointing to task types, triggers, notifications, and examples in separate files. The main SKILL.md provides concise summaries with links to deeper content, and the task/trigger summary tables serve as navigation aids with direct anchor links to reference files. | 3 / 3 |
Total | 10 / 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/databricks-agent-skills
- Commit
caf71f1
- 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.