databricks-pipelines
Develop Lakeflow Spark Declarative Pipelines (formerly Delta Live Tables) on Databricks. Use when building batch or streaming data pipelines with Python or SQL. Invoke BEFORE starting implementation.
71
87%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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 description with excellent trigger term coverage (including the former product name), clear 'when' guidance, and a highly distinctive niche. Its main weakness is the lack of specific concrete actions — it says 'Develop' but doesn't enumerate what specific capabilities the skill provides (e.g., defining streaming tables, setting data quality expectations, configuring materialized views).
Suggestions
Add 2-3 specific concrete actions to improve specificity, e.g., 'Define streaming tables, materialized views, and data quality expectations using Lakeflow Spark Declarative Pipelines.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Lakeflow Spark Declarative Pipelines / Delta Live Tables on Databricks) and mentions batch/streaming data pipelines with Python or SQL, but doesn't list specific concrete actions beyond 'Develop'. Lacks detail on what specific operations it performs (e.g., define tables, configure streaming sources, set expectations/quality rules). | 2 / 3 |
Completeness | Clearly answers both 'what' (develop Lakeflow Spark Declarative Pipelines on Databricks) and 'when' (when building batch or streaming data pipelines with Python or SQL, invoke before starting implementation). The explicit 'Use when...' clause and timing guidance ('BEFORE starting implementation') are present. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords: 'Lakeflow', 'Spark', 'Declarative Pipelines', 'Delta Live Tables', 'Databricks', 'batch', 'streaming', 'data pipelines', 'Python', 'SQL'. The inclusion of the former name 'Delta Live Tables' is excellent for matching users who may use either term. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific Databricks product (Lakeflow Spark Declarative Pipelines / Delta Live Tables). Unlikely to conflict with general Python, SQL, or even other Databricks skills due to the precise product naming. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that serves as an effective hub for Lakeflow Spark Declarative Pipelines development. The decision tree is particularly valuable for guiding dataset type selection, and the common traps section prevents frequent mistakes. The API reference tables are comprehensive but contribute to the skill's length — though this is partially justified by the breadth of the framework and the clear progressive disclosure to detailed reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and packed with useful reference information, but the extensive API reference tables are very long and could arguably be split into a separate reference file. The decision tree and common traps sections are well-targeted, though some trap explanations are slightly verbose. The CLAUDE.md/AGENTS.md template content adds bulk that could be more concise. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (bundle init with exact flags, bundle deploy/run/validate commands, YAML config examples, scheduling job YAML), a clear decision tree for choosing dataset types, and specific API mappings with current vs deprecated syntax. The scaffolding command is copy-paste ready with clear parameter explanations. | 3 / 3 |
Workflow Clarity | The development workflow is clearly sequenced (validate → deploy → run → check status) with explicit warnings about deploying before running. The decision tree provides an unambiguous flowchart for choosing dataset types. The 'Common Traps' section serves as validation guidance, and the warning about full refresh being dangerous with data loss risk acts as a safety checkpoint. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md provides a comprehensive overview with decision tree, common traps, and API reference tables, then links to detailed per-feature reference files (streaming-table-python.md, auto-cdc-sql.md, etc.) that are one level deep. The mandatory instruction to read linked references before implementing ensures proper navigation. References are clearly organized by feature and language. | 3 / 3 |
Total | 11 / 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.