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.
89
87%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 skill description with excellent trigger term coverage (including the former product name), clear when-to-use guidance, and strong distinctiveness through specific product naming. The main weakness is that it could be more specific about the concrete actions it enables (e.g., creating streaming tables, defining data quality expectations, configuring pipeline settings) rather than staying at the high level of 'develop pipelines'.
Suggestions
Add specific concrete actions like 'create materialized views, define streaming tables, configure data quality expectations, set up pipeline clusters' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Lakeflow Spark Declarative Pipelines / Delta Live Tables on Databricks) and mentions batch/streaming data pipelines with Python or SQL, but does not list specific concrete actions like 'create materialized views', 'define streaming tables', 'configure expectations', etc. | 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), plus includes an explicit invocation instruction ('Invoke BEFORE starting implementation'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lakeflow', 'Spark', 'Declarative Pipelines', 'Delta Live Tables', 'Databricks', 'batch', 'streaming', 'data pipelines', 'Python', 'SQL'. The inclusion of the former name 'Delta Live Tables' is especially helpful for users who know the old terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific product names (Lakeflow Spark Declarative Pipelines, Delta Live Tables, Databricks) that create a clear niche unlikely to conflict with generic data engineering or other pipeline skills. | 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, common traps, and API reference tables provide high-value guidance, and the progressive disclosure to detailed reference files is excellent. The main weakness is that the comprehensive API reference tables are quite lengthy for an overview skill and could potentially be split into a separate reference file to improve conciseness.
Suggestions
Consider moving the detailed API reference tables (Dataset Definition, Flow/Sink, CDC, Data Quality, Reading Data, Table/Schema, Import/Module) into a separate REFERENCE.md file and linking to it from the main skill, keeping only the most essential tables inline.
| 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 be better placed in a separate reference file. The decision tree and common traps sections are well-targeted, but the sheer volume (300+ lines) pushes beyond what's needed as an overview skill. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (bundle init with exact flags, bundle deploy/run commands, YAML config examples), specific code patterns (import statements, API calls), and a clear decision tree for choosing the right approach. The scaffolding section is copy-paste ready. | 3 / 3 |
Workflow Clarity | The development workflow is clearly sequenced (validate → deploy → run → check status) with explicit validation steps. The skill emphasizes deploying before running, warns about full refresh dangers, and the decision tree provides clear branching logic for choosing dataset types. The common traps section serves as an effective error-prevention checklist. | 3 / 3 |
Progressive Disclosure | The skill is an excellent overview that points to detailed reference files for each feature (streaming tables, materialized views, auto loader, auto CDC, expectations, sinks, etc.) with clear one-level-deep links. The API reference tables serve as a navigation index with links to specific skill files for each feature, and the Pipeline API Reference section at the bottom provides well-organized links to detailed guides. | 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/databricks-agent-skills
- Commit
f1c9cf7
- 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.