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 that clearly identifies a specific Databricks technology, includes the former product name for discoverability, and provides explicit 'when' guidance including timing advice. Its main weakness is the lack of specific concrete actions — it says 'develop' but doesn't enumerate what specific tasks it helps with (e.g., defining streaming tables, setting expectations, configuring pipelines).
Suggestions
Add 2-3 specific concrete actions to improve specificity, e.g., 'Define streaming tables, materialized views, and data quality expectations in Lakeflow Spark Declarative Pipelines.'
| 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 tables', 'define expectations', 'configure materialized views', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (develop Lakeflow Spark Declarative Pipelines on Databricks) and 'when' ('Use when building batch or streaming data pipelines with Python or SQL. Invoke BEFORE starting implementation.'). The explicit 'Use when...' clause with timing guidance is well done. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: '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 since many users will still use that term. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific Databricks product (Lakeflow Spark Declarative Pipelines / Delta Live Tables), which is a clear niche unlikely to conflict with general 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 high-quality, comprehensive skill that excels at actionability and progressive disclosure. The decision tree is an outstanding feature that gives Claude unambiguous guidance for choosing dataset types, and the Common Traps section proactively addresses frequent mistakes. The main weakness is moderate verbosity — the inline API reference tables and some redundant content could be trimmed or moved to reference files to reduce token consumption.
Suggestions
Move the large API reference tables (Dataset Definition, Flow/Sink, CDC, Data Quality, Reading Data, Table/Schema, Import/Module) to a separate reference file and link to it, keeping only the most critical quick-reference items inline to improve conciseness.
Remove the orphan 'Language-specific guides' header and the redundant one-line description ('Lakeflow Spark Declarative Pipelines... is a framework for building batch and streaming data pipelines') that appears mid-document after the API tables.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extensive and mostly efficient for its scope, but includes some unnecessary content like the 'Language-specific guides' orphan header, the full CLAUDE.md/AGENTS.md template content that could be in a reference file, and the redundant 'Lakeflow Spark Declarative Pipelines (formerly Delta Live Tables / DLT) is a framework...' line mid-document. The massive API reference tables, while useful, could arguably be in a separate reference file given their length. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: specific CLI commands with flags, exact JSON config files, copy-paste YAML for scheduling, precise API signatures in tables with current vs deprecated syntax, and a clear development workflow with exact commands. The decision tree is exceptionally actionable for choosing the right dataset type. | 3 / 3 |
Workflow Clarity | The development workflow section provides a clear 4-step sequence (validate → deploy → run → check status). The skill explicitly warns about destructive operations (full refresh data loss), mandates deploy-before-run, and includes validation checkpoints. The decision tree provides an unambiguous multi-step decision process, and the 'Common Traps' section serves as an error-recovery guide. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md serves as a comprehensive overview with a decision tree and common traps, then systematically links to detailed reference files organized by feature (streaming-table, materialized-view, auto-cdc, etc.) with clear one-level-deep navigation. The 'Pipeline API Reference' section at the bottom provides well-organized links grouped by category (Project & Lifecycle, Datasets/Flows/Quality). | 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
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.