Name: databricks-pipelines
Rating: 76 (1 reviews)
Author: databricks

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.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplar skill body: lean and actionable, with well-sequenced workflows, explicit validation/polling checkpoints, and a clean progressive-disclosure structure pointing to real reference files. No significant weaknesses.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich — decision trees, tables, and error mappings — with no padding explaining concepts Claude already knows; every line earns its place.	3 / 3
Actionability	Provides fully executable guidance: exact API decorators ('@dp.table()', 'CREATE OR REFRESH STREAMING TABLE'), concrete CLI commands ('databricks bundle deploy -t dev'), and precise error→fix strings.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (Decision Tree, Workflows A/B/C, deploy→validate→run→poll) with an explicit validation checkpoint ('Always poll the update') and a data-loss caution around full refresh.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview that maps each feature to a one-level-deep reference file via API tables and a Reference Index; all referenced paths resolve to real files in references/.	3 / 3
	Total	12 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with an explicit trigger clause and good natural keyword coverage. Its only weakness is specificity: it states the domain and a broad action rather than listing several concrete capabilities.

Suggestions

List a few concrete actions (e.g., 'define streaming tables and materialized views, add Auto CDC flows, set expectations, deploy via DAB bundles') to lift specificity from level 2 to level 3.

Consider adding a trigger term like 'Delta Live Tables / DLT' alongside 'Lakeflow' since users still commonly say the legacy name.

Dimension	Reasoning	Score
Specificity	Names the domain ('Lakeflow Spark Declarative Pipelines (formerly Delta Live Tables) on Databricks') and the broad action ('building batch or streaming data pipelines with Python or SQL'), but does not enumerate multiple specific concrete actions like the level-3 anchor requires.	2 / 3
Completeness	Explicitly states what it does ('Develop...Pipelines...on Databricks') and when to use it ('Use when building batch or streaming data pipelines with Python or SQL'), satisfying both what and when.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'data pipelines', 'batch or streaming', 'Python or SQL', 'Delta Live Tables', and 'Databricks' — alongside the technical product name.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Databricks Lakeflow/DLT pipelines) with distinct triggers and a named parent skill, making overlap with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: databricks/databricks-agent-skills
Path: skills/databricks-pipelines/SKILL.md
Commit: 3d79814

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.