Name: databricks-pipelines
Rating: 66.4 (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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A dense, well-organized index skill with executable commands, exact API signatures, and excellent progressive disclosure pointing to verified one-level-deep reference files. Its weaknesses are a small amount of verbosity (a stub sentence restating the description, some padded trap bullets) and an implicit rather than explicit validate→fix→re-validate feedback loop in the development workflow.

Suggestions

Remove or repurpose the one-line stub under 'Language-specific guides' (it restates the description and explains what DLT is); either delete the heading or replace it with actionable language-specific guidance.

Make the development workflow's feedback loop explicit: after 'Validate', add an 'If validation fails: review errors, fix, and re-validate; only deploy when validation passes' step to earn the workflow-clarity anchor.

Tighten the longest 'Common Traps' bullets so each states the trap and the fix with minimal preamble, reducing token cost without losing the decision guidance.

Dimension	Reasoning	Score
Conciseness	Quotes the stub sentence under 'Language-specific guides' ('Lakeflow Spark Declarative Pipelines (formerly Delta Live Tables / DLT) is a framework for building batch and streaming data pipelines') which restates the description and explains a concept Claude knows, and several padded 'Common Traps' bullets; the API tables are otherwise dense and earn their tokens.	2 / 3
Actionability	Quotes copy-paste-ready commands like 'databricks bundle init lakeflow-pipelines --config-file <(echo ...)' and the numbered workflow ('databricks bundle validate --profile <profile>', 'databricks bundle deploy -t dev'), plus exact API signatures ('@dp.table()', 'CREATE OR REFRESH STREAMING TABLE', 'dp.create_auto_cdc_flow()') and a concrete YAML scheduling snippet.	3 / 3
Workflow Clarity	Quotes the sequenced 'Development Workflow' (Validate → Deploy → Run → Check status) and strong safety notes ('You must deploy before running', 'Full refresh is the most expensive and dangerous option... used only when really necessary'), but the validate→fix→re-validate feedback loop is implied by ordering rather than an explicit retry checkpoint.	2 / 3
Progressive Disclosure	Quotes the 'MANDATORY: Before implementing...you MUST read the linked reference file' signal plus the API tables and final reference list mapping each feature to one-level-deep links like '[streaming-table-python](streaming-table/streaming-table-python.md)'; all referenced files verified present and detail is appropriately split across ~30 reference docs.	3 / 3
	Total	10 / 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 focused, third-person description that explicitly answers both what it does and when to use it, with strong trigger-term coverage including the legacy product name. The only weakness is specificity: it names the domain and one core action rather than enumerating multiple distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Quotes 'Develop Lakeflow Spark Declarative Pipelines' and 'building batch or streaming data pipelines with Python or SQL' — names the domain and core action, but presents one main action with modifiers rather than a list of multiple distinct concrete actions.	2 / 3
Completeness	Quotes 'Develop Lakeflow Spark Declarative Pipelines...on Databricks' (what) and an explicit 'Use when building batch or streaming data pipelines with Python or SQL' trigger (when), plus the extra 'Invoke BEFORE starting implementation' behavioral trigger — both what and when are explicit.	3 / 3
Trigger Term Quality	Quotes 'batch or streaming data pipelines', 'Python or SQL', 'Delta Live Tables' (the legacy name users still say), and 'Lakeflow Spark Declarative Pipelines' — good coverage of natural terms a Databricks user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped to Lakeflow/DLT declarative pipelines on Databricks with Python/SQL and batch/streaming framing, and defers CLI basics to a parent 'databricks-core' skill — a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 52 missing	Warning

	Total	14 / 16 Passed

Repository: databricks/devhub
Commit: 131db95

Reviewed: 5 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.