databricks-spark-declarative-pipelines

Creates, configures, and updates Databricks Lakeflow Spark Declarative Pipelines (SDP/LDP) using serverless compute. Handles data ingestion with streaming tables, materialized views, CDC, SCD Type 2, and Auto Loader ingestion patterns. Use when building data pipelines, working with Delta Live Tables, ingesting streaming data, implementing change data capture, or when the user mentions SDP, LDP, DLT, Lakeflow pipelines, streaming tables, or bronze/silver/gold medallion architectures.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is highly actionable with executable SQL/Python/CLI/MCP examples, a clear workflow with explicit validation feedback loops, and well-structured progressive disclosure into verified reference files. Its only weakness is moderate verbosity in a few rationale-heavy sections that could be trimmed.

Suggestions

Tighten or move the 'Gold Layer: Preserve Key Dimensions' rationale paragraphs into a reference file, since the decision logic is inferable from context and the prose adds tokens.

Consolidate the repeated inline 'See [..]' pointers that recur across Quick Reference, Task-Based Routing, and Best Practices to reduce redundancy while keeping routing tables.

Trim explanatory asides like 'bronze->silver->gold chains' definitions that restate concepts Claude already knows from the medallion table directly above them.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — tight tables, 'MUST use CREATE OR REFRESH... NEVER use CREATE OR REPLACE', and compact code blocks — but it includes rationale prose Claude could infer (e.g., the 'Gold Layer: Preserve Key Dimensions' guidance and repeated 'See [..]' pointers) that could be tightened, matching the 2-anchor rather than the lean 3-anchor.	2 / 3
Actionability	Provides copy-paste-ready executable guidance: SQL 'CREATE OR REFRESH STREAMING TABLE bronze_orders CLUSTER BY (order_date) AS SELECT ... FROM STREAM read_files(...)', Python '@dp.table(...)' with 'spark.readStream.format("cloudFiles")', CLI 'databricks pipelines init ...', and MCP 'get_table_stats_and_schema(catalog=..., table_names=[...])' — fully concrete rather than pseudocode.	3 / 3
Workflow Clarity	Clear sequencing via the 'Required Checklist', the three-way 'Choose Your Workflow', and a 'Post-Run Validation (Required)' section with an explicit feedback loop (check status -> validate data -> 'Fix the SQL/Python code, re-upload, and re-run the pipeline') for these batch pipeline operations.	3 / 3
Progressive Disclosure	SKILL.md is an overview pointing to real one-level-deep references (all 14 reference files and the script verified to exist), clearly signaled through routing tables ('If the pipeline needs... \| Read \| references/sql/2-ingestion.md') — well-organized and easy to navigate.	3 / 3
	Total	11 / 12 Passed

Description

100%

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

The description is specific, third-person, and provides both concrete capabilities and an explicit 'Use when' trigger clause with rich natural-language and acronym keywords. It is a strong, distinctive description that would reliably route the right users to this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creates, configures, and updates', 'Handles data ingestion with streaming tables, materialized views, CDC, SCD Type 2, and Auto Loader ingestion patterns' — matching the comprehensive-action anchor rather than the partial-coverage anchor at 2.	3 / 3
Completeness	Explicitly answers both what ('Creates, configures, and updates... Handles data ingestion...') and when via a clear 'Use when building data pipelines... or when the user mentions SDP, LDP, DLT...' clause, matching the explicit-trigger anchor at 3 rather than the implied-when anchor at 2.	3 / 3
Trigger Term Quality	Strong coverage of natural terms users would say — 'data pipelines', 'Delta Live Tables', 'streaming data', 'change data capture', plus acronym variants 'SDP, LDP, DLT, Lakeflow pipelines' and 'bronze/silver/gold medallion architectures' — beyond the missing-common-variations level at 2.	3 / 3
Distinctiveness Conflict Risk	A clear Databricks Lakeflow SDP/LDP niche with distinct triggers (SDP, LDP, DLT, Lakeflow, medallion) unlikely to fire for unrelated skills; third-person voice is maintained throughout with no first/second-person penalty.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 20 deeper-than-1-level, 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 30 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Commit: 1c43c21

Reviewed: 3 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.