Name: databricks-pipelines
Rating: 75.2 (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

93%

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%Weight 40%Scale 1-5

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

The body is an exemplar of a dense, well-structured reference skill: lean and high-signal, fully actionable with concrete APIs and commands, with explicit workflows, validation checkpoints, and clean one-level-deep progressive disclosure. No meaningful weaknesses.

Dimension	Reasoning	Score
Conciseness	The body is dense high-signal material — a decision tree, API tables, a migration table, and a Common Issues table — with no padding explaining what Databricks/pipelines/libraries are; it assumes Claude's competence and every section earns its tokens, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Provides concrete executable API calls (@dp.table(), CREATE OR REFRESH STREAMING TABLE, dp.create_auto_cdc_flow()), specific CLI commands (databricks bundle deploy -t dev), and exact before→after migration pairs covering common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Sequences multi-step work explicitly (Choose Your Workflow A/B/C → Running a Pipeline with ordered deploy/validate/run commands) and includes validation checkpoints and feedback loops ('Always poll the update', deploy-before-run, full-refresh data-loss warning requiring explicit user approval), matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to references/*.md (all referenced files exist on disk), an explicit Reference Index, and per-(feature,language) API tables that route to detail files, matching the 'clear overview with well-signaled one-level-deep references; easy navigation' anchor.	5 / 5
	Total	20 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 concrete, well-triggered, and explicit about both capability and when to invoke it, including a useful BEFORE-implementation timing cue. It is strong across all four dimensions with only minor specificity/keyword gaps.

Dimension	Reasoning	Score
Specificity	Quotes 'Develop Lakeflow Spark Declarative Pipelines' and 'building batch or streaming data pipelines with Python or SQL' — names the domain plus several concrete actions (batch and streaming pipelines in Python/SQL), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because it stops short of enumerating the full action set like ingestion/CDC/sink.	4 / 5
Completeness	Explicitly answers both what ('Develop ... Declarative Pipelines ... on Databricks') and when ('Use when building batch or streaming data pipelines with Python or SQL'), plus an explicit timing directive ('Invoke BEFORE starting implementation'), matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.	5 / 5
Trigger Term Quality	Includes natural terms users say — 'batch or streaming data pipelines', 'Python or SQL', 'Databricks', and the legacy synonym 'Delta Live Tables' — giving good keyword coverage; not a 5 because it omits common variations like file-format or source-specific triggers.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Lakeflow/DLT declarative pipelines on Databricks) with distinct triggers and even surfaces the legacy naming so it fires on either term, giving minimal conflict risk per the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	18 / 20 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: 653db60

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.