Name: databricks-serverless-migration
Rating: 73.6 (1 reviews)
Author: databricks

databricks-serverless-migration

Migrate Databricks workloads from classic compute to serverless compute. Use when migrating notebooks, jobs, pipelines, or Scala JARs (`spark_jar_task`) from classic clusters to serverless, checking if existing code is serverless-compatible, or writing new serverless-compatible code. Provides concrete fixes for the serverless Spark Connect architecture and guides the full migration. Not for classic DBR version upgrades or cluster configuration changes within classic compute.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 content is highly actionable with a clear, validated multi-step workflow and excellent progressive disclosure into real reference files. Its main weakness is conciseness: several patterns and fixes are restated across the category tables, the debug table, and the quick-fix code sections.

Suggestions

Consolidate the A1–M4, D1, and H2 patterns so each appears once — keep the pattern tables as the source of truth and have the Debug error→fix table link to them rather than re-explaining each fix.

Trim the Quick Fixes Reference code blocks to the 2–3 highest-value examples (DBFS→UC Volumes, streaming trigger, RDD→DataFrame) and point the rest to references/code-patterns.md to reduce duplication with the Category tables.

Move the long Failure Reporting Protocol redaction tables and output template into references/failure-reporting.md, leaving SKILL.md with the trigger conditions and a one-line link.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids basic-concept padding, but at ~840 lines it duplicates content: the A1–M4/D1/H2 patterns appear both in the Category tables and again verbatim in the Debug error→fix table, and the quick-fix code blocks restate fixes already in the tables. Mostly efficient but could be tightened by cross-referencing rather than repeating.	2 / 3
Actionability	Provides fully executable PySpark/SQL code, a concrete Jobs-API environments JSON block, copy-paste before/after examples, and a specific fix for every detected pattern — matching the 'fully executable; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear 4-step lifecycle (Ingest → Analyze → Test → Validate) with numbered steps, explicit validation checkpoints (post-rewrite lint, A/B comparison asserts, deterministic post-serialization scrub) and error-recovery feedback loops (debug → fix → retry).	3 / 3
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references (e.g., [JAR Migration](references/jar-migration.md), [Compatibility Checks](references/compatibility-checks.md)), and every referenced file exists in ./references/, giving easy navigation without nested depths.	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 concrete, trigger-rich, and complete, explicitly stating both when to use and when not to use the skill. Third-person voice is maintained throughout and it stays concise without padding.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Migrate Databricks workloads", "checking if existing code is serverless-compatible", "writing new serverless-compatible code", "Provides concrete fixes" — matching the rubric's 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ("Migrate... workloads", "Provides concrete fixes", "guides the full migration") and when ("Use when migrating... or writing new serverless-compatible code"), plus an explicit negative trigger ("Not for classic DBR version upgrades").	3 / 3
Trigger Term Quality	Includes natural phrases users would say ("migrating notebooks, jobs, pipelines, or Scala JARs", "checking if existing code is serverless-compatible") with good coverage; the parenthetical `spark_jar_task` is supplementary jargon rather than the only trigger.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (classic → serverless migration) and the explicit "Not for classic DBR version upgrades or cluster configuration changes within classic compute" clause sharply separates it from adjacent DBR/cluster skills, minimizing conflict.	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
skill_md_line_count	SKILL.md is long (848 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: databricks/databricks-agent-skills
Path: skills/databricks-serverless-migration/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.