CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

databricks-serverless-migration

Make direct code and configuration changes to migrate Databricks workloads from classic compute to serverless. Use for editing notebooks, jobs, pipelines, or Scala JARs (`spark_jar_task`), analyzing serverless compatibility, or writing serverless-compatible code. Provides concrete fixes for the serverless Spark Connect architecture and guides the full migration. For automated job migrations managed through the Compute Migrations API and CLI, use databricks-serverless-migration-api. Not for classic DBR version upgrades or cluster configuration changes within classic compute.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is databricks-serverless-migration in databricks/databricks-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A well-engineered, operational migration guide: concrete commands, templates, and tables; an explicitly validated workflow with feedback loops and a deliverables checklist; and exemplary reference navigation with verified anchors. The only weakness is mild redundancy around the DBR-upgrade boundary and a few trimmable rationale sentences.

DimensionReasoningScore

Conciseness

Largely dense and operational, but the classic-DBR-upgrade exclusion is repeated within the body ("this skill does not apply — classic DBR upgrades have a different compatibility surface" in Step 1 and "not a classic cluster with a newer DBR" in the same step's list) despite already being in the description, and a few rationale sentences ("This feedback loop is how the skill learns — without it, gaps go undiscovered") could be trimmed. These are minor instances of over-explanation, matching anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Fully executable guidance throughout: a copy-paste-ready environment spec JSON block, branch name templates ("serverless-test-{job_name}-{timestamp}"), exact calls ("w.jobs.get_run_output(run_id=...)", "system.billing.usage"), a DBR → spec.client version mapping table, the six supported Spark configs named verbatim, and exact report paths ("~/.databricks-migration-skill/reports/failure-<ISO-timestamp>.json"). Common cases are covered inline or via verified before/after reference snippets.

5 / 5

Workflow Clarity

The 4-step lifecycle (Ingest → Analyze → Test → Validate) is clearly sequenced with explicit validation (A/B comparison by "row count, schema, `exceptAll` row diff"), feedback loops ("If it fails, get the error output, debug, fix, and retry"; failure report after "typically 5+" repeated failures), stopping conditions, and checklists (six deliverables with "If any deliverable is missing, the migration is incomplete"). This matches the level-5 anchor exactly — explicit validation, error-recovery loops, and checklists are all present, so the batch-operation cap of 3 does not apply.

5 / 5

Progressive Disclosure

Clear overview body with 15 one-level-deep references that all exist on disk; each has a one-line entry in the Reference Guides index plus inline pointers with section anchors (e.g., references/testing-strategy.md#test-data-setup, references/quick-fixes.md#parameterize-catalogs-for-testing) that were verified to resolve to real headings. Reference files do not chain into further references, so navigation is one level deep and well signaled.

5 / 5

Total

19

/

20

Passed

Description

100%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 exemplary: concrete third-person actions, an explicit "Use for" trigger clause, and explicit boundaries that disambiguate a sibling API-based skill and exclude out-of-scope work. It packs distinct information into every sentence with no padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Make direct code and configuration changes", "editing notebooks, jobs, pipelines, or Scala JARs (`spark_jar_task`)", "analyzing serverless compatibility", "writing serverless-compatible code" — with comprehensive coverage of the migration scope. No vague or generic language remains, matching the level-5 anchor rather than the minor-gaps level-4 anchor.

5 / 5

Completeness

Explicitly answers "what" ("Provides concrete fixes for the serverless Spark Connect architecture and guides the full migration") and "when" via a concrete "Use for editing notebooks, jobs, pipelines, or Scala JARs..." trigger clause. Both are explicit with concrete trigger phrases, matching the level-5 anchor; a missing or weak "when" would cap it at 3, which does not apply.

5 / 5

Trigger Term Quality

Natural phrases users would say are comprehensively covered: "migrate Databricks workloads from classic compute to serverless", "notebooks, jobs, pipelines", "serverless compatibility", with synonyms ("migration", "serverless-compatible code") and "cluster configuration"/"DBR" appearing in the boundary clause. This matches the comprehensive-synonyms anchor, not merely good coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche (classic → serverless migration) with explicit disambiguation: "For automated job migrations managed through the Compute Migrations API and CLI, use databricks-serverless-migration-api" and "Not for classic DBR version upgrades or cluster configuration changes within classic compute". Conflict risk with sibling skills is actively minimized, matching the clear-niche anchor.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

plugins/databricks/claude/skills/databricks-serverless-migration/SKILL.md

Reviewed

Table of Contents

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.