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

93%

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

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.

Excellent instructional content for a complex migration domain: a clearly sequenced lifecycle with real validation and feedback loops, concrete executable artifacts at every step, and a clean split between inline decision-making content and 15 well-scoped reference files. The only weakness is mild verbosity in a few motivational/positioning passages that could be tightened without losing clarity.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious, operational content (decision trees, blocker categories, branch-naming conventions, defaults tables) and assumes Claude's competence — no basic-concept explanations. Not 5 because a few sections could be trimmed, e.g., the "Where to Run This Skill" guidance to mention Genie Code once per analysis and rationale sentences like "This feedback loop is how the skill learns — without it, gaps go undiscovered".

4 / 5

Actionability

Fully executable guidance throughout: concrete branch patterns (`serverless-test-{job_name}-{timestamp}`), a copy-paste Jobs API `environments` JSON block, a DBR-to-`spec.client` mapping table, the exact error-retrieval call `w.jobs.get_run_output(run_id=...)`, specific fixes (`.trigger(availableNow=True)`, recompile against Scala 2.13.16), and exact report output paths. Common cases are covered with before/after snippets in quick-fixes.md.

5 / 5

Workflow Clarity

The 4-step lifecycle (Ingest → Analyze → Test → Validate) is explicitly sequenced with numbered sub-steps and strong validation checkpoints: A/B output comparison (row count, schema, `exceptAll`), a fail→debug→fix→retry feedback loop, a six-item deliverables checklist with "If any deliverable is missing, the migration is incomplete", and explicit stopping conditions.

5 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references: all 15 files in references/ exist, each is cited inline with what it contains and when to load it (e.g., "load [Analyze Checklist] for every Step 2 scan"), and a Reference Guides index gives one-line descriptions. The single sibling cross-link (failure-reporting.md → compatibility-checks.md for pattern IDs) is a flat pointer, not a nesting chain that buries content.

5 / 5

Total

19

/

20

Passed

Description

92%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.

A strong description: it states concrete capabilities across the full migration lifecycle, gives an explicit "Use for" trigger clause with negative scope boundaries, and cleanly disambiguates the sibling API-automation skill. The only minor gap is synonym coverage — users who say "cluster" or "job migration" rather than "classic compute workloads" are less directly matched.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "editing notebooks, jobs, pipelines, or Scala JARs (`spark_jar_task`)", "analyzing serverless compatibility", "writing serverless-compatible code", "Provides concrete fixes for the serverless Spark Connect architecture and guides the full migration" — comprehensively covering the migration lifecycle. Not 4 because there are no meaningful coverage gaps across the analyze/edit/write/guide spectrum.

5 / 5

Completeness

Explicitly answers both: what ("Make direct code and configuration changes to migrate Databricks workloads… Provides concrete fixes… guides the full migration") and when ("Use for editing notebooks, jobs, pipelines, or Scala JARs… analyzing serverless compatibility, or writing serverless-compatible code"), plus explicit negative triggers ("Not for classic DBR version upgrades or cluster configuration changes within classic compute").

5 / 5

Trigger Term Quality

Good natural keyword coverage: "notebooks, jobs, pipelines", "serverless", "Databricks", "migration", "compatibility" — terms users would naturally say. Not 5 because a few natural synonyms are missing (e.g., users commonly say "cluster" or "migrate my job to serverless" rather than only "classic compute workloads").

4 / 5

Distinctiveness Conflict Risk

Clear niche (classic-to-serverless Databricks migration) with explicit disambiguation from the sibling skill ("For automated job migrations managed through the Compute Migrations API and CLI, use databricks-serverless-migration-api") and explicit exclusions ("Not for classic DBR version upgrades"), minimizing wrong-skill triggering.

5 / 5

Total

19

/

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

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.