CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

84%

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

73%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.

This is a highly actionable, well-sequenced migration skill with strong validation feedback loops and real, correctly-linked references. Its main weakness is token efficiency: substantial duplication between the inline category tables, the quick-fix section, and the error reference inflates the body well past what is needed.

Suggestions

Collapse the inline 'Debug failed serverless runs' error table (lines 603-634) into the Category A-G tables it duplicates, or move it to references/configuration-guide.md, keeping only a pointer inline.

Move the full Failure Reporting JSON schema and anonymization regex checklist into references/failure-reporting.md, leaving SKILL.md with the trigger conditions and a single pointer to reduce the ~150-line block.

De-duplicate the A1 cell-magic lint: the before/after example appears both in Step 2 and via the error table row; keep one worked example and cross-reference it.

DimensionReasoningScore

Conciseness

The body is ~840 lines and substantially verbose: the giant error-message table (lines 603-634) largely duplicates the Category A-G tables above it, the A1 lint pass repeats the same before/after twice, and many pattern rows restate their fix in three places (table, quick-fix section, error table).

2 / 5

Actionability

Every pattern ships concrete, copy-paste-ready code or commands (e.g., the streaming `.trigger(availableNow=True)` block, the RDD→DataFrame before/after examples, the environments JSON), and the error table maps specific errors to specific fixes.

5 / 5

Workflow Clarity

The 4-step lifecycle (Ingest → Analyze → Test → Validate) is explicitly sequenced with validation checkpoints: pre-run static scan, A/B comparison asserts, test-vs-production branch gating, a decision table for what goes to prod, and a deliverables checklist that says 'do not mark done if missing'.

5 / 5

Progressive Disclosure

SKILL.md is an overview that links one level deep to 10 real reference files (all verified present) with clear labels, but it inlines a large amount of material (full error table, full quick-fix code, full failure-report schema) that could live in those references, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

95%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 precise, third-person, and answers both what and when with concrete trigger phrases and an explicit out-of-scope statement. It is among the strongest examples in the rubric's good set.

DimensionReasoningScore

Specificity

"Migrate Databricks workloads from classic compute to serverless compute" names the domain plus several concrete actions (migrate notebooks, jobs, pipelines, Scala JARs; check compatibility; provide concrete fixes; guide the migration), with only minor coverage gaps on what 'guides' entails.

4 / 5

Completeness

It explicitly answers "what" (migrate workloads, provide fixes, guide migration) and "when" ("Use when migrating notebooks, jobs, pipelines, or Scala JARs... checking if existing code is serverless-compatible, or writing new serverless-compatible code"), plus a clear negative scope ("Not for classic DBR version upgrades").

5 / 5

Trigger Term Quality

It includes natural terms users would say ("migrating notebooks, jobs, pipelines, or Scala JARs", "serverless-compatible", "spark_jar_task", "classic clusters to serverless") plus technical synonyms and the specific task-type keyword, giving comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

The narrow serverless-migration niche, the "spark_jar_task" trigger, and the explicit "Not for classic DBR version upgrades" exclusion give it a clear niche with minimal conflict risk against other Databricks skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.