databricks-serverless-migration
Migrate Databricks workloads from classic compute to serverless compute. Use when migrating from classic to serverless, checking serverless code compatibility, or writing new serverless-compatible notebooks and jobs. Scans code for compatibility issues, 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.
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly defines its scope, provides specific actions, includes natural trigger terms, and explicitly states both when to use it and when not to use it. The exclusion clause is a particularly strong addition that helps disambiguate from related Databricks skills. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Scans code for compatibility issues', 'provides concrete fixes for the serverless Spark Connect architecture', 'guides the full migration'. Also specifies the domain clearly (Databricks classic to serverless compute). | 3 / 3 |
Completeness | Clearly answers both 'what' (scans code for compatibility issues, provides fixes for Spark Connect architecture, guides migration) and 'when' ('Use when migrating from classic to serverless, checking serverless code compatibility, or writing new serverless-compatible notebooks and jobs'). Also includes explicit exclusions ('Not for classic DBR version upgrades or cluster configuration changes within classic compute'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Databricks', 'serverless', 'classic compute', 'serverless compute', 'migrate/migrating', 'compatibility', 'Spark Connect', 'notebooks', 'jobs'. These cover the terms a user working on this migration would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Databricks classic-to-serverless migration). The explicit exclusion clause ('Not for classic DBR version upgrades or cluster configuration changes within classic compute') further reduces conflict risk with related Databricks skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 and well-structured migration skill with excellent concrete guidance — every incompatibility pattern has a specific, executable fix. The workflow is clearly sequenced with validation checkpoints, stopping conditions, and a deliverables checklist. The main weakness is that the skill tries to be both an overview and a comprehensive reference simultaneously, resulting in a very long document that could benefit from pushing more detailed tables and code examples into the referenced files.
Suggestions
Move the detailed compatibility check tables (Categories A-G) and extensive code examples to the referenced files (e.g., compatibility-checks.md, code-patterns.md) and keep only the most critical 5-10 patterns inline, reducing the main file length significantly.
Provide the bundle reference files so the progressive disclosure structure can actually function — currently 5 reference files are linked but none exist in the bundle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely comprehensive and detailed, which is valuable for a complex migration topic, but it's also very long (~500+ lines). Some sections could be tightened — for example, the blocker categories table in 'Understanding Migration Blockers' restates what the decision tree already covers, and the failure reporting protocol is quite verbose with schema details that could live in a reference file. However, it generally avoids explaining concepts Claude already knows and most content earns its place. | 2 / 3 |
Actionability | Excellent actionability throughout. Every migration pattern includes concrete before/after code examples that are executable and copy-paste ready. The compatibility check tables provide specific pattern → fix mappings, the streaming fixes include OOM prevention options, the job config transformation is specific, and the A/B comparison includes runnable Python code. The environment spec JSON is ready to use. | 3 / 3 |
Workflow Clarity | The 4-step migration lifecycle (Ingest → Analyze → Test → Validate) is clearly sequenced with explicit validation checkpoints. The two-branch testing strategy includes a decision tree for what goes to production vs. test-only. Stopping conditions are explicitly defined. The failure reporting protocol provides a clear feedback loop. The deliverables checklist ensures completeness verification before marking migration as done. | 3 / 3 |
Progressive Disclosure | The skill references multiple reference files (compatibility-checks.md, streaming-migration.md, networking-and-security.md, code-patterns.md, configuration-guide.md) with clear navigation links, which is good structure. However, no bundle files were provided, so these references are unverifiable. More importantly, the main SKILL.md itself is very long with substantial inline content (full compatibility tables, extensive code examples) that could have been pushed to the reference files, keeping the main file as a leaner overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (648 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- databricks/databricks-agent-skills
- Commit
caf71f1
- 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.