databricks-upgrade-migration
Upgrade Databricks runtime versions and migrate between features. Use when upgrading DBR versions, migrating to Unity Catalog, or updating deprecated APIs and features. Trigger with phrases like "databricks upgrade", "DBR upgrade", "databricks migration", "unity catalog migration", "hive to unity".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-structured skill description with strong trigger terms and clear 'when' guidance. The explicit trigger phrases section is a notable strength. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., rewriting API calls, updating configuration files, transforming Hive metastore references).
Suggestions
Expand the capability list with more concrete actions, e.g., 'Rewrites deprecated API calls, updates cluster configuration syntax, transforms Hive metastore references to Unity Catalog format.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks runtime) and some actions (upgrade versions, migrate between features, updating deprecated APIs), but doesn't list comprehensive concrete actions like specific migration steps, code transformations, or configuration changes. | 2 / 3 |
Completeness | Clearly answers both 'what' (upgrade Databricks runtime versions, migrate between features) and 'when' (explicit 'Use when' clause plus a 'Trigger with phrases like' section providing concrete trigger terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'databricks upgrade', 'DBR upgrade', 'databricks migration', 'unity catalog migration', 'hive to unity', plus mentions of 'deprecated APIs' and 'DBR versions' — these are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche — Databricks runtime upgrades and Unity Catalog migration are very specific domains unlikely to conflict with other skills. The trigger terms are domain-specific and precise. | 3 / 3 |
Total | 11 / 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 strong, highly actionable skill that covers a complex multi-step migration process with executable code, clear sequencing, and good validation checkpoints. Its main weakness is that it packs a lot of content into a single file — the four distinct workflows (runtime upgrade, UC migration, API migration, Delta protocol) could be better organized with progressive disclosure. Minor verbosity in the Prerequisites and Output sections could be trimmed.
Suggestions
Split the four major workflows (runtime upgrade, UC migration, API migration, Delta protocol) into separate referenced files, keeping SKILL.md as a concise overview with links to each detailed guide.
Remove the Prerequisites and Output sections — the prerequisites are either obvious or already implied by the steps, and the Output section merely restates what the steps accomplish.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient and avoids explaining basic concepts, but includes some sections that could be tightened — the Prerequisites section states obvious things ('Admin access to workspace'), the Output section restates what the steps already cover, and the version compatibility matrix includes an 'Effort' column that's subjective filler. The overall length is substantial but mostly justified by the breadth of the topic. | 2 / 3 |
Actionability | Excellent actionability throughout — provides fully executable Python scripts with the Databricks SDK, complete SQL statements for each migration option (SYNC, CTAS, DEEP CLONE), concrete API migration examples showing old vs new patterns, and a bulk migration script with row-count verification. All code is copy-paste ready with real SDK classes and methods. | 3 / 3 |
Workflow Clarity | The four steps are clearly sequenced (runtime upgrade → UC migration → API migration → Delta protocol upgrade). Validation checkpoints are explicit: dry_run before applying cluster changes, row count verification after table migration, DESCRIBE DETAIL to check protocol versions before upgrading, and a clear warning that protocol upgrades are irreversible with a workaround (DEEP CLONE). The error handling table adds additional recovery guidance. | 3 / 3 |
Progressive Disclosure | The skill is quite long (~200 lines of content) and could benefit from splitting detailed migration scripts and the error handling table into separate reference files. The Resources section with external links is good, and the Next Steps reference to 'databricks-ci-integration' is appropriate, but the main file tries to cover four distinct migration workflows inline rather than linking to dedicated guides for each. | 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
c8a915c
- 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.