databricks-lakebase-provisioned
Patterns and best practices for Lakebase Provisioned (Databricks managed PostgreSQL) for OLTP workloads. Use when creating Lakebase instances, connecting applications or Databricks Apps to PostgreSQL, implementing reverse ETL via synced tables, storing agent or chat memory, or configuring OAuth authentication for Lakebase.
68
82%
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 around Lakebase Provisioned PostgreSQL, lists specific concrete use cases, and includes an explicit 'Use when...' clause with diverse trigger scenarios. The description is concise yet comprehensive, uses third-person voice appropriately, and contains highly distinctive terminology that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating Lakebase instances, connecting applications to PostgreSQL, implementing reverse ETL via synced tables, storing agent/chat memory, and configuring OAuth authentication. | 3 / 3 |
Completeness | Clearly answers both 'what' (patterns and best practices for Lakebase Provisioned PostgreSQL for OLTP workloads) and 'when' with an explicit 'Use when...' clause listing five specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lakebase', 'PostgreSQL', 'OLTP', 'reverse ETL', 'synced tables', 'agent memory', 'chat memory', 'OAuth authentication', 'Databricks Apps'. These cover a wide range of natural user queries related to this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Lakebase Provisioned (Databricks managed PostgreSQL) is a very specific product/service. The combination of Lakebase, PostgreSQL, reverse ETL, synced tables, and OAuth makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable skill with excellent executable code examples covering the full range of Lakebase Provisioned use cases. Its main weaknesses are moderate verbosity (overview table, feature descriptions Claude doesn't need) and lack of explicit multi-step workflow sequencing with validation checkpoints. The progressive disclosure could be improved by moving the lengthy SQLAlchemy pattern, MCP tools section, and CLI reference into separate files.
Suggestions
Add an explicit end-to-end workflow section with numbered steps and validation checkpoints (e.g., verify instance state after creation before attempting connection).
Move the MCP tools section, CLI quick reference, and SQLAlchemy token refresh pattern into separate referenced files to reduce SKILL.md length and improve progressive disclosure.
Remove the overview feature table and 'When to Use' section — these describe rather than instruct and Claude can infer the use cases from the patterns themselves.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview table and 'When to Use' section explain things Claude could infer. The feature table, available regions list, and some contextual descriptions add moderate bloat. However, the code examples themselves are lean and the overall structure avoids excessive verbosity. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples for every major pattern: instance creation, OAuth token generation, notebook connection, SQLAlchemy with token refresh, CLI commands, and MCP tool usage. Key details like sslmode, token expiry, and capacity values are all specified. | 3 / 3 |
Workflow Clarity | While individual patterns are clear, there's no explicit end-to-end workflow with validation checkpoints. For instance, creating an instance, waiting for it to be ready, then connecting is not sequenced with verification steps. The token refresh pattern is well-documented but the overall provisioning workflow lacks explicit validation/feedback loops. | 2 / 3 |
Progressive Disclosure | References to connection-patterns.md and reverse-etl.md are well-signaled, and related skills are linked. However, the SKILL.md itself is quite long (~250 lines) with substantial inline content (SQLAlchemy pattern, MCP tools, CLI reference) that could be split into referenced files. No bundle files were provided to verify the referenced paths exist. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
93cb4e3
- 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.