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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable code and commands, and is reasonably well organized, but it suffers from repeated token-generation coverage, missing validation checkpoints in database workflows, and signaled reference files that are not actually present.

Suggestions

Add explicit validation/verification steps to the connection and token-refresh workflows (e.g., test the connection or assert token validity before use) to introduce a validate→fix→retry feedback loop and raise workflow clarity.

Consolidate the repeated OAuth token-generation examples (Quick Start, 'Generate OAuth Token', and MCP 'generate_lakebase_credential') into a single canonical pattern referenced where needed, to remove redundancy and improve conciseness.

Either create the referenced connection-patterns.md and reverse-etl.md files or remove/fix the broken reference links, and consider moving the MCP tool tables and CLI quick reference into a reference file so SKILL.md stays a tight overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient (code and tables dominate, minimal concept explanation) but the OAuth token-generation pattern recurs ~3 times and CLI/SDK/MCP sections re-cover the same create/get/delete operations, so it is not the lean every-token-earns-its-place level 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code with complete imports (WorkspaceClient, psycopg, SQLAlchemy), concrete CLI commands, MCP tool calls with real parameters, and a %pip install line — matching the level-3 executable-code anchor.	3 / 3
Workflow Clarity	Sections are logically sequenced but database workflows (especially the token-refresh and connection patterns) lack explicit validation checkpoints or validate→fix→retry feedback loops, which per the rubric caps database-operation workflows at 2 rather than 3.	2 / 3
Progressive Disclosure	The body is well-sectioned and acts as an overview, but it signals references to connection-patterns.md and reverse-etl.md that do not exist as bundle files, and substantial API/CLI detail is inline rather than split out — matching level 2 rather than the resolved one-level-deep references of level 3.	2 / 3
	Total	9 / 12 Passed

Description

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.

The description is specific, trigger-rich, and complete, with an explicit 'Use when' clause and concrete actions that clearly distinguish it from adjacent skills. It uses appropriate third-person voice with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — creating Lakebase instances, connecting Apps to PostgreSQL, reverse ETL via synced tables, storing agent/chat memory, and OAuth configuration — matching the level-3 anchor rather than the domain-plus-some-actions of level 2.	3 / 3
Completeness	Explicitly states what ('Patterns and best practices for Lakebase Provisioned... for OLTP workloads') and when via an explicit 'Use when' clause with concrete triggers, satisfying the level-3 both-what-and-when requirement and avoiding the missing-trigger cap at 2.	3 / 3
Trigger Term Quality	Covers natural terms users would say — PostgreSQL, Databricks Apps, OLTP, reverse ETL, synced tables, chat memory, OAuth — providing broad keyword coverage beyond the level-2 'some relevant keywords' anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Databricks managed PostgreSQL for OLTP) with distinctive triggers unlikely to overlap with generic database skills, matching the level-3 clear-niche anchor rather than the level-2 'could still overlap'.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 2 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Commit: 1c43c21

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.