databricks-lakebase-autoscale

Patterns and best practices for Lakebase Autoscaling (next-gen managed PostgreSQL). Use when creating or managing Lakebase Autoscaling projects, configuring autoscaling compute or scale-to-zero, working with database branching for dev/test workflows, implementing reverse ETL via synced tables, or connecting applications to Lakebase with OAuth credentials.

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 concrete SDK calls, code, and version pins, and is well-structured with clear sections. Its weak spots are missing validation/feedback loops for risky operations and three referenced task files that do not actually exist in the bundle.

Suggestions

Add explicit validation/retry checkpoints for the auth-credential and connection workflows (e.g., verify the Lakebase-scoped token works before trusting the pool; retry loop for scale-to-zero wake-up) to lift workflow clarity above 2.

Provide the referenced task files (connections.md, operations.md, reverse-etl.md) or remove the 'Task files' pointers, since the bundle currently points to files that do not exist.

Move the inline region lists and version pin block into a bundled reference or a clearly dated/old-patterns section so the main body stays lean and the time-sensitive data is isolated.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of concept-explanation padding (no 'what is Postgres' filler), but inline time-sensitive facts — a region list, version pins, and the pip install block — add bulk that isn't placed in a deprecated/old-patterns section, keeping it just off the lean 'every token earns its place' level.	2 / 3
Actionability	Provides concrete executable guidance throughout: `generate_database_credential`, `pip install` version pins, a `ConnectionPool`/`OAuthConnection` recipe, `max_lifetime=2700`, `WorkspaceClient().postgres`, `.wait()`, `FieldMask`, `sslmode=require`, and the `postgresql+psycopg://` URL prefix — copy-paste ready.	3 / 3
Workflow Clarity	Steps are clearly sequenced (numbered lead-connection pattern, resource model, create/update flow with `.wait()`/`FieldMask`), but for auth-critical and database operations there are no explicit validate→fix→retry checkpoints or feedback loops, which caps workflow clarity at 2 per the destructive/batch-operations guideline.	2 / 3
Progressive Disclosure	The body has clear sections and a 'Task files' list signaling one-level-deep references to connections.md, operations.md, and reverse-etl.md, but those referenced bundle files are not present in the skill directory, so navigation breaks at the first hop.	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 strong: it names a specific niche, lists concrete capabilities, and provides an explicit, multi-trigger 'Use when' clause that answers both what and when. It is concise without fluff and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the product surface — creating/managing projects, configuring autoscaling compute and scale-to-zero, database branching, reverse ETL via synced tables, and OAuth app connections — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states what it does ('Patterns and best practices for Lakebase Autoscaling...') and an explicit, detailed 'Use when...' clause covering multiple triggers, answering both what and when.	3 / 3
Trigger Term Quality	Natural verb-phrase triggers ('creating or managing... projects', 'configuring autoscaling compute', 'database branching for dev/test workflows', 'reverse ETL via synced tables', 'connecting applications') give good coverage of phrasings users would actually say.	3 / 3
Distinctiveness Conflict Risk	Lakebase Autoscaling is a clearly named niche (managed PostgreSQL with autoscaling/branching/scale-to-zero/synced tables) with distinct triggers unlikely to fire for other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.