CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

The body is a high-quality, action-dense reference that adds genuinely non-obvious Lakebase knowledge. It loses points only on workflow feedback loops and on progressive disclosure, where the advertised task files are absent from the bundle.

Suggestions

Add the referenced bundle files (connections.md, operations.md, reverse-etl.md) or remove the dangling references so the disclosure structure is real.

For long-running and destructive operations (branch delete, compute scale changes), add an explicit validate→fix→retry checkpoint sequence to lift workflow_clarity.

Move the dense inline reference material (resource model, non-obvious facts, limitations) into the task files so SKILL.md stays a lean overview pointing one level deep.

DimensionReasoningScore

Conciseness

Dense and lean throughout — tables, terse lists, and code blocks carry domain-specific non-obvious facts (e.g. "max_lifetime=2700", "0.5–32 CU with max - min <= 16") with no padding or explanation of concepts Claude already knows.

3 / 3

Actionability

Provides executable guidance: exact credential-minting code (cred.token as password), a concrete connection recipe (psycopg_pool, OAuthConnection, max_lifetime=2700), pip install with pinned versions, and canonical resource paths — copy-paste ready.

3 / 3

Workflow Clarity

The lead connection pattern is a clean 1-2-3 sequence and LRO `.wait()` is flagged, but database/long-running operations lack explicit validate→fix→retry feedback loops; per the rubric, missing feedback loops for database operations caps this at 2.

2 / 3

Progressive Disclosure

Sections are well-organized and references are signaled ("See connections.md", task-files list), but the referenced files (connections.md, operations.md, reverse-etl.md) do not exist in the bundle, and substantial reference material is inline rather than split into those files.

2 / 3

Total

10

/

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 across all dimensions: third-person voice, concrete actions, explicit "Use when" triggers, and a well-scoped niche. It neither over-claims nor pads with fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "creating or managing Lakebase Autoscaling projects, configuring autoscaling compute or scale-to-zero, working with database branching... implementing reverse ETL via synced tables, or connecting applications to Lakebase with OAuth credentials" — matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers what ("Patterns and best practices for Lakebase Autoscaling (next-gen managed PostgreSQL)") and when via a clear "Use when..." clause enumerating multiple triggers, satisfying both halves.

3 / 3

Trigger Term Quality

Covers natural terms a user would actually say — "Lakebase Autoscaling", "scale-to-zero", "database branching", "reverse ETL", "synced tables", "OAuth credentials" — with good coverage and common variations.

3 / 3

Distinctiveness Conflict Risk

Targets a clearly distinct niche (Lakebase Autoscaling, next-gen managed PostgreSQL) with specialized triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
databricks-solutions/ai-dev-kit
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.