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.
64
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./databricks-skills/databricks-lakebase-autoscale/SKILL.mdQuality
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 identifies the product domain (Lakebase Autoscaling / managed PostgreSQL), lists specific capabilities, and provides explicit trigger guidance via a well-structured 'Use when...' clause. The description is concise yet comprehensive, with strong domain-specific trigger terms that minimize conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating/managing projects, configuring autoscaling compute, scale-to-zero, database branching for dev/test, reverse ETL via synced tables, and connecting applications with OAuth credentials. | 3 / 3 |
Completeness | Clearly answers both 'what' (patterns and best practices for Lakebase Autoscaling managed PostgreSQL) and 'when' with an explicit 'Use when...' clause listing five distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lakebase Autoscaling', 'PostgreSQL', 'autoscaling compute', 'scale-to-zero', 'database branching', 'dev/test', 'reverse ETL', 'synced tables', 'OAuth credentials'. Good coverage of domain-specific terms a user working with this product would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with product-specific terminology ('Lakebase Autoscaling', 'synced tables', 'scale-to-zero') that clearly differentiates it from generic database or PostgreSQL skills. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid reference document for Lakebase Autoscaling with good structural elements (tables, resource model, comparison matrix) and an important auth warning. However, it leans more toward a reference document than an actionable skill—the lead connection pattern lacks a complete executable example inline, and multi-step workflows lack validation checkpoints. The content is moderately concise but could be tightened by moving region lists, version details, and the Provisioned comparison to referenced files.
Suggestions
Add a complete, copy-paste-ready Python code block for the lead connection pattern (OAuthConnection + ConnectionPool) directly in the SKILL.md rather than deferring entirely to connections.md.
Add explicit validation/verification steps to workflows—e.g., after project creation, verify with a GET call; after connection setup, run a test query to confirm connectivity.
Move the region lists, version numbers, and Provisioned comparison table to a referenced file (e.g., reference.md) to reduce the main file's token footprint and improve progressive disclosure.
Include a brief end-to-end workflow (create project → create branch → get endpoint → connect) with numbered steps and checkpoints to improve workflow clarity for the most common task.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and well-structured with tables and bullet points, but includes some information Claude likely already knows (e.g., what OLTP is, what standard Postgres drivers are) and the 'Non-obvious facts to preserve' section, while useful, includes region lists and version numbers that add bulk. The comparison table with Provisioned is borderline necessary depending on use case. | 2 / 3 |
Actionability | Provides a concrete credential generation snippet and the lead connection pattern outline, but the connection pattern is described in prose steps rather than a complete executable code block. The actual executable examples are deferred to connections.md, and the inline code is limited to a small credential snippet and a pip install command. | 2 / 3 |
Workflow Clarity | The lead connection pattern provides a numbered sequence but lacks validation checkpoints or error handling steps. The resource model hierarchy is clear, and the note about LROs needing .wait() is helpful, but there's no explicit workflow for common multi-step operations like creating a project and connecting to it, with validation at each step. The critical auth warning is good but reactive rather than integrated into a workflow. | 2 / 3 |
Progressive Disclosure | References three task files (connections.md, operations.md, reverse-etl.md) with clear descriptions, which is good structure. However, no bundle files were provided to verify these exist, and the SKILL.md itself contains substantial inline detail (region lists, limitations, comparison tables) that could arguably be in referenced files. The overview-to-detail split is reasonable but the main file is heavy. | 2 / 3 |
Total | 8 / 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.
93cb4e3
Table of Contents
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.