databricks-lakebase
Manage Lakebase Postgres Autoscaling projects, branches, and endpoints via Databricks CLI. Use when asked to create, configure, or manage Lakebase Postgres databases, projects, branches, computes, or endpoints.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a solid skill description that clearly identifies its niche (Lakebase Postgres via Databricks CLI), includes an explicit 'Use when' clause with relevant trigger terms, and is unlikely to conflict with other skills. The main area for improvement is listing more specific concrete actions beyond the general 'manage, create, configure' verbs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Lakebase Postgres Autoscaling) and some actions (manage projects, branches, endpoints via Databricks CLI), but doesn't list multiple specific concrete actions like 'create project', 'scale endpoint', 'delete branch' in detail. | 2 / 3 |
Completeness | Clearly answers both 'what' (manage Lakebase Postgres Autoscaling projects, branches, and endpoints via Databricks CLI) and 'when' (explicit 'Use when asked to create, configure, or manage Lakebase Postgres databases, projects, branches, computes, or endpoints'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lakebase', 'Postgres', 'Databricks CLI', 'projects', 'branches', 'computes', 'endpoints', 'databases'. Good coverage of domain-specific terms a user would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche combining Lakebase Postgres Autoscaling with Databricks CLI. The specific product names and tooling make it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with excellent CLI command examples and well-sequenced workflows including validation steps and error recovery paths. The main weakness is that the Schema Permissions section and some 'What's Next' content are verbose and could be more concise or split into separate reference files. Overall it provides high-quality, practical guidance for managing Lakebase Postgres resources.
Suggestions
Consider moving the detailed 'Schema Permissions for Deployed Apps' section to a separate reference file (e.g., SCHEMA_PERMISSIONS.md) and linking to it from the main skill, keeping only a brief summary inline.
Trim the introductory paragraph ('Lakebase is Databricks' serverless Postgres-compatible database...') — Claude doesn't need the product positioning; jump straight to what the skill enables.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanations (e.g., 'Lakebase is Databricks' serverless Postgres-compatible database (similar to Neon)' and the detailed Schema Permissions section is quite lengthy). The resource hierarchy and ID format rules earn their place, but the 'What's Next' section could be tighter. | 2 / 3 |
Actionability | Provides fully executable CLI commands with concrete flags, JSON payloads, and profile arguments throughout. Commands are copy-paste ready with clear placeholders, and the skill consistently directs users to run `-h` for discovery rather than guessing. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints — e.g., verifying auto-provisioned resources after project creation, the two-step unprotect-then-delete branch workflow, and the deploy-first workflow for schema permissions with a clear error recovery path (Option A vs Option B). The troubleshooting table adds further error recovery guidance. | 3 / 3 |
Progressive Disclosure | The skill references a parent `databricks-core` skill and a `databricks-apps` skill appropriately, but the Schema Permissions section is quite lengthy and could be split into a separate reference file. The content is well-structured with headers but some sections (especially 'What's Next') inline substantial detail that could benefit from being in separate files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- databricks/devhub
- Commit
0b6297e
- 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.