CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/databricks-lakebase/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

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

The content is mostly lean, executable, and well-structured with copy-paste CLI examples and clear cross-skill navigation. Its main weakness is workflow_clarity: the destructive branch-deletion operation proceeds without an explicit pre-delete validation checkpoint, capping that dimension.

Suggestions

Add an explicit validation step before the destructive delete-branch command (e.g. confirm the branch is not protected and is not the production branch via a list/check, then delete) to lift workflow_clarity above 3.

For role/permission management, inline a minimal concrete example of a create-role command with a representative --json spec instead of only pointing to 'create-role -h', to close the actionability gap.

Trim the introductory 'Lakebase is Databricks' serverless Postgres-compatible database ...' framing to a single line since it explains product context Claude can infer, improving conciseness.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (e.g. 'Do NOT guess command syntax. Discover ... dynamically'), with only minor intro over-explanation such as defining what Lakebase is, so it sits above midpoint but not fully lean.

4 / 5

Actionability

Most guidance is copy-paste ready CLI commands (e.g. the create-project and create-branch blocks), but role/permission management defers to 'databricks postgres create-role -h' rather than giving concrete spec fields, a minor gap.

4 / 5

Workflow Clarity

Create-a-project has a clear sequence with verification (list-branches/list-endpoints/list-databases), but the destructive delete-branch workflow lacks an explicit validation checkpoint before deletion, so per the destructive-operation cap it cannot exceed 3.

3 / 5

Progressive Disclosure

Well-organized single file with clear section headers and one-level cross-skill references ('use the databricks-apps skill', 'use the parent databricks-core skill'); no bundle files exist, so structure is good with only minor organization gaps versus an ideal overview-split.

4 / 5

Total

15

/

20

Passed

Description

87%Weight 40%Scale 1-5

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, clearly answering both what it does and when to use it with a distinct niche. Verb choice is slightly generic ('create, configure, or manage') which is the only thing keeping specificity and trigger_term_quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Quotes several concrete resources/actions ('Manage Lakebase Postgres Autoscaling projects, branches, and endpoints via Databricks CLI' and 'create, configure, or manage ... databases, projects, branches, computes, or endpoints'), but the verbs 'create, configure, or manage' are generic, so it lands above the 3-anchor without full comprehensive coverage.

4 / 5

Completeness

It explicitly states both the 'what' ('Manage Lakebase Postgres Autoscaling projects, branches, and endpoints via Databricks CLI') and the 'when' with a concrete 'Use when ... create, configure, or manage ...' trigger clause, matching the 5-anchor exactly.

5 / 5

Trigger Term Quality

Strong product-specific keywords ('Lakebase Postgres', 'projects, branches, computes, endpoints') map well to what a user would say, but a few natural synonyms or file-extension-style tokens are missing, keeping it just below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The narrow Lakebase Postgres Autoscaling niche with product-specific triggers ('Lakebase Postgres', 'computes, endpoints') gives it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
databricks/devhub
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.