CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-lakebase

Databricks Lakebase Postgres: projects, scaling, connectivity, Lakebase synced tables, and Data API. Use when asked about Lakebase databases, OLTP storage, or connecting apps to Postgres on Databricks.

72

Quality

88%

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

77%

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

A highly actionable, well-sequenced skill body with strong workflow checkpoints and bundled references, held back only by some duplicated content and one orphaned reference file that is not surfaced from the overview.

Suggestions

Remove duplication: keep the Provisioned→Autoscaling mapping in either the blockquote or the table (not both), and have the Troubleshooting row for 'permission denied for schema' link to the Schema Permissions section instead of repeating the full recovery steps.

Link references/medallion-from-cdc.md from the body (e.g., a one-line entry alongside the other Reference docs) so it is discoverable, or remove it if it is no longer meant to ship.

Consolidate the connection/token steps: present the scriptable single-copy version once and reference it, rather than showing the get-endpoint/generate-credential flow twice in prose and script form.

DimensionReasoningScore

Conciseness

Dense and mostly high-signal with no basic-concept padding, but it duplicates material — the Provisioned→Autoscaling migration is both a long blockquote and a full table, and the permission-denied recovery appears in both the Schema Permissions section and the Troubleshooting table — so it could be tightened rather than earning the lean 3.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands with --json payloads, psql connection strings, JSON-path tables, and a scriptable bash/python pipe, matching the executable-and-specific anchor.

3 / 3

Workflow Clarity

Multi-step flows are explicitly sequenced with checkpoints ("ALWAYS Do This First", reuse-vs-create, deploy-first workflow) and include a feedback loop for destructive permission-denied recovery with A/B options and data-loss warnings, satisfying the validation-checkpoint anchor required for database/destructive operations.

3 / 3

Progressive Disclosure

The body is a well-signaled overview pointing one level deep to 6 real reference files each with a one-line summary, but 7 reference files exist and medallion-from-cdc.md is never linked, leaving otherwise-excellent navigation with a real discovery gap; this sits below the 3 anchor's "easy navigation" bar.

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.

A strong, third-person description that concretely lists capabilities and pairs them with an explicit, natural-language trigger clause. It cleanly answers both what the skill does and when to use it with minimal risk of conflicting with other skills.

DimensionReasoningScore

Specificity

Names multiple concrete capability areas — "projects, scaling, connectivity, Lakebase synced tables, and Data API" — matching the multiple-specific-actions anchor rather than the partial domain-only anchor at 2.

3 / 3

Completeness

Explicitly states both what it does (the capability list) and when to use it via a "Use when asked about..." trigger clause, satisfying the what-AND-when anchor; not 2 because the when is explicit, not merely implied.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say ("Lakebase databases", "OLTP storage", "connecting apps to Postgres on Databricks"), giving good keyword coverage rather than the missing-variations level at 2.

3 / 3

Distinctiveness Conflict Risk

Targets a clearly distinct niche (Databricks Lakebase Postgres / OLTP) with specific triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

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/databricks-agent-skills
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.