CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-apps

Build apps on Databricks Apps platform. Use when asked to create dashboards, data apps, analytics tools, or visualizations. Auto-detects need for Lakebase when app stores state; evaluates data access patterns (analytics vs Lakebase synced tables) before scaffolding. Invoke BEFORE starting implementation.

65

Quality

80%

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

The canonical home for this skill is databricks-apps in databricks/databricks-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A well-structured, highly actionable skill body with clear phase-ordered workflows, explicit validation gates, and clean one-level-deep progressive disclosure into real reference files. The main weakness is conciseness: several rules and caveats are restated multiple times across sections.

Suggestions

Consolidate the app-name constraint (≤26 chars, lowercase letters/numbers/hyphens) into a single canonical location and cross-reference it from the Scaffolding and Directory Naming sections instead of restating it three times.

Tighten the Scaffolding Rules Protocol into a compact checklist; the five-step prose explanation largely describes runtime manifest consumption that can be expressed more tersely.

Dedupe the repeated 'DO NOT guess' / 'derive from manifest output' guidance so it appears once near the manifest step and is referenced elsewhere.

DimensionReasoningScore

Conciseness

Mostly efficient and oriented around anti-patterns/gotchas rather than basics Claude already knows, but the app-name constraint is restated three times and the Scaffolding Rules Protocol plus repeated 'DO NOT guess' guidance could be tightened.

3 / 5

Actionability

Concrete, mostly executable commands throughout (manifest, init, validate, docs, logs) with wrong-vs-correct examples, but API specifics are deliberately deferred to `npx @databricks/appkit docs` and several workflows delegate details to referenced guides.

4 / 5

Workflow Clarity

The Development Workflow is explicitly ordered with validation checkpoints (typegen → verify ✓ → update selectors → validate before deploy), a required user-facing Decision Gate, and feedback-loop guidance for smoke-test and validation failures.

5 / 5

Progressive Disclosure

A 'Required Reading by Phase' table maps each phase to a single one-level-deep reference file under references/ and references/appkit/, and every referenced path exists on disk; the body is a lean overview pointing to detail files.

5 / 5

Total

17

/

20

Passed

Description

83%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.

A strong, third-person description that clearly states capabilities and explicit trigger conditions, with concrete auto-detection and data-access behaviors that aid routing. Minor gains are possible in trigger synonym coverage and distinctiveness against sibling Databricks skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Build apps', 'create dashboards, data apps, analytics tools, or visualizations', 'Auto-detects need for Lakebase', 'evaluates data access patterns' — but 'Build apps on Databricks Apps platform' is a somewhat generic lead, leaving minor coverage gaps versus the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both what ('Build apps on Databricks Apps platform') and when ('Use when asked to create dashboards, data apps, analytics tools, or visualizations... Invoke BEFORE starting implementation') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'create dashboards, data apps, analytics tools, or visualizations' map well to what a user would say, though synonym coverage is limited and there are no file-extension-style anchors relevant to this domain.

4 / 5

Distinctiveness Conflict Risk

The 'Databricks Apps platform' niche is clear with distinct triggers, but it sits in a family with the parent databricks-core and databricks-lakebase skills, creating minor overlap risk with closely related skills.

4 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 21 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 21 deeper-than-1-level

Warning

Total

13

/

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.