CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

databricks-apps

Build apps on Databricks Apps platform. Use when asked to create data apps, analytics tools, or custom interactive visualizations. A plain "create a dashboard" request means a managed AI/BI (Lakeview) dashboard → use databricks-aibi-dashboards, not this skill. Evaluates data access patterns (analytics vs Lakebase synced tables) before scaffolding. Invoke BEFORE starting implementation.

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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-engineered skill body: an ordered workflow with mandatory decision gates and explicit validation checkpoints, copy-paste-ready CLI commands, and clean progressive disclosure into 18 verified reference files. The only notable flaw is modest redundancy — disambiguation prose repeated between description and body, and the app-name rule stated three times — which costs a little token efficiency.

DimensionReasoningScore

Conciseness

The body is dense with directives, commands, and gotchas and explains almost nothing Claude already knows, but there is redundant repetition — the dashboard-vs-app disambiguation from the description is restated in the long paragraphs at the top, and the ≤26-char lowercase-hyphen name rule appears three times (Generic Guidelines, Scaffolding section, Directory Naming) — fitting anchor 4 (minor trims possible) rather than anchor 5.

4 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: `databricks apps manifest`, `databricks apps init --name ... --features ... --set ...`, `npx @databricks/appkit docs`, `<pm> run typegen`, `databricks apps validate --profile`, and post-deploy `apps get`/`apps logs`, plus a wrong-vs-right scaffolding example — anchor 5.

5 / 5

Workflow Clarity

"Development Workflow (FOLLOW THIS ORDER)" sequences the decision gate before scaffolding with explicit numbered steps and validation checkpoints (typegen "verify all queries show ✓" before writing UI, `apps validate` before deploy, post-deploy status verification with the PAT/OAuth caveat), and the Required Reading by Phase table acts as a checklist — anchor 5.

5 / 5

Progressive Disclosure

The body works as an overview and routing layer: a phase-indexed table signals one-level-deep references for each task, a routing table maps data-access patterns to guides, and all 18 referenced files (references/*.md and references/appkit/*.md) exist on disk — anchor 5.

5 / 5

Total

19

/

20

Passed

Description

82%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 description that clearly states both what the skill does and when to use it, with excellent explicit boundary routing against the nearest competing skill. Its main weakness is a thin action list — it names the domain and the data-access evaluation step but omits the scaffold/typegen/validate/deploy verbs that would make capabilities comprehensive.

Suggestions

Enumerate the core actions in the description, e.g. "Scaffolds projects via databricks apps init, generates typed SQL query contracts, and validates/deploys with the Databricks CLI" to lift specificity from domain-plus-two-actions to several concrete actions.

Add one or two natural synonyms users would say, such as "custom app" or "interactive data tool", to broaden trigger-term coverage beyond "data apps / analytics tools / custom interactive visualizations".

DimensionReasoningScore

Specificity

"Build apps on Databricks Apps platform" and "Evaluates data access patterns (analytics vs Lakebase synced tables) before scaffolding" name the domain plus roughly two concrete actions, but the description never enumerates the core verbs the skill performs (scaffold via apps init, generate types, validate, deploy), matching anchor 3 rather than the 'several specific actions' of anchor 4.

3 / 5

Completeness

It explicitly answers both questions: what ("Build apps on Databricks Apps platform") and when ("Use when asked to create data apps, analytics tools, or custom interactive visualizations") with concrete trigger phrases and a timing directive ("Invoke BEFORE starting implementation"), clearly matching anchor 5.

5 / 5

Trigger Term Quality

"data apps", "analytics tools", "custom interactive visualizations", and "create a dashboard" are natural user phrases with good coverage, but common synonyms a user might say (e.g. "custom app", "internal tool", "interactive tool") are absent, fitting anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

It explicitly routes the most likely wrong-trigger case away ("A plain 'create a dashboard' request means a managed AI/BI (Lakeview) dashboard → use databricks-aibi-dashboards, not this skill"), giving a clear niche with minimal conflict risk — anchor 5.

5 / 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.

Validation — 13 / 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: 31 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 31 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

databricks/databricks-agent-skills

Path

plugins/databricks/antigravity/skills/databricks-apps/SKILL.md

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.