databricks-apps
Build apps on Databricks Apps platform. Use when asked to create dashboards, data apps, analytics tools, or visualizations. Evaluates data access patterns (analytics vs Lakebase synced tables) before scaffolding. Invoke BEFORE starting implementation.
93
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong skill description that clearly identifies the platform (Databricks Apps), lists concrete use cases (dashboards, data apps, analytics tools, visualizations), and provides explicit trigger guidance. The inclusion of workflow timing ('Invoke BEFORE starting implementation') and the evaluation step for data access patterns adds valuable specificity. It uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Build apps on Databricks Apps platform', 'create dashboards, data apps, analytics tools, or visualizations', 'Evaluates data access patterns', and 'scaffolding'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Build apps on Databricks Apps platform, evaluates data access patterns before scaffolding') and when ('Use when asked to create dashboards, data apps, analytics tools, or visualizations'). Also includes timing guidance ('Invoke BEFORE starting implementation'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'dashboards', 'data apps', 'analytics tools', 'visualizations', 'Databricks Apps'. Also includes technical terms like 'Lakebase synced tables' that domain users would use. Good coverage of natural terms. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to the Databricks Apps platform specifically, with distinct triggers like 'Databricks Apps', 'Lakebase synced tables', and 'data access patterns'. Unlikely to conflict with generic app-building or visualization skills due to the platform-specific framing. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that serves as an effective routing document for Databricks Apps development. Its strongest aspects are the actionable CLI commands, the explicit decision gate workflow requiring user input before proceeding, and the clean progressive disclosure via phase-based reference links. Minor verbosity from repeated constraints and some overlap between the decision gate and routing table prevent a perfect conciseness score.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows (React, TypeScript, SQL), but there's some repetition — the decision gate table and routing table overlap, and several warnings are repeated (e.g., app name constraints appear twice). The scaffolding section is thorough but could be tighter. | 2 / 3 |
Actionability | Provides concrete, executable CLI commands for every step (manifest, init, validate), specific flag syntax with examples, correct/incorrect command comparisons, and clear routing tables for which pattern to use. The scaffolding workflow is copy-paste ready with explicit --set syntax derived from manifest output. | 3 / 3 |
Workflow Clarity | The development workflow is clearly sequenced with an explicit decision gate before scaffolding, numbered steps for analytics apps (SQL → typegen → read types → write UI → update tests → validate), and validation checkpoints. The 'DO NOT write UI code before running typegen' warning and the required user confirmation at the decision gate are strong feedback loops. | 3 / 3 |
Progressive Disclosure | Excellent structure with a phase-based reference table at the top, clear one-level-deep links to specific guides (SQL, frontend, Lakebase, Genie, etc.), and the SKILL.md serves as a concise overview/routing document. The `npx @databricks/appkit docs` command provides an additional discovery layer for API details. | 3 / 3 |
Total | 11 / 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/databricks-agent-skills
- Commit
f1c9cf7
- 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.