databricks-aibi-dashboards
Create Databricks AI/BI dashboards. Use when creating, updating, or deploying Lakeview dashboards. CRITICAL: You MUST test ALL SQL queries via execute_sql BEFORE deploying. Follow guidelines strictly.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 solid skill description with clear trigger terms and explicit 'Use when' guidance targeting a well-defined niche. Its main weakness is that the capability description could be more specific about what concrete actions the skill enables beyond the high-level create/update/deploy. The internal instruction about testing SQL queries and following guidelines is operational detail that slightly clutters the selection-oriented purpose of the description.
Suggestions
Expand the 'what' portion with more specific capabilities, e.g., 'Create charts, tables, filters, and layouts for Databricks AI/BI Lakeview dashboards' to improve specificity.
Move the 'CRITICAL: You MUST test ALL SQL queries...' instruction into the skill body rather than the description, as it's an execution guideline rather than a selection signal.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks AI/BI dashboards) and mentions actions like creating, updating, deploying, and testing SQL queries, but doesn't list specific concrete capabilities like chart types, layout configuration, data source setup, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (create Databricks AI/BI dashboards, test SQL queries, deploy) and 'when' ('Use when creating, updating, or deploying Lakeview dashboards'), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Databricks', 'AI/BI', 'dashboards', 'Lakeview', 'SQL queries', 'deploying'. Users asking about Databricks dashboards would naturally use these terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific product names (Databricks, Lakeview) and a clear niche (AI/BI dashboards). Very unlikely to conflict with other skills unless there are multiple Databricks-related skills. | 3 / 3 |
Total | 11 / 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 strong, well-structured skill that provides highly actionable guidance for creating Databricks dashboards. Its greatest strengths are the clear validation workflow with explicit feedback loops, concrete JSON examples showing correct vs incorrect patterns, and excellent progressive disclosure to reference files. The main area for improvement is minor redundancy in validation warnings and some overlap between inline guidelines and the quality checklist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and contains domain-specific knowledge Claude wouldn't inherently know (dashboard JSON structure, field matching rules, layout grid system). However, there's some redundancy—the validation workflow warning is repeated multiple times, and the quality checklist partially duplicates earlier sections. The WARNING callouts, while important, add verbosity. | 2 / 3 |
Actionability | Highly actionable with concrete JSON examples for correct and incorrect field matching patterns, specific SQL expression patterns, exact layout dimensions, and a clear tool-based workflow. The examples are copy-paste ready and the correct/wrong pattern comparison is particularly useful for avoiding common errors. | 3 / 3 |
Workflow Clarity | The mandatory validation workflow is exceptionally clear with a 5-step visual diagram, explicit validation at step 3 with a feedback loop (fix and re-test), and a pre-deployment quality checklist. The workflow correctly gates deployment on successful query validation, which is critical for avoiding broken dashboards. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference table pointing to one-level-deep files for widget specifications, filters, examples, and troubleshooting. The main SKILL.md provides essential guidelines and patterns while deferring detailed specifications to dedicated files. Related skills are also well-signaled at the bottom. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
b4071a0
- 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.