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 specific product domain. The main weakness is that the capability description could be more specific about what kinds of dashboard operations are supported. The 'CRITICAL' and 'Follow guidelines strictly' portions are internal instructions that don't help with skill selection and add noise.
Suggestions
Expand the capability list with more specific actions (e.g., 'create charts, configure filters, define datasets, manage layouts') to improve specificity.
Remove internal process instructions ('CRITICAL: You MUST test ALL SQL queries...', 'Follow guidelines strictly') from the description since these don't aid skill selection and belong in the skill body.
| 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, AI/BI) that create a clear niche unlikely to conflict with other skills like generic SQL or dashboard tools. | 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 clear, actionable guidance for building Databricks dashboards. The mandatory validation workflow with explicit feedback loops is excellent, and the progressive disclosure to reference files is well-organized. Minor verbosity from repeated warnings and some sections that could be tightened slightly prevent a perfect conciseness score, but overall this is a high-quality skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but some sections are slightly verbose—e.g., the WARNING/CRITICAL callouts are repeated multiple times, and the tool table + examples could be tightened. The ASCII workflow box adds visual weight. Overall reasonable but not maximally lean. | 2 / 3 |
Actionability | Provides concrete, executable JSON patterns, specific tool invocations with parameters, exact SQL function names, precise layout coordinates, and copy-paste-ready code examples. The field matching rules include both correct and incorrect patterns, making guidance unambiguous. | 3 / 3 |
Workflow Clarity | The 5-step mandatory validation workflow is clearly sequenced with explicit validation at step 3 (execute_sql), a fix-and-retry feedback loop, and a quality checklist before deployment. The workflow explicitly gates deployment on successful query testing, which is exactly the right pattern for this destructive/batch operation. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to widget specifications, filters, examples, and troubleshooting files. Related skills are also linked. The main file contains the essential workflow and guidelines without burying details that belong in reference files. | 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
02aac8c
- 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.