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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a strong validation-driven workflow, but it is held back by repeated mandatory-testing warnings and a broken progressive-disclosure layer where every signaled reference file is missing from the bundle.

Suggestions

Provide the four missing reference files (1-widget-specifications.md, 2-filters.md, 3-examples.md, 4-troubleshooting.md) so the Reference Files table resolves to real content.

Consolidate the repeated 'test every query via execute_sql' message into the workflow box and the checklist, removing the standalone WARNING line and the duplicated emphasis in the tools table.

Move the detailed inline widget-expression and layout-grid specifications into 1-widget-specifications.md to reduce body length and let SKILL.md function as a true overview.

Dimension	Reasoning	Score
Conciseness	The technical guidance is domain-specific and not padded with concepts Claude already knows, but the mandatory-testing message is repeated across the ASCII workflow box, the tools table, a WARNING line, and checklist item 11, and the heavy uppercase/bold emphasis ('CRITICAL', 'MANDATORY', 'DO NOT SKIP') could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: exact manage_dashboard calls with real parameters, correct-vs-wrong JSON field patterns, and specific expression/layout snippets rather than vague direction.	3 / 3
Workflow Clarity	The five-step workflow is clearly sequenced with an explicit validation checkpoint (STEP 3 test via execute_sql), a fix-before-proceeding feedback loop, and an 11-item pre-deploy quality checklist.	3 / 3
Progressive Disclosure	The Reference Files table is well-signaled and one level deep, but all four referenced files (1-widget-specifications.md, 2-filters.md, 3-examples.md, 4-troubleshooting.md) are absent from the bundle, so navigation leads to dead ends; substantial inline widget/layout/cardinality detail also overlaps what those references should hold.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, specific description with an explicit Use-when trigger and both current and legacy product names. Its only real flaw is the second-person 'You MUST' phrasing, which breaks the third-person voice convention and costs a specificity point.

Suggestions

Rewrite the description in third person to remove the second-person 'You MUST test ALL SQL queries', e.g. 'Tests all SQL queries via execute_sql before deploying.'

Consider trimming 'CRITICAL: ... Follow guidelines strictly.' — the mandatory-testing point is enforced in the body and the emphasis reads as filler in the description.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Create Databricks AI/BI dashboards', 'creating, updating, or deploying', 'test ALL SQL queries via execute_sql') which would merit a 3, but the second-person 'You MUST test ALL SQL queries' violates the required third-person voice and incurs the rubric's -1 specificity penalty.	2 / 3
Completeness	Clearly answers both what ('Create Databricks AI/BI dashboards') and when via an explicit 'Use when creating, updating, or deploying Lakeview dashboards' trigger clause.	3 / 3
Trigger Term Quality	Covers the natural product names a user would say for both the current and former branding — 'Databricks AI/BI dashboards' and 'Lakeview dashboards' — alongside action verbs, giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	The 'Databricks AI/BI dashboards' / 'Lakeview dashboards' niche is highly specific with distinct triggers, making accidental activation for unrelated skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing, 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Path: databricks-skills/databricks-aibi-dashboards/SKILL.md
Commit: a7e1d51

Reviewed: about 5 hours ago

Table of Contents

Discovery Implementation Validation

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.