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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

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

The content is highly actionable, concise, and features an exemplary validated workflow, but progressive disclosure is undercut by missing referenced bundle files and a fair amount of detail kept inline. Fixing the broken references would raise the overall quality.

Suggestions

Create the missing references/ files (1-widget-specifications.md, 2-filters.md, 3-examples.md, 4-troubleshooting.md) so the signaled navigation actually resolves.

Move the inline widget field-expression and layout detail into 1-widget-specifications.md to keep SKILL.md a true overview, keeping only the workflow and rules in the body.

Verify referenced paths match actual bundle filenames to avoid dead links.

Dimension	Reasoning	Score
Conciseness	The body is dense with tables, JSON/SQL snippets, and concrete rules, with no explanations of concepts Claude already knows; the repeated CRITICAL/WARNING emphasis is the only minor padding and each line carries actionable information.	3 / 3
Actionability	It provides executable JSON field expressions, exact tool actions with required params, copy-paste manage_dashboard examples, and precise layout/cardinality rules — fully concrete and instruction-ready.	3 / 3
Workflow Clarity	A five-step workflow is explicitly sequenced with a mandatory validation checkpoint (STEP 3: TEST EVERY QUERY), a fix-and-retry feedback loop, and an 11-item pre-deploy quality checklist.	3 / 3
Progressive Disclosure	The "What are you building?" table signals one-level-deep references well, but the referenced files (1-widget-specifications.md, 2-filters.md, 3-examples.md, 4-troubleshooting.md) do not exist in a references/ directory, so navigation is broken, and substantial spec detail is inline rather than split out.	2 / 3
	Total	11 / 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.

The description is specific, complete with an explicit trigger, and clearly niched; its only weakness is the second-person "You MUST test..." instruction, which violates the third-person-voice guideline and lowers specificity. The rest of the criteria are strong.

Suggestions

Rephrase "You MUST test ALL SQL queries via execute_sql BEFORE deploying" in third person (e.g., "Tests all SQL queries via execute_sql before deploying") to avoid the voice penalty.

Move the validation imperative out of the description into the body, keeping the description a concise capability + trigger statement.

Dimension	Reasoning	Score
Specificity	"Create Databricks AI/BI dashboards" and "creating, updating, or deploying" name multiple concrete actions, matching the score-3 anchor, but the second-person clause "You MUST test ALL SQL queries" triggers the rubric's −1 specificity penalty for non-third-person voice.	2 / 3
Completeness	It states what the skill does ("Create Databricks AI/BI dashboards") and provides an explicit "Use when creating, updating, or deploying Lakeview dashboards" trigger, satisfying both what and when.	3 / 3
Trigger Term Quality	"Databricks AI/BI dashboards" and "Lakeview dashboards" cover the natural terms a user would say, including the former product name, giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The Databricks AI/BI / Lakeview dashboard niche has distinct triggers and is unlikely to fire for unrelated skills.	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
Commit: 1c43c21

Reviewed: 3 days 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.