Name: databricks-aibi-dashboards
Rating: 68 (1 reviews)
Author: databricks

databricks-aibi-dashboards

Create Databricks AI/BI dashboards. Must use when creating, updating, or deploying Lakeview dashboards as Databricks Dashboard have a unique json structure. CRITICAL: You MUST test ALL SQL queries via CLI 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

85%Weight 40%Scale 1-5

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 well-sequenced validated workflow and excellent progressive disclosure to real reference files. The only meaningful weakness is conciseness: repeated emphasis of the same CLI gotchas and some coaching prose inflate the token budget.

Suggestions

State the bare-table-name and --dataset-catalog/--dataset-schema flag-only rules once in an authoritative location and cross-reference it instead of repeating the full explanation in Quick Reference, Step 2, Step 5 comments, and Implementation Guidelines.

Trim coaching prose such as "A good dashboard comes from knowing the data first. Spend time here — the exploration drives design decisions..." to directive guidance.

Consider moving the extended Theme & Color / palette-design rules into a reference file (e.g. references/7-theme-and-color.md) to shorten the body while keeping a concise 60/30/10 summary inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with product-specific gotchas Claude does not know, but it includes coaching prose ("A good dashboard comes from knowing the data first. Spend time here...") and repeats the bare-table-name and flag-only rules across Quick Reference, Step 2, Step 5 comments, and Implementation Guidelines, which could be tightened.	3 / 5
Actionability	Fully executable guidance throughout: exact databricks CLI commands with precise flags, copy-paste-ready JSON skeletons, and concrete examples covering create/update/publish/delete and widget definitions.	5 / 5
Workflow Clarity	The NEW DASHBOARD CREATION WORKFLOW is a clear five-step sequence with explicit validation ("You MUST test ALL SQL queries via CLI BEFORE deploying", Step 3 verify-data checkpoint), a feedback loop ("If values don't match expectations... adjust the story before creating the dashboard"), and a 13-item Quality Checklist before deploy.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references; the Widget Index and Reference Files tables map tasks to references/1-6 files, all of which exist on disk, and detailed widget specs are appropriately split out from the body.	5 / 5
	Total	18 / 20 Passed

Description

82%Weight 40%Scale 1-5

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 strong, explicitly covering both capability and trigger conditions with product-specific terms. Its main weakness is the second-person "You MUST test..." phrasing, which the rubric penalizes, and slightly incomplete action coverage.

Suggestions

Rewrite in third person to avoid the second-person penalty, e.g. "Tests all SQL queries via CLI before deploying" instead of "You MUST test ALL SQL queries".

Expand the action list to surface more of the building-block capabilities (e.g. add filters, theme/palette, widgets) so specificity reaches comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("Create", "creating, updating, or deploying", "test ALL SQL queries via CLI"), but coverage of the dashboard-building surface is partial; base 4 reduced by 1 because the description uses second person ("You MUST test ALL SQL queries"), which the rubric penalizes.	3 / 5
Completeness	Explicitly answers both what ("Create Databricks AI/BI dashboards") and when ("Must use when creating, updating, or deploying Lakeview dashboards") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes the natural product terms a user would say ("Databricks AI/BI dashboards", "Lakeview dashboards", "Databricks Dashboard"); a few generic synonyms ("visualize", "report") are absent, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Databricks AI/BI / Lakeview dashboards) with product-specific triggers, so it is unlikely to fire for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (550 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	13 / 16 Passed

Repository: databricks/databricks-agent-skills
Path: plugins/databricks/claude/skills/databricks-aibi-dashboards/SKILL.md
Commit: 691deaa

Reviewed: 5 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.