Conciseness

The body is dense and information-rich — exact CLI invocations, a widget catalog table, and high-value non-obvious gotchas ("Elements are joined verbatim with no separator", "merged stderr breaks jq") with almost no explanation of concepts Claude already knows. Not anchor 5 because the "test ALL SQL queries" mandate is repeated (workflow header and checklist item 11), "Follow these guidelines strictly" appears twice, and the Spark SQL patterns section restates functions Claude knows; not anchor 3 because these are minor trims in an otherwise lean document.

Actionability

Fully executable throughout: copy-paste-ready commands (`databricks lakeview create ... -o json | jq -r '.dashboard_id'` with flag-only vs JSON-only field notes), a required JSON skeleton, an allowed-expression grammar for widget fields, and a 13-item pre-deploy checklist covering common failure modes. Specific examples cover the common cases, matching anchor 5.

Workflow Clarity

The 5-step creation workflow is clearly sequenced with explicit validation checkpoints (Step 3 "run the SQL Queries you intend to add in each dataset to confirm that they run properly", checklist item 11) and a feedback loop ("If values don't match expectations, ensure the query is correct, fix the data if you can, or adjust the story"). The update path adds a credential-mode verification step before publish, matching anchor 5.

Progressive Disclosure

The body is a genuine overview that routes to eight one-level-deep reference files, all verified to exist, via a Reference Files table, a widget-catalog Spec column mapping each widget to its file, and inline pointers with working section anchors (e.g., 7-dashboard-design.md#profiling-the-data). Navigation is easy and content is appropriately split, matching anchor 5.

Specificity

Lists several concrete actions ("Create Databricks AI/BI dashboards", "creating, updating, or deploying Lakeview dashboards", "test ALL SQL queries via CLI BEFORE deploying"), which matches anchor 4, but the second-person directive "You MUST test ALL SQL queries via CLI BEFORE deploying" violates the third-person voice rule, reducing specificity by 1. It sits above anchor 3 because it names more than 1-2 concrete actions, and the filler "Follow guidelines strictly" adds no capability.

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 anchor 5 pattern. It is not anchor 4 because the when-clause is explicit and specific rather than merely implied or generic.

Trigger Term Quality

Good keyword coverage of the product names users would naturally say — "Databricks AI/BI dashboards", "Lakeview dashboards", "Databricks Dashboard" — including the legacy synonym. Not anchor 5 because common variations like "chart", "KPI", "report", or "visualization" are absent; not anchor 3 because the core natural terms and synonyms are present.

Distinctiveness Conflict Risk

Clear niche with distinct triggers: "Databricks AI/BI dashboards" and "Lakeview dashboards" name a specific product, so minimal conflict risk even against sibling skills like databricks-apps. The trigger set is product-specific rather than generic, matching anchor 5.