Suitable for pet grooming, bathing, and store services; clinical diagnosis, medication advice, or animal medical care are outside this skill.
Execution Points
Cream base, orange action highlights, dark brown borders, rounded cards; mint and light pink for a small amount of service categorization, and in-chart data must have sufficient contrast. The top is organized by store, date, and staff filters, followed by booked/attended/cancelled counts and trends, then service combinations and shift details. Customers and pets are separate entities; multiple pets in a household must not be counted repeatedly as multiple customers; repeat purchases are defined by a stable customer key and observation window. Cross-day shifts and overlapping bookings are calculated by actual start and end times; utilization is not output when total scheduled hours are missing. Satisfaction is shown together with the number of valid reviews; unreviewed is not treated as negative; lists show only fields necessary for the task. Primary color #E87B36, background #FFF6E9, body text #4B352A, accent #77AD9F.
Conversation Examples
For "which store can't keep up," combine booking peaks, available staff, and hours; when only service counts are available, state that they are only a workload proxy and do not claim staff efficiency.
How DB-GPT Works
- Communicate in the user's language. First infer intent from the selected data, prior context, dashboard, and annotations; when the expression is ambiguous but workable, state one reasonable assumption and continue. Ask one specific question only for gaps that would change the result, and do not repeat generic clarification phrases.
- The selected database is used for read-only discovery only; confirm fields, granularity, units, date ranges, null values, and unique keys. When there is no data, layout can still be discussed; before generating actual metrics, ask the user to select a data source. Illustrative values must be clearly labeled and never disguised as query results.
- When creating an editable dashboard, call the existing dashboard tool and load the dashboard-builder workflow: first plan_dashboard, and create according to the existing confirmation flow; when modifying an existing dashboard, first load_dashboard_draft, then propose changes matching the version. Visual specifications supplement the business plan and cannot skip SQL validation, saving, or publishing rules.
- Use the report generation tool only when the user explicitly asks for an HTML report; a native dashboard must not be secretly replaced with an image or standalone HTML. The native schema uses only the fields, chart types, and theme attributes allowed by the tool, and does not pass arbitrary CSS or nonexistent layout enums. Decorations that cannot be fully expressed should be reduced to usable color schemes/layouts, with the differences explained.
- Before editing, preserve the user's data, metric definitions, and unmodified components. Metric changes must update titles, units, and calculation definitions accordingly; for ratio aggregation, sum numerators and denominators first. Do not fabricate targets, year-over-year comparisons, or forecasts when there is no target data.
- Before delivery, check empty results, long labels, narrow screens, light and dark themes, legends, zero values, and missing values; animations respect the user's reduced-motion preference. Report only execution results confirmed by the tool.
Resources and Boundaries
This directory is a DB-GPT product skill; it does not modify host global configuration, install external scripts, or send data to reference websites. It uses fonts already provided by the system and project, and falls back to Chinese fonts when external fonts are missing. The interface shows a style demonstration; business values come from the selected data in actual use.
Reference Sources
Reference Sive's related skills for scenario and visual direction; the rules were rewritten by DB-GPT Dashboard Lab and are not an official Sive release package.