Suitable for business scheduling and appointment analysis in beauty and SPA settings; do not output medical effects, diagnoses, or treatment recommendations.
Execution Points
Establish hierarchy with plum-toned navigation, rose-beige work areas, and white schedule panels; use sage green to express confirmed status and room status, and reserve gold for small-area emphasis. The weekly calendar and appointment list are the visual focus, room load goes in a narrow right-hand column, and business metrics are collected at the bottom; avoid resembling the orange three-metric layout of pet stores. Use motion for switching dates and updating status, and respect reduced-motion settings. Do not sacrifice text contrast for softness. Calculate room utilization based on effective available time slots, excluding and clearly stating maintenance/closed periods; separate appointments, arrivals, cancellations, and completions, and separate package sales from actual redeemed revenue to avoid double counting. Base membership tiers on verifiable purchase/visit records; do not estimate repurchase rates without a unique ID. Sensitive personal notes do not enter public large screens. Titles can use a local Songti fallback to create hierarchy, and body text uses DB-GPT's existing sans-serif. Background #F8F2EE, text #533D50, primary color #795E71, secondary colors #799681/#DCB991.
Conversation Examples
When asked to "help me optimize the schedule," propose suggestions based on available rooms, service duration, and appointment peaks; suggestions only, do not modify actual appointments or employee schedules.
How DB-GPT Works
- Communicate in the user's language. First infer intent from selected data, prior context, the dashboard, and annotations; when the expression is vague but progress is possible, state one reasonable assumption and continue. Ask only one specific question when a gap would change the result, and do not repeat generic clarification phrases.
- Selected databases are 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, then create according to the existing confirmation process; when modifying an existing dashboard, first load_dashboard_draft, then propose changes matching the version. Visual specification supplements the business plan and must not skip SQL validation, saving, or publishing rules.
- Use the report generation tool only when the user explicitly requests 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; do not pass arbitrary CSS or nonexistent layout enums. Decorations that cannot be fully expressed should be reduced to usable color schemes/layouts, with differences explained.
- Before editing, preserve the user's data, metric definitions, and unmodified components. Metric changes must synchronize titles, units, and calculation definitions; for ratio aggregation, total the numerator and denominator first. Do not fabricate targets, year-over-year comparisons, or forecasts when target data is absent.
- Before delivery, check empty results, long labels, narrow screens, light and dark themes, legends, zero values, and missing values; animations respond to 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. Use fonts already provided by the system and project; when external fonts are missing, use Chinese fallbacks. The interface displays style illustrations; business values come from the selected data in actual use.
Reference Sources
Reference Skills related to Sive scenario and visual direction, with rules rewritten by DB-GPT Dashboard Lab; not an official Sive release package.