Suitable for online courses, training, and learner progress; do not judge an individual's ability or motivation based on a single score.
Implementation Points
Cream canvas, peach and sky blue as accent colors, dark brown outlines; rounded cards and light hard shadows create a modular feel. Titles and numbers still use locally available Chinese fonts; downloading fonts is not required. The top shows participant count, completed count, and completion rate; the middle shows course progress and time trends; the bottom shows class/course details. The denominator of the completion rate is learners or enrollment records that meet the participation criteria; clearly state whether withdrawals/not-started are included. Different courses have different full scores and durations and must be standardized before comparison; unsubmitted assignments and 0 scores are kept separate. An empty class does not show 100% completion, and tasks that are not yet due are not counted as overdue. Body text #39312E, background #FFF8E9, action green #429079, contrast blue #85B5DA, peach #E8AD98; progress is paired with percentages and numerators/denominators so it can be read independently of color.
Dialogue Examples
When asked "is this course effective," combine participation, completion, ratings, and sample size, and do not report only the average score; distinguish between those who have completed and those still learning.
How DB-GPT Works
- Communicate in the user's language. First infer intent from the selected data, prior context, dashboards, and annotations; when the expression is vague but actionable, 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.
- The selected database is used only for read-only discovery; confirm fields, granularity, units, date ranges, null values, and unique keys. When there is no data, layout can still be discussed; before actual metrics are generated, 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. The visual specification supplements the business plan and must not skip SQL validation, saving, or publishing rules.
- Only use the report generation tool 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; do not pass arbitrary CSS or nonexistent layout enums. Decorations that cannot be fully expressed should be reduced to usable color schemes/layouts, and the differences should be 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 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 should 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 the host's global configuration, does not install external scripts, and does not 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 skill for the scenario and visual direction; the rules were rewritten by DB-GPT Dashboard Lab and are not an official Sive release package.