Agent Skills › Zafer-Liu/Data-Analysis-Agent › prophet

prophet

GitHub

利用Prophet模型进行时间序列预测，分解趋势与季节性。需识别时间列、目标及节假日，验证数据频率与异常，执行预测并可视化结果，提示结构突变。

skills/prophet/SKILL.md Zafer-Liu/Data-Analysis-Agent

Trigger Scenarios

需要进行时间序列预测需要分解数据的趋势和季节性成分

Install

npx skills add Zafer-Liu/Data-Analysis-Agent --skill prophet -g -y

More Options

Use without installing

npx skills use Zafer-Liu/Data-Analysis-Agent@prophet

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill prophet -a claude-code -g -y

安装 repo 全部 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --all -g -y

预览 repo 内 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --list

SKILL.md

Frontmatter

{
    "icon": "🔮",
    "name": "prophet",
    "description": "使用 Prophet 分解趋势季节性并预测（forecast 时间序列预测）",
    "allowedTools": [
        "get_schema",
        "query_data",
        "run_analysis",
        "generate_chart"
    ]
}

Prophet 预测

确认时间列、目标、频率、预测期及已知节假日。用时间切分验证，展示趋势、季节性、预测区间和误差；异常点或结构突变应单独提示。

Tool routing

Use get_schema to identify the time column, target column, known holiday or event fields, and source table.
Use query_data only to verify frequency, gaps, outliers, and enough history for trend and seasonality.
Use run_analysis with analysis_name="Time_Series_Prophet" for the actual forecast computation.
Use generate_chart on forecast, trend, or seasonality result tables after run_analysis succeeds.