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

sarima

GitHub

利用SARIMA模型进行季节性时间序列预测。通过校验数据频率与周期，执行参数估计、误差分析及预测区间计算，并生成可视化图表，适用于业务数据分析场景。

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

Trigger Scenarios

需要进行季节性时间序列预测分析历史数据的季节模式与趋势

Install

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

More Options

Use without installing

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

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill sarima -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": "sarima",
    "description": "使用 SARIMA 建模季节性时间序列预测（forecast）",
    "allowedTools": [
        "get_schema",
        "query_data",
        "run_analysis",
        "generate_chart"
    ]
}

SARIMA 预测

确认时间频率和季节周期，检查数据长度能否覆盖足够周期。执行季节模型与时间验证，报告参数、误差、预测区间和季节模式；数据不足时不要强行拟合。

Tool routing

Use get_schema to identify the time column, target column, seasonal frequency, and source table.
Use query_data only to verify sorted frequency, missing periods, and enough seasonal cycles.
Use run_analysis with analysis_name="Time_Series_SARIMA" for the actual forecast computation.
Use generate_chart on forecast or seasonal diagnostic result tables after run_analysis succeeds.