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

arima

GitHub

基于ARIMA模型进行单变量时间序列预测。通过识别时间列与目标列，验证数据质量后执行预测计算，并生成可视化图表，输出预测值、置信区间及误差指标。

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

Trigger Scenarios

需要进行时间序列预测使用ARIMA模型分析历史数据趋势

Install

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

More Options

Use without installing

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

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill arima -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": "arima",
    "description": "使用 ARIMA 进行单变量时间序列预测（forecast）",
    "allowedTools": [
        "get_schema",
        "query_data",
        "run_analysis",
        "generate_chart"
    ]
}

ARIMA 预测

确认时间列、频率、目标和预测区间，按时间排序并处理缺口。检查平稳性，选择合理参数，使用时间切分验证，输出预测值、区间和误差，并说明外部冲击限制。

Tool routing

Use get_schema to identify the time column, target column, table name, and available covariates.
Use query_data only to verify ordering, missing timestamps, frequency, and enough rows for modeling.
Use run_analysis with analysis_name="Time_Series_ARIMA" for the actual forecast computation.
Use generate_chart on the returned forecast or diagnostic result tables after run_analysis succeeds.