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

regression

GitHub

执行线性回归分析，验证数据假设并计算模型指标。通过工具路由获取Schema、查询数据、运行回归分析及生成图表，解释变量影响与不确定性。

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

Trigger Scenarios

需要分析连续目标变量与解释变量关系进行线性回归建模与结果可视化

Install

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

More Options

Use without installing

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

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill regression -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": "regression",
    "description": "执行线性回归并解释关键变量影响（linear regression 回归分析）",
    "allowedTools": [
        "get_schema",
        "query_data",
        "run_analysis",
        "generate_chart"
    ]
}

线性回归

确认连续目标、解释变量和分析口径，检查缺失、异常、共线性与残差假设。报告拟合与验证指标、系数方向和不确定性；明确相关关系不等于因果关系。

Tool routing

Use get_schema to identify the continuous target, candidate predictors, and source table.
Use query_data to verify field names, missingness, outliers, and whether the target is numeric.
Use run_analysis with analysis_name="Regression" for the actual regression computation.
Use generate_chart on coefficient, residual, or prediction result tables after run_analysis succeeds.