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

logistic

GitHub

执行二分类或多分类逻辑回归分析。通过检查目标编码、正类定义、特征泄漏及类别不平衡，计算模型指标与系数，生成ROC等图表，并将统计结果转化为业务含义。

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

Trigger Scenarios

需要构建逻辑回归模型分析变量对二分类结果的影响评估多分类问题的概率预测

Install

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

More Options

Use without installing

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

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill logistic -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": "logistic",
    "description": "执行二分类或多分类逻辑回归分析（logistic regression 分类）",
    "allowedTools": [
        "get_schema",
        "query_data",
        "run_analysis",
        "generate_chart"
    ]
}

逻辑回归

确认目标编码、正类定义和特征，检查泄漏、共线性及类别不平衡。报告验证集指标、系数或优势比及不确定性，并把模型结论翻译成业务含义。

Tool routing

Use get_schema to identify the target, positive-class definition, features, and source table.
Use query_data to verify class balance, coding, missingness, and candidate feature fields.
Use run_analysis with analysis_name="Logistic_Regression" for the actual model computation.
Use generate_chart on ROC, feature importance, or result tables after run_analysis succeeds.