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

winsorize

GitHub

对数值字段执行缩尾处理以消除极端值。流程包括识别目标列、分析分布、设定边界后清洗，并对比处理前后的数据分布与关键指标，记录受影响行数，确保不默认覆盖原始数据。

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

Trigger Scenarios

需要处理数据中的异常值或极端值需要对数值字段进行缩尾（Winsorize）操作

Install

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

More Options

Use without installing

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

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill winsorize -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": "winsorize",
    "description": "对极端值执行缩尾处理并验证影响（outlier 缩尾）",
    "allowedTools": [
        "get_schema",
        "profile_data",
        "clean_data",
        "query_data"
    ]
}

缩尾处理

识别目标数值字段和异常分布，说明上下界规则后再缩尾。不得默认覆盖原始数据；比较处理前后的分布、均值和关键指标，并记录边界与受影响行数。

Tool routing

Use get_schema to identify the target table and candidate numeric columns.
Use profile_data to quantify distribution tails before modification.
Use clean_data with the winsorize operation only after the percentile bounds are clear.
Use query_data after cleaning to verify clipped values, row counts, and key metric changes.

Implementation reference

Tool entries: agent/tools/business/data.py::_tool_profile_data, agent/tools/business/data.py::_tool_clean_data
Profiling implementation: Function/Clean/data_profile.py
Winsorization implementation: Function/Clean/winsorize.py