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

inset

GitHub

该技能用于诊断和处理数据缺失值。通过量化缺失程度、判断缺失机制及业务含义，选择删除或插补策略。流程包括使用工具识别字段、分析缺失、执行清理并验证结果变化，确保处理过程可追溯且符合用户意图。

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

Trigger Scenarios

需要处理数据中的缺失值请求对数据进行清洗以消除空值询问如何填补或删除NULL值

Install

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

More Options

Use without installing

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

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill inset -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": "inset",
    "description": "诊断并处理缺失值（missing value 缺失值处理）",
    "allowedTools": [
        "get_schema",
        "profile_data",
        "clean_data",
        "query_data"
    ]
}

缺失值处理

先量化字段和行级缺失，判断缺失机制及业务含义，再选择删除、常数、统计量或分组插补。修改前说明影响，保留可追溯结果，并在处理后验证缺失率和分布变化。

Tool routing

Use get_schema to identify tables, nullable fields, and candidate columns.
Use profile_data to quantify missingness before any modification.
Use clean_data with the appropriate missing-value operation only when the user intent is clear.
Use query_data after cleaning to verify row counts, remaining nulls, and distribution 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
Missing-value implementation: Function/Clean/missing_handler.py