Agent Skills
› Zafer-Liu/Data-Analysis-Agent
› decile
decile
GitHub执行十分位分层分析,将样本等频划分为十组以识别高低价值群体。通过确认指标与实体,计算各组分布及累计贡献,处理空值并输出可执行的分层策略及可视化图表。
Trigger Scenarios
需要进行用户或数据分层分析
请求进行十分位(Decile)计算
识别高价值与低价值客户群体
Install
npx skills add Zafer-Liu/Data-Analysis-Agent --skill decile -g -y
SKILL.md
Frontmatter
{
"icon": "📉",
"name": "decile",
"description": "执行十分位分层分析并识别高低价值群体(segmentation 分层分析)",
"allowedTools": [
"get_schema",
"query_data",
"run_analysis",
"generate_chart"
]
}
十分位分析
确认排序指标、分析实体和方向,将有效样本等频划分为十组,报告每组样本量、指标范围、核心结果及累计贡献。标记空值和并列值处理方式,并给出可执行的分层策略。
Tool routing
- Use
get_schemato identify the entity key, ranking metric, target metric, and source table. - Use
query_datato verify field names, null handling needs, and sample distribution. - Use
run_analysiswithanalysis_name="Data_Decile_Analysis"for the decile computation. - Use
generate_charton returned decile result tables afterrun_analysissucceeds.
Implementation reference
- Tool entry:
agent/tools/business/data.py::_tool_run_analysis - Analysis registry:
Function/Analyze/registry.py - Analysis implementation:
Function/Analyze/Data_Decile_Analysis/analyze.py - Chart implementation:
Function/Charts_generation/chart_generate.py
Version History
- d6a2c3e Current 2026-07-24 12:12


