# Decile

> Decile is an Agent Skill for business published in the Zafer-Liu/Data-Analysis-Agent repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

执行十分位分层分析并识别高低价值群体

- Skill name: `decile`
- Category: [Business](https://www.openparable.com/skill/business/1)
- Source: https://github.com/Zafer-Liu/Data-Analysis-Agent/blob/HEAD/skills/decile/SKILL.md
- Repository: Zafer-Liu/Data-Analysis-Agent (2,062 GitHub stars when collected)

## SKILL.md

# 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

1. Use `get_schema` to identify the entity key, ranking metric, target metric, and source table.
2. Use `query_data` to verify field names, null handling needs, and sample distribution.
3. Use `run_analysis` with `analysis_name="Data_Decile_Analysis"` for the decile computation.
4. Use `generate_chart` on returned decile result tables after `run_analysis` succeeds.

## 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`

---

Source: https://www.openparable.com/skill/business/decile (OpenParable). Cite the canonical URL above.
