# Trimming

> Trimming is an Agent Skill for general use 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.

对异常样本执行截尾处理并评估偏差

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

## SKILL.md

# 截尾处理

先定义异常判据和业务合理范围，量化拟删除样本及其特征。仅在用户意图明确时执行，保留原始数据和可追溯输出；处理后报告样本损失及潜在选择偏差。

## Tool routing

1. Use `get_schema` to identify the target table and candidate numeric columns.
2. Use `profile_data` to quantify outliers and candidate trim boundaries before modification.
3. Use `clean_data` with the trimming operation only when the user has confirmed the rule or bounds.
4. Use `query_data` after cleaning to verify row loss, boundary effects, 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`
- Trimming implementation: `Function/Clean/trimming.py`

---

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