Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/codebook-pass
调查数据清洗Skill。处理调查数据（CGSS/CHIP/CSS等）时的标准化清洗流程，包括缺失值处理、变量编码统一、数据异常值检测。触发词：数据清洗/调查数据/codebook/数据清洗流程/问卷数据处理
Passed 6 of 19 test cases with the skill, and 13 of 19 without it.
and 2 more in the full report
3 fixed13 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Show me the required JSON structure for documenting variable transformations when cleaning survey variable cgss_2021_urban (originally coded as 1=Urban, 2=Rural, 9=Unknown).
| Checked | Without skill | With skill |
|---|---|---|
| Structures the provenance JSON variable entry with keys original_codes, transformed_codes, and missing_handling | Missed | Passed |
The instructions your model reads when the skill loads.
本 Skill 是处理中国综合社会调查（CGSS）、中国家庭收入调查（CHIP）、中国社会科学调查（CSS）等大型调查数据的标准化清洗流程。确保从 codebook 到可用面板数据的每一步都可审计、可复现。
调查数据清洗的核心原则：原始数据只读不修改，所有转换操作记录在 processed/ 文件夹中，且必须更新 provenance.json。
三个关键规则：
processed/ 文件夹中进行原始数据 → 导入检查 → 变量命名规范化 → 缺失值处理 → 异常值处理 → 编码统一 → 合并面板 → 输出报告
必须执行：
import pandas as pd
import numpy as np
# 读取原始数据
df = pd.read_stata("data/raw/cgss2021.dta")
# 基础检查
print(f"样本量: {len(df)}")
print(f"变量数: {len(df.columns)}")
test cases passed, vs 13 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.