luzhiyu-econ/data-quality-audit
wiki/attachments/skills/data-quality-audit/SKILL.md
对数据文件进行全面质量审计，检查缺失值、异常值、编码和面板完整性。
testing
Updated Apr 7, 2026
$ install --global
skillsauthnpx skillsauth add luzhiyu-econ/luzhiyu-econ.github.io data-quality-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 7, 2026, 3:16 AM37.0s1 file scanned
SKILL.md
- name:
- data-quality-audit
- description:
- 对数据文件进行全面质量审计，检查缺失值、异常值、编码和面板完整性。
审计数据文件：$ARGUMENTS
执行以下检查并输出报告：
1. 基本信息
- 文件格式、编码（尝试 UTF-8/GBK/GB18030）
- 行数、列数、文件大小
2. 变量检查
- 列出所有变量名、数据类型
- 标记可能的 ID 变量和时间变量
3. 缺失值分析
- 每个变量的缺失比例
- 缺失比例 > 30% 的变量标记为高风险
- 缺失模式分析（随机缺失 vs 系统性缺失）
4. 异常值检测
- 数值变量：超过 3 倍标准差的观测数量
- 建议 winsorize 的上下限（1% 和 99% 分位数）
5. 面板数据检查（如果检测到面板结构）
- Entity-Time 唯一性检验
- 面板是否平衡（balanced）
- 缺失的 entity-time 组合数量
6. 汇总建议
- 数据可用性评分（A/B/C/D）
- 必须处理的问题清单
- 建议的清洗步骤
输出到 output/data_quality_report.md
Related Skills
luzhiyu-econ/stata-to-python
development
VerifiedTrustedCommunity
将 Stata .do 文件翻译为等效的 Python 脚本。
SKILL.mdUpdated Apr 7, 2026
luzhiyu-econ/replication-package
tools
VerifiedTrustedCommunity
构建完整的学术论文复制包（replication package）。
SKILL.mdUpdated Apr 7, 2026
luzhiyu-econ/regression-diagnostics
tools
VerifiedTrustedCommunity
对回归分析结果进行全面诊断。支持 DID、IV、RDD 三种方法。
SKILL.mdUpdated Apr 7, 2026
luzhiyu-econ/paper-structure
research
VerifiedTrustedCommunity
生成学术论文的标准结构框架和 LaTeX 模板。
SKILL.mdUpdated Apr 7, 2026