/variable-map

SkillDocs & knowledge

Summarizes how an economics/management empirical variable is measured in the literature, including its calculation methods, data sources, role in models, and availability in the project.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the /variable-map skill

What this skill tells your AI

The instructions your AI receives, as published by lambenthan/empiricalwiki in .claude/skills/variable-map/SKILL.md and read by ahel’s review.

把分散在文献卡片里的变量信息整理成可执行的变量字典。适合回答“耐心资本怎么测算”“管理者短视有哪些口径”“ESG 用哪个数据源”。

Workflow

Step 1: Locate Relevant Pages

读取:

  • wiki/variables/*.md
  • wiki/papers/*.md
  • wiki/datasets/*.md
  • wiki/models/*.md
  • 当前项目的 README.mdraw/notes/research-intent.md(如果存在)

按变量名称、别名、构念、角色、标签和 source_papers 匹配。

Step 2: Build the Comparison Table

输出表格至少包含:

字段含义
变量/构念如耐心资本、ESG、管理者短视
模型角色被解释变量、核心解释变量、中介、调节、控制等
测算口径公式或文本描述
数据来源数据库、表名、项目路径
样本频率firm-year、quarter 等
来源文献wiki paper slug
优点为什么可用
风险内生性、口径争议、缺失值、复现难点
项目可用性已有 / 缺失 / 需要手工整理

Step 3: Archive

生成:

wiki/outputs/variable-map-{slug}-{YYYY-MM-DD}.md

并追加日志:

python3 tools/research_wiki.py log wiki "variable-map | <variable> | output: outputs/<file>"

Constraints

  • 只比较 wiki 或本地项目中已有证据,不凭常识补数据库表名。
  • 不把不同口径强行合并;口径不同就分行。
  • 如果信息来自论文但本地数据没有,明确写“项目暂缺”。

Signals

GitHub stars
83
Forks
17
Last commit
Jun 2026
Advanced
Catalog kind
skill
Gateway key
variable-map
Source
github.com/lambenthan/empiricalwiki