Economics Thesis logo

Economics Thesis

Community
ZehChou
economics-thesis

经济学实证论文自动化工作流——从选题到排版成文的全流程交互式指导

Overview

PublisherZehChou
Repositorycn-economics-thesis-workflow-skill
Skill nameeconomics-thesis
Stars
85
Forks
4
Bundled files
38
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 38 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ZehChou on GitHub. Read the source before you install it.

Installation

Install the Economics Thesis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ZehChou/cn-economics-thesis-workflow-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ZehChou/cn-economics-thesis-workflow-skill.git \
  .claude/skills/economics-thesis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Economics Thesis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Economics Thesis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Economics Thesis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

经济学实证论文自动化工作流 (Economics Thesis Workflow)

概述

本 Skill 定义了一套分步骤交互式工作流,让 AI Agent 引导用户从零完成一篇完整的中文经济学实证学位论文。

核心契约(设计目标,所有改动朝此对齐)

用户只提供两样东西:数据 + 对选择题的回答。 Agent 负责其余全部:检索文献、清洗数据、跑计量、解读结果、撰写正文、排版成文。 交付物是一份对齐范文结构与版式的 .docx 学位论文。

一切设计取舍以此为准:

  • 不让用户写代码、不应求用户装环境、不做数据质量审查(用户给什么就用什么,除非用户主动要求);
  • 能自动的绝不追问,只在真正需要判断的节点设 CHECKPOINT(选方法、定变量、认模型、选稳健性、定异质性维度、认大纲);
  • 代码不是给用户看的,是给 Agent 跑的——因此集中放附录,Phase 只讲"做什么、验收什么"。

工作流总览

Phase 0 ──→ Phase 1 ──→ Phase 2 ──→ Phase 3 ──→ Phase 4
环境准备      选题与         文献综述       数据与         基准回归
             文献定位        与理论框架     变量
                                               │
                         Phase 5 ◄─────────────┘
                         内生性处理
                           │
                    ┌──────┼──────┐
                    ▼      ▼      ▼
               Phase 6  Phase 7  Phase 8
               稳健性   机制检验  异质性
               检验               分析
                    │      │      │
                    └──────┼──────┘
                           ▼
                       Phase 9
                   论文撰写与排版成文

用户水平分档

首次使用本 Skill 时,AI 应询问用户水平,后续全程按该档位自适应:

档位定位AI 行为
L1(新手)第一次做实证论文,需要 mini 教学每个阶段解释核心概念(点到为止,用户反问再深入);推荐执行路径偏保守(默认选项);提示每一步的常见问题
L2(有基础)有计量经济学基础,做过基本回归跳过概念解释;直接输出方案和技术细节;用户自主选择分支
L3(进阶)熟悉高级计量方法,追求深度推荐前沿方法(如异质性处理效应、机器学习辅助 IV);讨论模型识别假设的深层问题;提供更多自定义选项

外部参考仓库与工具链

仓库/工具定位使用方式
easy-paperTypst 中文论文模板设计参考:格式参数作为无范文时的排版默认值(附录 A)
docx-skill-4-cn-paperNode.js docx 辅助函数集排版路线 N:Phase 9 直接使用其辅助函数模式(附录 B)
pyfixestPython 高维固定效应回归后端 B 主力:feols 对应 reghdfe,sunab 对应 Sun–Abraham(附录 H)
pyalexOpenAlex 客户端文献元数据 L0:题录、摘要、引用网络(附录 J.2)
translators_CNZotero 中文抓取器中文文献 L1:知网/万方/维普一键入库(附录 J.3)
mcp-for-stataStata MCP 服务器后端 A(可选):仅当用户显式选择 Stata 时才配置(附录 C/I)

通用交互模式:计量分析流程

Phase 4-8 共享以下交互循环,各 Phase 仅需指定方法列表、数据检查清单和解读模板:

┌──────────────────────────────────────────────────────────┐
│ ① 方法推荐 ── AI 基于数据/文献推荐 3-5 种方法            │
│ ② 🔴 CHECKPOINT 用户确认 ── 用户选择 1-3 种方法          │
│ ③ 变量就绪检查 ── 确认所需变量能定位到(不做质量审查)    │
│ ④ 写分析脚本并运行 ── 后端 B: scripts/*.py(附录 H)     │
│                     后端 A: do/*.do(附录 I)            │
│    🛟 失败分支:读错误栈修复重试;同一错误连续 2 次 → 暂停,│
│    交用户确认数据结构/环境(错误处理见附录 D.2)          │
│ ⑤ 结果解读 ── AI 解读输出并给出结论                       │
│ ⑥ 🔴 CHECKPOINT 用户确认 ── 满意 → 下一 Phase;           │
│    不满意 → 回到 ①(先把本轮规格记入 log/spec-search.csv,│
│    禁止无记录地换规格;研究诚信红线见附录 D.5)            │
└──────────────────────────────────────────────────────────┘

状态持久化

每次 Phase 完成后,AI 应将状态写入 project_root/.thesis_state.json:

json
{
  "user_level": "L2",
  "analysis_backend": "python",
  "current_phase": 5,
  "model_framework": { "method": "TWFE", "fe": ["id", "year"], "cluster": "id" },
  "data_path": "cleaned/dataset.dta",
  "citation_db": {}
}

analysis_backend 决定 Phase 4-8 取附录 H(python,默认)还是附录 I(stata)。 字段含义见附录 D.1。

后续启动时读取该文件恢复状态,避免跨会话丢失。


阶段导航

阶段文件内容概要
Phase 0phases/00-environment.md环境准备:契约对齐、执行后端选择、依赖检测、范文提取、状态初始化
Phase 1phases/01-topic.md选题与文献定位:用户输入、文献搜索、选题评估报告
Phase 2phases/02-literature.md文献综述与理论框架:分类精读、综述生成、机制推演
Phase 3phases/03-data.md数据与变量:数据来源、变量构造、描述统计
Phase 4phases/04-baseline.md基准回归:方法推荐、分析脚本(附录 H/I)、结果解读、显著性改善
Phase 5phases/05-endogeneity.md内生性处理:来源诊断、IV/PSM/DID/GMM 等方法、模型框架确立
Phase 6phases/06-robustness.md稳健性检验:替换度量/样本/方法、安慰剂检验
Phase 7phases/07-mechanism.md机制检验:中介效应、调节效应、分组回归
Phase 8phases/08-heterogeneity.md异质性分析:预先指定维度、全交互 + 交互项检验、多重检验校正
Phase 9phases/09-writing.md论文撰写与排版成文:排版路线 P/N、大纲、正文、图表、排版

附录导航

附录文件内容概要
Aappendices/A-easypaper-format.md版式规范(无范文时的默认基准)
Bappendices/B-docx-helper.mddocx 辅助函数接口定义
Cappendices/C-stata-mcp.md后端 A 的 Stata MCP 配置(仅选 Stata 时需要)
Dappendices/D-general-rules.md通用规则、状态字段、错误处理、时间估计、研究诚信红线
Eappendices/E-reviewer-qa.md审稿人/答辩常见问题应对策略
Fappendices/F-analysis-archive.md分析脚本归档规范(Stata do/ + Python scripts/)
Gappendices/G-reference-management.md参考文献管理建议
Happendices/H-analysis-backend-python.md后端 B(默认)代码真源:Phase 4-8 全套 Python
Iappendices/I-analysis-backend-stata.md后端 A(可选)代码真源:Phase 4-8 全套 Stata
Jappendices/J-literature-acquisition.md文献获取:OpenAlex/Crossref/S2 + Zotero 中文抓取 + PDF 提取

代码真源规则(避免两份代码漂移)

Phase 4-8 的 .md 文件里不出现可运行代码。
所有代码只在两个附录里维护:
  后端 B → 附录 H(默认)      后端 A → 附录 I(可选)
Phase 文件只保留:方法列表 / CHECKPOINT / 表格形态 / 解读模板 / 验收清单

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Economics Thesis AI skill do?

经济学实证论文自动化工作流——从选题到排版成文的全流程交互式指导

Why use Economics Thesis on TypingMind?

Because you install it once and use it with any model. Economics Thesis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Economics Thesis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZehChou/cn-economics-thesis-workflow-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Economics Thesis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Economics Thesis?

As many as you like. As long as a model supports skills, you can use Economics Thesis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Economics Thesis AI skill free?

It is published on GitHub by ZehChou. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇