Agent skill · Audited from source

Er Mechanism

skill · brycewang-stanford/Awesome-Journal-SkillsMIT licenceAudited 24 Oct 2026 · source 9b73efe58ece

★ 1,301pushed 27 days ago
✓SAFEGrade B · 89/100 · 24 Oct 2026 · 9b73efe
1,301repo stars · whole brycewang-stanford/Awesome-Journal-Skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 9b73efe58ece and found no filesystem, network or shell access and no hard-coded secrets. What it does: Use when designing or writing the mechanism analysis for an Economic-Research empirical manuscript. Enforces the post-江艇(2022) paradigm — estimate D→M with the main identification strategy and argue M→Y from theory,…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Er Mechanism (brycewang-stanford/Awesome-Journal-Skills)”. Retrieved 24 Oct 2026. https://modelsatlas.com/skills/brycewang-stanford/er-mechanism

Trust audit

Audit 0.4.1 · source read 24 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 9b73efe58ece · 24 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

What it tells the agent

Full source on GitHub ↗

Its description: Use when designing or writing the mechanism analysis for an Economic-Research empirical manuscript. Enforces the post-江艇(2022) paradigm — estimate D→M with the main identification strategy and argue M→Y from theory,…

---
name: er-mechanism
description: Use when designing or writing the mechanism analysis for an Economic-Research empirical manuscript. Enforces the post-江艇(2022) paradigm — estimate D→M with the main identification strategy and argue M→Y from theory, instead of running mediation step-wise / Sobel tests.
---

# 机制分析(er-mechanism)

机制分析是《经济研究》实证文章的近乎必备环节。但**它的方法论近年发生了根本转向**——本 skill 按转向后的口径写。

## 触发时机

- 主回归结果已稳健,但缺机制分析
- 机制只有"我们认为可能是因为......"的口头说明
- 审稿人问"为什么会有这个效应?"
- 你正打算(或已经)跑中介效应三步法 / Sobel 检验 —— **请先读下一节**

## ⚠ 范式转向:不要再用中介效应逐步法

**江艇(2022)《因果推断经验研究中的中介效应与调节效应》,《中国工业经济》第 5 期,第 100–120 页**——已成为四大刊(《经济研究》《管理世界》《中国工业经济》《经济学(季刊)》)机制分析的准规范。核心结论:

- **建议停止使用中介效应逐步法(Baron-Kenny 三步法)与 Sobel 检验。** 在因果框架下,处理 D 可借识别策略视为外生,但**中介变量 M 几乎从不是随机的**。
- 在 Y 对 (D, M) 的回归里,M 的系数(即"M→Y 那一步")混入了 M 与 Y 之间的遗漏变量偏误和反向因果,**不具因果含义**;据此分解出的"中介效应""间接效应占比"也不可信。
- 三步法还隐含"无未观测的处理后混杂"这一**极强且不可检验**的假设。

> 一句话:别用一个内生回归去"证明"机制。

## 正确做法:D→M + 理论论证 M→Y

机制检验 = 两件事:

1. **实证上,只估计 D→M**:把机制变量 M 当作被解释变量,**沿用与主回归 D→Y 完全相同的识别策略**(同样的 DID / IV / RDD、同样的固定效应与聚类)。这一环是被可信识别的因果关系——"处理确实改变了机制变量"。
2. **理论上,论证 M→Y**:用经济学理论、制度背景、已有文献说明"M 为什么会影响 Y"。这一环**不跑回归**,靠论证。

配套代码:`resources/code/stata/07_mechanism.do`。

### 机制写作三段式

```
本文进一步从[机制名]角度提供证据。
第一,理论上,[机制变量 M] 应通过[路径]影响[结果 Y]——[引理论/制度/文献,著者-出版年制,如(江艇,2022)]。
第二,实证上,本文以 [M] 为被解释变量,沿用基准识别策略估计 D→M,结果见表 X:
       处理使 [M] [上升/下降] [量级],与上述理论预期一致。
第三,结合 [理论/文献],[M] 的变化进而通过[路径]作用于 [Y],构成本文主效应的机制。
```

注意第三步只做**逻辑闭合**,不报告"间接效应=0.0X、占比 Y%"这类来自中介分解的数字。

## 机制设计三原则

1. **理论指引**:机制变量必须能挂上某支理论,不是凭空想。
2. **时间一致**:M 的测量时点在处理 D 之后、结果 Y 之前;构造 M **不得使用未来信息**。
3. **可证伪**:能写出"若机制成立 → 应观察到 D 改变 M;若不成立 → 不应观察到"。

## 用异质性侧证机制(推荐替代"中介"的思路)

比中介分解更可信的机制证据,是**理论驱动的异质性**:若机制是 M,则在"M 渠道更畅通/更受约束"的子样本中,主效应应更强/更弱。

> 例:若效应来自"融资约束缓解",则在**融资约束更紧**的企业中效应应更大。在该子样本验证,比跑一个 M 的内生中介回归更有说服力。

这把机制(为什么有效应)与异质性(什么条件下更强)打通——详见 `er-heterogeneity`。

## 范文对标(确属《经济研究》)

- 张勋、万广华、张佳佳、何宗樾《数字经济、普惠金融与包容性增长》,《经济研究》2019 年第 8 期——机制分析范本:数字金融→收入,逐层拆解"创业 + 金融可得性"渠道并配合群体异质性。

## 必查清单

- [ ] 至少 1 个机制(理想 2–3 个互补机制)
- [ ] 机制变量来源于理论 / 文献,不是凭空想
- [ ] 机制检验**只跑 D→M**,与主回归同一识别策略
- [ ] M→Y 由理论 / 制度 / 文献论证,而**非**内生回归
- [ ] 机制变量构造的时间逻辑正确(不使用未来信息)
- [ ] 机制部分至少 1 张独立回归表
- [ ] (如适用)用理论驱动的异质性侧证机制
- [ ] 机制结果与主回归方向一致(不一致则解释)

## 反模式

- 用"我们认为可能是因为......"一句话代替机制分析
- **跑中介三步法 / Sobel / Bootstrap 间接效应占比**——已被四大刊普遍弃用
- 把 Y 对 M 的内生回归当作"M 影响 Y 的证据"
- 机制变量构造时使用了未来信息
- 机制结果方向与主效应相反却不解释
- 机制变量与处理变量本质是同一个东西的不同度量(同义反复,不算机制)

## 输出格式

```
【机制数】X 个
【机制变量】[M1, M2, ...]
【D→M 识别策略】与主回归一致 / 不一致(需修)
【M→Y 论证方式】理论 / 制度 / 文献(不跑内生回归)
【中介三步法 / Sobel 命中】无 / 有(必须移除)
【时间一致性】通过 / 待修
【异质性侧证】有 / 无
【下一步】er-heterogeneity
```

Excerpt, first 2,568 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 9b73efe

Download folder ↗
git clone https://github.com/brycewang-stanford/Awesome-Journal-Skills
git -C Awesome-Journal-Skills checkout 9b73efe58ece

The author documents no install command, so this uses the repository directly. Our verdict covers commit 9b73efe58ece only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 9b73efe58ece

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/brycewang-stanford/er-mechanism/badge.svg)](https://modelsatlas.com/skills/brycewang-stanford/er-mechanism/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Er Topic Selection✓SAFE

brycewang-stanford/Awesome-Journal-Skills

Use when an Economic-Research manuscript is at the topic-selection stage and the theoretical grounding, marginal-contribution sentence, or venue match are unsettled. Produces the contribution-sentence template and the…

★ 1.3kGrade B
Er Workflow✓SAFE

brycewang-stanford/Awesome-Journal-Skills

Use when deciding which er-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for 《经济研究》 (Economic Research Journal). Routes — does not replace — the specialized skills.

★ 1.3kGrade B
Er Tables Figures✓SAFE

brycewang-stanford/Awesome-Journal-Skills

Use when finalizing regression tables and figures for an Economic-Research manuscript. Enforces three-line table style, footnote conventions, column-count discipline, and figure aesthetics.

★ 1.3kGrade B
Er Submission✓SAFE

brycewang-stanford/Awesome-Journal-Skills

Use when running the final pre-submission preflight for 《经济研究》 — anonymization, author rules, abstract & keywords, reference style, anti-plagiarism, supplementary files, and the submission portal. Distinguishes…

★ 1.3kGrade B
Er Style✓SAFE

brycewang-stanford/Awesome-Journal-Skills

Use when polishing the language and rhetoric of an 《经济研究》 manuscript — eliminating empty-significance phrases, fixing vague policy talk, replacing method-flexing with mechanism, and aligning tense / person / hedging…

★ 1.3kGrade B
Er Rebuttal✓SAFE

brycewang-stanford/Awesome-Journal-Skills

Use when responding to reviewer and editorial-board reports for an 《经济研究》 (Economic Research Journal) R&R — sequencing manuscript revision before letter writing, drafting point-by-point replies in the accept /…

★ 1.3kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/brycewang-stanford/er-mechanism/badge.svg)](https://modelsatlas.com/skills/brycewang-stanford/er-mechanism/)

Questions about Er Mechanism

What does the Er Mechanism skill do?
Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. | 覆盖主流期刊的 Claude Code/Codex 期刊技能包,从选题、识别策略到表格规范与审稿回复全流程,助你快速发论文。
Is Er Mechanism safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Er Mechanism access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (9b73efe58ece), read on 2026-10-24. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.