Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

China Corporate Finance Empirical Study (china-cf-study) · brycewang-stanford | DecimalAI

researchby brycewang-stanford

China Corporate Finance Empirical Study (china-cf-study)

brycewang-stanford/China-CF-Study

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

根据研究者提供的**研究计划书（Research Proposal）**执行基于中国制度环境的公司金融类实证研究全流程。**启动后第一件事：根据计划书的主题、识别策略、贡献边际与样本范围，从中国-context 英文顶级期刊池（JF/JFE/RFS/JFQA/MS/JCF/JBF/JAR/JAE/TAR/CAR/JIBS/China Economic Review/PBFJ 等 25+ 期刊）中推荐 5 本最匹配的目标期刊（[J1]–[J5]），等待研究者明确选定一本；该期刊决定 main.tex 的 bibliographystyle、Section 骨架、Introduction 风格与表注规范**。然后用 Python 完成数据清洗、描述性统计、基准回归、内生性检验（IV/2SLS、DML）、平行趋势、异质性、机制、稳健性检验与图表绘制。LaTeX 表格和图像严格遵循 template/ 示例格式，研究逻辑与排版严格遵循 rule/ 下的《通用实证研究逻辑与规范总结》与《回归表写作规范总结》。数据集与政策集从 asset/ 中按计划书中的关键词检索。**当计划书预期的实证结果无法

SkillScore77Maintained

Automatic

Research pack

Last verified 8/7/2026

What it changes

Passed 17 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill77%

Checks it passed that the model alone missed

The response declines to write long prose text for paper sections.
The response specifies recording the failure and chosen remedy in DECISION_LOG.md.
The response requires explicit cross-referencing to the variable definition table in the note.

and 18 more in the full report

12 fixed5 passed either way4 still failing1 broke

Pass-rate lift: +50 pp
Tokens: +479%
Agent turns: 0%
Response time: -20%

Model gemini-3.6-flashMeasured 8/7/2026v117 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-china-cf-study/SKILL.md https://app.decimal.ai/s/brycewang-stanford-china-cf-study/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-china-cf-study, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-china-cf-study/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-china-cf-study

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-china-cf-study/SKILL.md https://app.decimal.ai/s/brycewang-stanford-china-cf-study/SKILL.md

Raw file: /s/brycewang-stanford-china-cf-study/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-china-cf-study.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

During the execution of an empirical corporate finance pipeline, the baseline regression failed to achieve statistical significance on the primary treatment variable, forcing a switch to an alternative variable measure (Plan-B B1). What file must be updated to track this choice and what details must be logged?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies logging the change in DECISION_LOG.md.	Passed	Passed
The response requires recording the expected result, observed test statistic, triggered rule, chosen branch, and re-test result in the log entry.	Missed	Passed

case-15 · gemini-3.6-flash · 8/7/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md870 linessingle file

China Corporate Finance Empirical Study (china-cf-study)

1. 定位与适用范围

本 skill 指导基于中国制度环境的公司金融类实证研究的完整流程。覆盖：

以 A 股上市公司、中国城市/省级面板为主体样本
识别策略：DID（含 staggered/CS-DID/Sun-Abraham）、Panel FE + IV/2SLS、PSM-DID、DML / DML-IV、合成控制、RDD
研究主题：投融资、治理、股权结构、机构投资者、信贷、创新、披露、审计、分析师、ESG 等
代码语言：Python（pandas / numpy / statsmodels / linearmodels / pyfixest / econml / doubleml / scikit-learn / matplotlib）
表格输出：LaTeX（严格遵循 template/ 格式与 rule/ 规范）

本 skill 不替代研究者的研究设计判断，而是把每一环节的标准流程、代码骨架、表格/图像模板提供给研究者，保证产出质量达到中国-context 英文顶级期刊（JF、JFE、RFS、JFQA、RCFS、JCF、JBF；JAR、JAE、TAR、CAR、RAST；MS、SMJ、JIBS；AER、QJE、JPubE、JEEM；以及 China Economic Review、Pacific-Basin Finance Journal、Emerging Markets Review、China Journal of Accounting Research 等 China-friendly 主流刊）的写作与方法论要求。目标期刊在启动后第二步即由 skill 推荐 + 研究者锁定（见 §3.4），后续 main.tex 的 bibliographystyle、Section 骨架、Introduction 风格、表注规范均以此为准。

2. 工作目录结构（项目根即 working directory）

China-CF-study/                 ← working directory
├── asset/                      ← 中国常见数据集与政策集索引（研究者提供检索关键词）
│   ├── macrodatas_list.csv           # 马克数据网数据集清单（宏观/上市公司/城市层）
│   ├── ppmandata_trade_list.csv      # 皮皮慢数据（政策/贸易/金融等）清单
│   ├── 全网首发计量方法+政策数据库.pdf # 原始政策冲击数据库 PDF（975 页，含 800+ 实证研究的方法-政策详尽案例）
│   ├── 计量方法+政策数据库.md       # ★ 上面 PDF 的 50 页 markdown 精简版（按"方法 × 政策 × 数据"三维交叉重组；首选入口）
│   └── MCP.docx                      # MCP 服务器清单（如 CSMAR-MCP），含安装网址
├── rule/                       ← 强制性写作与方法论规范（AI 必须逐项遵循）
│   ├── 通用实证研究逻辑与规范总结.docx
│   └── 回归表写作规范总结.docx
├── template/                   ← LaTeX 表格与图片模板（格式模仿对象）
│   ├── main.tex                      # ★ 正文 .tex 模板——新项目 main.tex 的 Preamble / References / Appendix 块均以此为底
│   ├── sum_stat.tex                  # 描述性统计
│   ├── variables.tex                 # 变量定义
│   ├── baseline.tex                  # 基准回归（渐进式加控制 + 渐进式加 FE）
│   ├── addctr.tex                    # 加入附加控制变量
│   ├── measures.tex                  # 替换因变量度量
│   ├── specification.tex             # 高维交互固定效应
│   ├── iv.tex                        # 2SLS 工具变量
│   ├── psm_ddml.tex                  # PSM + DML（Panel A / Panel B）
│   ├── bunching-did.tex              # Bunching-DID
│   ├── channel1.tex, channel2.tex, channel3.tex   # 机制分析（按渠道分组）
│   ├── heterogeneity1.tex, heterogeneity2.tex, heterogeneity3.tex # 异质性（bdiff）

Track record

Benchmark

17 / 22

test cases passed, vs 6 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / Auto-Empirical-Research-Skills

skills/67-econfin-workflow-toolkit/China-CF-study/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

brycewang-stanford/Foreign-CF-Study根据研究者提供的**研究计划书（Research Proposal）**执行基于**外国（美国/欧盟/英国/日本/跨国）制度环境**的公司金融类实证研究全流程。**启动后第一件事：根据计划书的主题、识别策略、贡献边际与样本范围，从外国 CF 顶刊池（AER/QJE/JPE/JF/JFE/RFS/JFQA/JAR/JAE/MS/JCF/JBF 等 25+ 期刊）中推荐 5 本最匹配的目标期刊（[J1]–[J5]），等待研究者明确选定一本；该期刊决定 main.tex 的 bibliographystyle、Section 骨架、Introduction 风格与表注规范**。然后用 Python 完成数据清洗、描述性统计、基准回归、内生性检验（IV/2SLS、DML）、平行趋势、异质性、机制、稳健性检验与图表绘制。LaTeX 表格和图像严格遵循 template/ 示例格式，研究逻辑与排版严格遵循 rule/ 下的《通用实证研究逻辑与规范总结》与《回归表写作规范总结》。数据集与政策集从 asset/ 中按计划书中的关键词检索（WRDS / NBER/Fed releases / FRED Close match+36 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

China Corporate Finance Empirical Study (china-cf-study)

1. 定位与适用范围

2. 工作目录结构（项目根即 working directory）

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills