fin-data-acquisition SKILL.md skillA

fin-data-acquisition from csmar432/finai-research is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add csmar432/finai-research/fin-data-acquisition@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
csmar432/finai-research
Path
.agents/skills/fin-data-acquisition/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Jul 12, 2026
Size
9,902 bytes
Repository stars
108
License
MIT

根据REFINED_DESIGN.md中的变量定义,自动获取所需数据并生成可执行的回归分析脚本(Python/Stata)。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# fin-data-acquisition

根据REFINED_DESIGN.md中的变量定义,自动获取所需数据并生成可执行的回归分析脚本(Python/Stata)。

## 触发条件

- 关键词: `获取数据` `数据获取` `data acquisition` `下载数据` `数据准备` `实证数据`
- Skill语法: `Skill: fin-data-acquisition`
- 前置条件: 已完成 `REFINED_DESIGN.md` (研究设计文档)

## 核心原则

### 禁止行为 (未经用户明确授权不得执行)

```
❌ 静默回退到模拟数据
❌ 自动生成虚假回归结果
❌ 在用户未同意情况下继续流水线使用模拟数据
❌ 跳过数据源预检查直接获取数据
```

### 数据源预检查 (强制执行)

在任何数据获取前,必须先运行数据源检查:

```python
from scripts.data_source_checker import DataSourceChecker, DataRequirement

# 第一步:定义数据需求
requirements = [
    DataRequirement(
        name="financial_data",
        user_facing_name="A股财务数据",
        description="ROA、资产负债率、企业规模、研发投入",
        sources=["tushare", "wind", "csmar", "akshare"],
        required=True,
    ),
    DataRequirement(
        name="esg_data",
        user_facing_name="ESG评级",
        sources=["msci", "商道融绿", "华证"],
        required=False,
    ),
    DataRequirement(
        name="macro_data",
        user_facing_name="宏观数据",
        sources=["user-financial", "user-wb-data", "user-imf-data"],
        required=True,
    ),
]

# 第二步:运行数据源检查
checker = DataSourceChecker()
results = checker.check(requirements)

# 第三步:展示可用性报告
checker.print_report(results)
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add csmar432/finai-research/fin-data-acquisition@sha256:03bd0a8ffd183874

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_eybgjwr4asx5m2c5.svg)](https://markdownregistry.com/a/art_eybgjwr4asx5m2c5)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 12, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-07-12 ce45dd4 9,902 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9902 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

csmar432/finai-research · 108 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_eybgjwr4asx5m2c5
GET https://markdownregistry.com/api/v1/resolve?ref=csmar432/finai-research/fin-data-acquisition
GET https://markdownregistry.com/api/v1/blob/03bd0a8ffd1838749d61d48e0ad0cde0b2e9dc7a40d1f469c8656dcbba89f587

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from csmar432/finai-research

fin-brief-generator SKILL.md skill
csmar432/finai-research · .agents/skills/fin-brief-generator/SKILL.md · 根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FIN_BRIEF.md,减少用户填写负担。
v1.0.0 · audit A · 108 stars
fin-experiment-design SKILL.md skill
csmar432/finai-research · .agents/skills/fin-experiment-design/SKILL.md · 经济金融实证方法设计。根据研究想法和REFINED_DESIGN.md,生成完整的实证研究设计方案,覆盖识别策略选择、样本构建、变量定义、稳健性检验清单和内生性处理方案。
git:20260916.3368f05 · audit A · 108 stars
fin-full-pipeline SKILL.md skill
csmar432/finai-research · .agents/skills/fin-full-pipeline/SKILL.md · 经济金融研究端到端完整流程。从研究想法到可投稿论文,覆盖文献综述、想法生成、新颖性验证、实证方法设计、论文大纲、正文写作、图表生成、LaTeX编译和投稿前检查。
git:20260808.91b52c9 · audit A · 108 stars
fin-generate-idea SKILL.md skill
csmar432/finai-research · .agents/skills/fin-generate-idea/SKILL.md · 针对经济金融研究方向的创意生成与评估。生成8-12个可发表的研究idea,过滤后在数据可行的情况下进行小规模实证验证,输出排序后的研究想法报告。
git:20260712.ce45dd4 · audit A · 108 stars
fin-idea-discovery SKILL.md skill
csmar432/finai-research · .agents/skills/fin-idea-discovery/SKILL.md · 经济金融研究的完整想法发现流程。从研究方向出发,经过文献综述、想法生成、新颖性验证、实证方法设计和数据获取,输出经过数据实证验证的可执行研究方案。
git:20260712.ce45dd4 · audit A · 108 stars
fin-lit-review SKILL.md skill
csmar432/finai-research · .agents/skills/fin-lit-review/SKILL.md · 经济金融领域的系统性文献综述。整合 Semantic Scholar + ArXiv + OpenAlex + NBER 构建引文网络,识别研究缺口,生成结构化文献地图。
git:20260712.ce45dd4 · audit A · 108 stars
fin-novelty-check SKILL.md skill
csmar432/finai-research · .agents/skills/fin-novelty-check/SKILL.md · 验证经济金融研究想法的新颖性。在JF、JFE、RFS、JME等顶刊及arXiv中搜索近三年文献,输出结构化新颖性报告和定位策略。
git:20260712.ce45dd4 · audit A · 108 stars
fin-paper-convert SKILL.md skill
csmar432/finai-research · .agents/skills/fin-paper-convert/SKILL.md · Compile LaTeX to PDF and convert to target journal format
v1 · audit B · 108 stars
fin-paper-draft SKILL.md skill
csmar432/finai-research · .agents/skills/fin-paper-draft/SKILL.md · 经济金融论文正文写作。根据PAPER_OUTLINE.md大纲和REFINED_DESIGN.md研究设计,生成完整的论文正文草稿(英文/中文),覆盖Introduction到Conclusion所有章节。
git:20260830.bd8bc9d · audit A · 108 stars
fin-paper-figure SKILL.md skill
csmar432/finai-research · .agents/skills/fin-paper-figure/SKILL.md · Generate academic-quality figures (>=300 DPI) for economics and finance papers
v1 · audit B · 108 stars
fin-paper-plan SKILL.md skill
csmar432/finai-research · .agents/skills/fin-paper-plan/SKILL.md · Generate structured paper outline adapted to target journal
v1 · audit B · 108 stars
fin-paper-writing SKILL.md skill
csmar432/finai-research · .agents/skills/fin-paper-writing/SKILL.md · 经济金融论文写作编排器。根据PAPER_OUTLINE.md和REFINED_DESIGN.md,编排调用fin-paper-draft(正文写作)、fin-paper-figure(图表生成)、fin-review-loop(review…
git:20260727.3f3a820 · audit A · 108 stars

Every file in csmar432/finai-research

Other files named fin-data-acquisition

fin-data-acquisition SKILL.md skill
csmar432/finai-research · .cursor/skills/fin-data-acquisition/SKILL.md · 根据REFINED_DESIGN.md中的变量定义,自动获取所需数据并生成可执行的回归分析脚本(Python/Stata)。
v1.0.0 · audit A · 108 stars

Browse by kind, by grade A, or by owner.