Agent skill

Fin Novelty Check

by csmar432 in csmar432/finai-research

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。

MITAuto-check passedResearch & Science

Install Fin Novelty Check

skills CLI
$ npx skills add csmar432/finai-research --skill fin-novelty-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install csmar432/finai-research fin-novelty-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/csmar432/finai-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/fin-novelty-check .claude/skills/fin-novelty-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fin-novelty-check
GitHub stars
109
Token cost
~1.4k tokens
SKILL.md length
234 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

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。

  • Works in 7 steps: 想法解析 → 多源并行检索 → 四维评估 → …
  • Tasks that involve Academic paper search
  • SKILL.md covers 核心功能, 工作流程, MCP 工具快速参考 and 与其他技能的关系, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fin Novelty Check is an agent skill from csmar432/finai-research. 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。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Academic paper search and Econometrics and empirical research. It works with arXiv and Model Context Protocol. The repository describes itself as: Evidence-first AI workflow for economic and financial research: literature → identification → data → econometrics → verifiable LaTeX. 43 data sources, 58 method modules, 18 AI… The licence is MIT.

When your agent uses it

  • Tasks that involve Academic paper search
  • Tasks that involve Econometrics and empirical research

Example prompts

  • “/fin-novelty-check”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. 想法解析
  2. 多源并行检索
  3. 四维评估
  4. 综合评分
  5. 识别竞争论文
  6. 定位策略(MEDIUM/LOW 专用)
  7. 生成报告

What it can do on your machine

Read from SKILL.md and the folder at commit 47eebb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fin Novelty Check loads about 1.4k tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from csmar432/finai-research at commit 47eebb7, republished under its MIT licence (© csmar432). 234 words, ~1,447 tokens.

Download SKILL.mdSave it as .claude/skills/fin-novelty-check/SKILL.md (or your agent's skills folder).
name
fin-novelty-check
description
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。
argument-hint
研究想法或IDEA_REPORT.md路径

研究想法新颖性验证

在顶刊数据库中系统性检索,评估研究想法的原创性,输出定位策略。

核心功能

  • 四维评估:相似度 / 方法差异 / 样本独特性 / 机制新颖性
  • 顶刊检索:JF / JFE / RFS / JME / arXiv / NBER
  • 中文顶刊:经济研究 / 金融研究 / 管理世界
  • 综合评分:HIGH (≥8) / MEDIUM (6-8) / LOW (<6)
  • 定位策略:差异化路径 + 潜在风险规避

工作流程

Step 1: 想法解析

将研究想法拆解为 3-5 个可检验的核心主张(Claims):

原始想法: "数字金融对中小企业创新的影响"

核心主张:
1. 数字金融能显著提升中小企业创新投入
2. 融资约束是主要作用机制
3. 东部地区效果强于西部地区
4. 对民营企业效果强于国有企业

每个 Claim 需包含:

  • 变量关系:[X] → [Y]
  • 假设方向:[正向/负向/倒U型]
  • 适用情境:[样本范围]
Step 2: 多源并行检索

对每个 Claim 分别检索,使用以下模板:

JF/JFE/RFS(英文顶刊)
python
server: user-brave-search
tool: brave_web_search
params: {
    "query": "site:jf.com digital finance SME innovation empirical"
}
# 替换: site:jfe.oxfordjournals.org, site:rfs.org
arXiv(近3年预印本)
python
server: user-arxiv
tool: semantic_search
params: {
    "query": "digital finance AND (SME OR \"small business\") AND (innovation OR R&D) AND (2023 OR 2024 OR 2025)"
}
NBER(工作论文)
python
server: user-nber-wp
tool: get_nber_papers
params: {
    "category": "corporate finance OR financial economics",
    "year_from": 2023
}
中文顶刊
python
server: user-brave-search
tool: brave_web_search
params: {
    "query": "site:er.cngp.org.cn OR site:jr.cass.org.cn 数字金融 中小企业 创新 实证"
}
# 经济研究: site:er.cngp.org.cn
# 金融研究: site:jr.cass.org.cn
# 管理世界: site:管理与世界.ajcass.com
补充检索(更宽泛)
python
server: user-openalex
tool: get_openalex_works
params: {
    "query": "digital finance innovation SMEs empirical",
    "per_page": 30
}
Step 3: 四维评估

对每个 Claim 逐一评估:

维度评估问题评分 (1-10)
相似度 (S)已有多少研究做了一样的 X→Y?1=完全相同, 10=从未做过
方法差异 (M)你的方法与已有研究有何不同?1=方法相同, 10=全新方法
样本独特性 (U)数据/样本是否独特?1=常用数据, 10=独有数据
机制新颖性 (N)机制解释是否新颖?1=常见机制, 10=全新机制

评估标准详解:

相似度 (S):

  • 1-3:完全相同的 X→Y 已有多个顶刊研究
  • 4-6:相近主题(如数字金融→创新),但 X/Y 定义不同
  • 7-10:X→Y 组合从未被研究过

方法差异 (M):

  • 1-3:直接复用已有研究方法(如标准DID)
  • 4-6:有改进(如异质性DID、动态DID)
  • 7-10:引入全新方法或组合(如合成DID + 机器学习)

样本独特性 (U):

  • 1-3:常用数据库(AShare、Compustat)
  • 4-6:独特样本(特定地区/行业/时间段)
  • 7-10:独有数据(自建数据库、实地调查)

机制新颖性 (N):

  • 1-3:融资约束/资源获取等常见机制
  • 4-6:细分机制(如融资约束的某个维度)
  • 7-10:全新机制(如心理账户、数字化转型路径)
Step 4: 综合评分

计算每个 Claim 的加权得分:

Claim_Score = 0.3*S + 0.25*M + 0.25*U + 0.2*N

整体评分:

  • 取所有 Claim 的平均分
  • 考虑最薄弱 Claim 的下限约束

评级:

  • HIGH (≥8):可以继续,建议在 Introduction 中明确差异化
  • MEDIUM (6-8):需要调整,建议按 Step 6 调整策略
  • LOW (<6):建议更换想法或重大调整
Step 5: 识别竞争论文

找出与本研究最相似的 3 篇论文:

选择标准:
1. X→Y 组合相同或高度相似
2. 发表在同级及以上期刊
3. 时间在近5年内

对每篇论文说明:
- 为什么相似(Claim 重叠度)
- 本研究的差异化点
- 如何在 Introduction 中委婉处理
Step 6: 定位策略(MEDIUM/LOW 专用)

如果评分为 MEDIUM 或 LOW,提供调整建议:

问题类型调整策略
相似度过高聚焦细分样本(特定行业/地区/规模)
方法无差异引入新方法或数据来源
样本无独特性使用独有数据或组合多个数据库
机制常见挖掘新机制或异质性分析

定位策略模板:

本研究与 [竞争论文] 的区别:
1. [维度1]: [本研究做法] vs [竞争论文做法]
2. [维度2]: ...
3. [维度3]: ...

Contribution 重申:
- 本研究首次在 [样本/情境] 下检验 [X→Y]
- 采用 [新方法/改进方法] 解决了 [问题]
- 发现 [新机制/异质性模式]
Step 7: 生成报告
output/fin-novelty/NOVELTY_REPORT.md
markdown
# 新颖性报告: [研究想法标题]

> 评估日期: [日期]
> 评估者: fin-novelty-check

## 整体评级: HIGH / MEDIUM / LOW
## 综合评分: X/10

---

## 研究想法摘要

**核心主张**:
1. [主张1]
2. [主张2]
3. [主张3]

**预期贡献**:
- 理论贡献: [1-2句话]
- 实证贡献: [1-2句话]
- 政策贡献: [1-2句话]

---

## 主张分析

| 主张 | 相似度(S) | 方法(M) | 样本(U) | 机制(N) | 单项得分 | 权重分 |
|------|-----------|---------|---------|---------|----------|--------|
| 1. X→Y | 7 | 8 | 6 | 5 | 6.55 | 0.30 |
| 2. M中介 | 6 | 7 | 8 | 7 | 6.95 | 0.25 |
| 3. 异质性 | 8 | 6 | 7 | 8 | 7.30 | 0.25 |
| 4. [样本] | 9 | 8 | 7 | 8 | 8.15 | 0.20 |

**加权综合得分**: 7.19/10

---

## 顶刊检索结果

### JF/JFE/RFS
- [竞争论文1] — [期刊] [年份] — [相似点] / [差异点]
- [竞争论文2] — ...

### arXiv / NBER
- [预印本1] — [年份] — [相似点] / [差异点]

### 中文顶刊
- [文献1] — [期刊] [年份] — [相似点] / [差异点]

---

## Top 3 竞争论文

### 1. [Citation]
**期刊**: [期刊名] | **年份**: [年份]
**相似点**: [为什么与本研究重叠]
**差异点**: [本研究的独特之处]
**在 Introduction 中的处理**: [如何委婉地承认相关研究同时指出差异]

### 2. [Citation]
...

### 3. [Citation]
...

---

## 审稿人风险评估

| 风险 | 审稿人可能质疑 | 缓解策略 |
|------|---------------|----------|
| R1 | "这个选题太老了" | 强调样本/方法/情境的独特性 |
| R2 | "方法没有新意" | 展示方法改进或新方法应用 |
| R3 | "数据不够独特" | 说明数据来源的不可替代性 |

---

## 定位策略

[仅当 MEDIUM/LOW 时填写]

### 当前问题
- 相似度较高维度: [维度]
- 需要改进方向: [方向]

### 建议调整
1. **样本聚焦**: [具体建议]
2. **方法改进**: [具体建议]
3. **机制挖掘**: [具体建议]

### 差异化定位

本研究的核心差异化:


---

## 建议期刊

根据研究主题和评分建议目标期刊:
- [期刊1] — [理由]
- [期刊2] — [理由]

---

## 下一步

- [ ] 如果 HIGH:可直接进入 `fin-experiment-design`
- [ ] 如果 MEDIUM:按调整建议修改想法后重新评估
- [ ] 如果 LOW:建议重新生成想法或更换研究方向

Checkpoint:向用户展示报告,询问是否继续:

markdown
## 新颖性评估完成

**评级**: HIGH (7.8/10)
**核心风险**: 相似度中等,需加强方法差异

**是否继续**?
 [1] 继续 — 进入实验设计 (`fin-experiment-design`)
 [2] 调整 — 按建议调整想法后重新评估
 [3] 更换 — 重新生成研究想法

MCP 工具快速参考

数据源工具查询模板
JFbrave_web_searchsite:jf.com [keywords]
JFEbrave_web_searchsite:jfe.oxfordjournals.org [keywords]
arXivsemantic_search[topic] AND [method] AND (2023 OR 2024 OR 2025)
NBERget_nber_paperscategory, year_from=2023
OpenAlexget_openalex_worksquery, per_page=30
论文全文get_context7_by_queryquery, max_results

与其他技能的关系

  • 上游:
    • fin-generate-idea → 输出候选想法供验证
    • fin-lit-review → 文献综述为新颖性判断提供依据
  • 下游:
    • fin-experiment-design → 新颖性验证通过后进入设计
    • fin-paper-writing → 在 Introduction 中引用竞争论文

注意事项

  1. 评分是主观的:基于检索结果的定性评估,需结合实际文献
  2. HIGH 不代表无风险:高评分仍需在 Introduction 中妥善处理竞争文献
  3. 中文顶刊同样重要:经济研究/金融研究/管理世界的相关研究必须检索
  4. 预印本也是竞争:arXiv/NBER 工作论文代表最新进展
  5. 评分阈值灵活:可根据目标期刊调整(如 RFS 可接受 MEDIUM)

© csmar432, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/fin-novelty-check of csmar432/finai-research.

Open the folder on GitHubat commit 47eebb7

Compare with similar skills

Fin Novelty Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fin Novelty Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fin Novelty Check this skillcsmar432/finai-research109—~1.4kAutomated safety check: PassMIT
Paper Searchopenags/paper-search-mcp2.8k—~1.2kAutomated safety check: NotesMIT
Arxiv MCP Serverblazickjp/arxiv-mcp-server3.2k—~353Automated safety check: PassApache-2.0
Nature Academic Searchwp-a/nature-academic-search304—~1.4kAutomated safety check: PassMIT
Paper Searchopenags/paper-search-mcp2.8k—~794Automated safety check: NotesMIT
Rival Search MCPdamionrashford/RivalSearchMCP132—~796Automated safety check: PassMIT

Similar skills

  • Paper Search

    openags/paper-search-mcp

    Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc).

    2.8k GitHub stars~1.2k tokensUpdated 9 days ago
    Research & ScienceAuto-check: notes
  • Arxiv MCP Server

    blazickjp/arxiv-mcp-server

    A skill your agent uses when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or…

    3.2k GitHub stars~353 tokensUpdated 3 days ago
    Research & ScienceAuto-check passed
  • Nature Academic Search

    wp-a/nature-academic-search

    A skill your agent uses when users ask to 找文献、做文献检索、查论文、查临床试验、核验引用、去重文献、设计 PubMed/MeSH 检索式、追踪上下游引文、解析 DOI/PMID/PMCID/arXiv/OpenAlex/Semantic Scholar/NCT ID, 或导出 RIS、BibTeX、NBIB、ENW;also use for…

    304 GitHub stars~1.4k tokensUpdated 9 days ago
    Research & ScienceAuto-check passed
  • Paper Search

    openags/paper-search-mcp

    Search, download, and read academic papers through the paper-search MCP tools (mcppaper-search), covering arXiv, PubMed, bioRxiv, Semantic Scholar, Crossref, OpenAlex and 15+ other sources.

    2.8k GitHub stars~794 tokensUpdated 9 days ago
    Research & ScienceAuto-check: notes
  • Rival Search MCP

    damionrashford/RivalSearchMCP

    Deterministic deep research via RivalSearchMCP. An agent skill from damionrashford/RivalSearchMCP.

    132 GitHub stars~796 tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Academic Search and Citation Router

    Yuan1z0825/nature-skills

    Finds papers across literature sources, verifies and converts citations, builds MeSH strategies and audits independent citations of a paper.

    47k GitHub stars~884 tokensUpdated today
    Research & ScienceAuto-check passed

More from csmar432/finai-research

All 15 skills in this repo
  • Fin Arch Diagram

    csmar432/finai-research

    生成研究/项目架构图、流程图、层次图(swimlane / processflow / hierarchytree)。适合 PPT 汇报、技术文档、综述插图。输出风格接近 draw.io,可选 graphviz(高质量)/ matplotlib(零依赖)双后端。

    109 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Brief Generator

    csmar432/finai-research

    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FINBRIEF.md,减少用户填写负担. An agent skill from csmar432/finai-research.

    109 GitHub stars~1.7k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Data Acquisition

    csmar432/finai-research

    根据REFINEDDESIGN.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)。

    109 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Experiment Design

    csmar432/finai-research

    经济金融实证方法设计。根据研究想法和REFINEDDESIGN.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。

    109 GitHub stars~4.2k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Generate Idea

    csmar432/finai-research

    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。

    109 GitHub stars~2.5k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Idea Discovery

    csmar432/finai-research

    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。

    109 GitHub stars~2.7k tokensUpdated 5 days ago
    Auto-check passed

Questions about Fin Novelty Check

What does Fin Novelty Check do?

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。. Fin Novelty Check is an agent skill from csmar432/finai-research.

When should I use Fin Novelty Check?

Fin Novelty Check fits situations like: tasks that involve Academic paper search; tasks that involve Econometrics and empirical research.

How do I install Fin Novelty Check in Claude Code?

Run `npx skills add csmar432/finai-research --skill fin-novelty-check -a claude-code`. Or copy the skill folder (.agents/skills/fin-novelty-check in csmar432/finai-research) into .claude/skills/fin-novelty-check in your project. Claude Code loads it when a task matches its description.

How do I install Fin Novelty Check in Codex?

Run `npx skills add csmar432/finai-research --skill fin-novelty-check -a codex`. Or copy the skill folder (.agents/skills/fin-novelty-check in csmar432/finai-research) into .agents/skills/fin-novelty-check in your project. Codex loads it when a task matches its description.

Can I use Fin Novelty Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add csmar432/finai-research --skill fin-novelty-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fin-novelty-check, .gemini/skills/fin-novelty-check, .github/skills/fin-novelty-check and .opencode/skills/fin-novelty-check in your project.

What does Fin Novelty Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Fin Novelty Check is instructions for the agent only. Our summary lists: Python 3.

Does Fin Novelty Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fin Novelty Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fin Novelty Check use?

Fin Novelty Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fin Novelty Check use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fin Novelty Check?

Skills that share tags, products or a category with Fin Novelty Check: Paper Search (openags/paper-search-mcp, 2.8k stars), Arxiv MCP Server (blazickjp/arxiv-mcp-server, 3.2k stars), Nature Academic Search (wp-a/nature-academic-search, 304 stars) and Paper Search (openags/paper-search-mcp, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fin Novelty Check?

csmar432 (a GitHub user) maintains it in csmar432/finai-research, which has 109 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 6, 2026.

Source: csmar432/finai-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.