Agent skill

Fin Generate Idea

by csmar432 in 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。

MITAuto-check passedResearch & Science

Install Fin Generate Idea

skills CLI
$ npx skills add csmar432/finai-research --skill fin-generate-idea -a claude-code

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

GitHub CLI
$ gh skill install csmar432/finai-research fin-generate-idea --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-generate-idea .claude/skills/fin-generate-idea && 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-generate-idea
GitHub stars
109
Token cost
~2.5k tokens
SKILL.md length
237 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

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。

  • Works in 6 steps: 每个想法必须基于文献:不能凭空生成想法 → 数据可行性是硬过滤:无数据路径的想法不进推荐名单 → 模拟数据需要授权:未授权的模拟想法必须标记 → …
  • Tasks that involve Brainstorming
  • SKILL.md covers 流程概览, 触发条件, 输出文件 and 阶段详解, plus 5 more sections
  • Calls python

What it does

Fin Generate Idea is an agent skill from 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。

Its SKILL.md is about 2.5k 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 Brainstorming and Econometrics and empirical research. It works with 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 Brainstorming
  • Tasks that involve Econometrics and empirical research

Example prompts

  • “/fin-generate-idea”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 每个想法必须基于文献:不能凭空生成想法
  2. 数据可行性是硬过滤:无数据路径的想法不进推荐名单
  3. 模拟数据需要授权:未授权的模拟想法必须标记
  4. 评分必须透明:展示所有维度的评分和权重
  5. 中文顶刊不可忽视:A股研究中中文文献是重要先例来源
  6. 新颖性评估必须具体:不能只说"新颖",要指出具体增量贡献

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

    Shell commands in SKILL.md call:

    • python

    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 Generate Idea loads about 2.5k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 237 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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). 237 words, ~2,476 tokens.

Download SKILL.mdSave it as .claude/skills/fin-generate-idea/SKILL.md (or your agent's skills folder).
name
fin-generate-idea
description
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。
argument-hint
research-field

经济金融研究想法生成器

针对研究方向 $ARGUMENTS 生成 8-12 个排序研究想法,经过数据可行性筛选后输出推荐名单。

流程概览

研究方向输入
     ↓
阶段1: 研究领域解析 + 约束提取
     ↓
阶段2: 文献提取 — 使用 MCP 获取高影响力论文
     ↓
阶段3: 缺口分析 — 识别领域内"未完成"的工作
     ↓
阶段4: 想法生成 — 基于文献生成 8-12 个想法
     ↓
阶段5: 【强制】数据可行性筛选 — 对每个想法运行数据源检查
     ↓
阶段6: 过滤标记 — 无数据路径的想法标记"需授权模拟"
     ↓
阶段7: 综合排序 — noverlty × 0.4 + data × 0.3 + publish × 0.3
     ↓
输出: IDEA_REPORT.md

触发条件

当用户明确要求生成具体研究想法时触发,例如:

  • "有什么关于[领域]的研究想法"
  • "生成[领域]的研究idea"
  • "帮我找[领域]的研究方向"
  • "我想研究[主题],有什么新想法"

输出文件

output/fin-ideas/
├── IDEA_REPORT.md         ← 完整想法报告(8-12个想法,含评分)
├── IDEA_DATA_CHECK.md     ← 数据可行性检查结果
└── IDEA_CANDIDATES.md     ← 精简版(TOP 3-5)

阶段详解

阶段1: 研究领域解析
1.1 解析研究领域

识别研究方向所属的宏观领域:

领域核心关键词典型研究问题
绿色金融ESG、碳排放、绿色债券、气候风险、绿色信贷绿色政策效果、环境信息披露
数字金融Fintech、数字支付、互联网金融、API银行数字普惠、金融科技赋能
碳经济学碳交易、碳配额、碳关税、减排激励碳市场效率、政策有效性
宏观金融货币政策传导、金融周期、系统性风险政策传导机制、金融稳定
公司金融融资约束、资本结构、公司治理、并购融资决策优化、公司价值
资产定价因子模型、异常收益、机构投资者定价因子、收益预测
行为金融投资者情绪、散户行为、羊群效应行为偏差、市场效率
金融科技区块链、数字货币、开放银行新技术应用、模式创新
1.2 提取约束

从用户输入中提取约束条件:

python
constraints = {
    "target_journal": "JF/JFE/RFS/经济研究/金融研究/...",
    "method_preference": "DID/IV/RDD/机器学习/...",
    "data_preference": "A股/美股/宏观/...",
    "time_range": "2010-2024/特定事件窗口/...",
    "sample_restriction": "创业板/国有企业/...",
}
阶段2: 文献提取
2.1 MCP 多源检索

必须按以下顺序执行检索:

yaml
# 第1步:NBER 工作论文(优先)
CallMcpTool: user-nber-wp -> search_nber_papers
  query: "[研究领域] + China + empirical"
  year_from: 2023

# 第2步:OpenAlex(250M+论文)
CallMcpTool: user-openalex -> get_openalex_works
  query: "[研究领域] + [核心机制] + China"
  per_page: 30

# 第3步:中文顶刊(A股必查)
CallMcpTool: user-brave-search -> brave_web_search
  query: "经济研究 金融研究 管理世界 [核心关键词]"
  num_results: 15

# 第4步:ArXiv(方法论文)
CallMcpTool: user-arxiv -> semantic_search
  query: "[研究领域] + empirical methods China"
  max_results: 15
2.2 高影响力论文筛选

从检索结果中筛选高影响力论文:

筛选标准阈值原因
期刊层次JF/JFE/RFS/JME/QJE + 中文顶刊质量保证
引用量前 20% 或 >50 次引用经时间检验
发表时间近 5 年为主前沿性
方法可靠性识别策略清晰可参照
2.3 文献结构化提取

对每篇核心文献提取:

markdown
## 文献卡片

- **标题**: [论文标题]
- **期刊**: [期刊名]
- **年份**: [发表年份]
- **作者**: [作者列表]
- **核心发现**: [1-2句话]
- **方法**: [DID/IV/RDD/...]
- **数据**: [数据集描述]
- **研究缺口**: [从该论文的 limitation 或 future work 中提取]
阶段3: 缺口分析
3.1 缺口识别框架

使用以下框架系统识别研究缺口:

缺口类型描述识别方法
理论缺口某理论预测在特定场景未被验证文献中"我们尚不清楚..."
方法缺口某方法在特定场景未被使用方法 vs 市场组合矩阵
数据缺口某数据集未被用于某研究问题新数据源 vs 研究问题
场景缺口某发现未在特定市场验证市场 vs 机制组合矩阵
机制缺口某传导路径未被检验机制链条中的空白
3.2 缺口输出模板
markdown
## 已识别研究缺口

### 缺口 1: [缺口名称]
- **类型**: [理论/方法/数据/场景/机制]
- **描述**: [具体描述]
- **为什么重要**: [理论和实践意义]
- **可行性**: [数据和方法是否可行]

### 缺口 2: [缺口名称]
...
阶段4: 想法生成
4.1 生成提示词

使用 LLM 生成基于文献的研究想法:

你是一名经济金融领域顶级学者。请基于以下文献综述和研究缺口,
生成8-12个可发表的研究想法。

【研究领域】
[领域名称]

【核心文献】
[文献卡片列表]

【已识别的研究缺口】
1. [缺口1]
2. [缺口2]
...

【约束条件】
- 目标期刊: [期刊]
- 偏好方法: [方法]
- 数据偏好: [数据]

【生成要求】
1. 每个想法必须对应一个或多个研究缺口
2. 明确识别策略(DID/IV/RDD/面板/机器学习)
3. 明确所需核心数据
4. 指出边际贡献(理论/方法/数据)
5. 评估发表潜力
6. 基于文献给出"初步信号"(支持假设的已有证据)
4.2 想法格式

每个想法必须按以下格式输出:

markdown
## Idea N: [标题]

### 基本信息
- **研究缺口**: [对应缺口编号]
- **研究问题**: [一句话描述]
- **核心机制**: [因果传导路径]

### 方法设计
- **识别策略**: [方法]
- **关键识别假设**: [假设内容]
- **估计方法**: [模型]

### 数据需求
- **核心数据集**: [数据源]
- **时间范围**: [样本期]
- **关键变量**: [Y, X, 控制变量]

### 边际贡献
- **理论**: [理论贡献]
- **方法**: [方法贡献]
- **数据**: [数据贡献]

### 发表潜力
- **目标期刊**: [期刊]
- **新颖性**: [高/中/低]
- **可行性**: [高/中/低]

### 初步信号
- **文献支持**: [支持假设的已有文献]
- **机制合理性**: [1-5评分]
阶段5: 数据可行性筛选(强制)

对每个想法执行数据源检查

5.1 调用 IdeaDataValidator
python
from scripts.idea_data_checker import quick_check, IdeaDataValidator

# 准备想法列表
ideas = [
    {
        "id": f"idea_{i}",
        "title": "[想法标题]",
        "description": "[描述]",
        "keywords": "[关键词列表]",
    }
    for i in range(1, 13)
]

# 执行数据可行性检查
report = quick_check(ideas)
5.2 筛选逻辑
python
def filter_ideas_by_feasibility(report: ValidationReport) -> dict:
    """根据数据可行性筛选想法"""

    # 分类
    available = [r for r in report.idea_results
                 if r.feasibility == Feasibility.AVAILABLE]

    partial = [r for r in report.idea_results
               if r.feasibility == Feasibility.PARTIALLY_AVAILABLE]

    gap = [r for r in report.idea_results
           if r.feasibility == Feasibility.DATA_GAP]

    auth = [r for r in report.idea_results
            if r.feasibility == Feasibility.REQUIRES_AUTH]

    return {
        "green": available,      # 可立即推荐
        "yellow": partial,       # 可推进但需补充
        "red": gap,             # 需先补充数据
        "orange": auth,         # 需授权模拟
    }
阶段6: 用户授权决策

橙色标签的想法需要用户明确授权才能进入推荐名单

6.1 展示授权请求
⚠️ 以下想法需要您授权使用模拟数据:

想法 9: [标题]
- 所需数据: [数据描述]
- 缺失原因: [原因]
- 授权后果: 研究结果不能用于正式发表

想法 10: [标题]
...

──────────────────────────────────────────────
请选择:
  (1) 授权模拟 — 使用模拟数据继续(结果不能发表)
  (2) 跳过模拟想法 — 仅推荐数据可行的想法
  (3) 补充数据 — 稍后补充真实数据后再评估
6.2 标记处理
python
# 用户授权后,标记为可推荐
authorized_ideas = [idea for idea in ideas if idea.get("authorized_synthetic")]

# 未授权的想法标记为"需授权"
for idea in ideas:
    if idea.get("feasibility") == Feasibility.REQUIRES_AUTH and not idea.get("authorized_synthetic"):
        idea["status"] = "REQUIRES_AUTH"
        idea["recommendation"] = "需用户授权使用模拟数据"
阶段7: 综合排序
7.1 评分公式
综合评分 = 新颖性评分 × 0.4 + 数据可行性评分 × 0.3 + 发表潜力评分 × 0.3
维度权重评分标准
新颖性40%高=10, 中=7, 低=4
数据可行性30%可行=10, 部分=6, 缺口=0, 模拟=3
发表潜力30%顶刊=10, 一区=8, 二区=6
7.2 排序输出
python
def rank_ideas(ideas: list[dict], report: ValidationReport) -> list[dict]:
    """综合排序想法"""

    # 构建评分查找表
    score_map = {r.idea["id"]: r.feasibility_score for r in report.idea_results}

    ranked = []
    for idea in ideas:
        novelty = {"high": 10, "medium": 7, "low": 4}.get(idea.get("novelty"), 5)
        data_score = score_map.get(idea["id"], 0) * 10  # 转换为10分制
        publish = {"top": 10, "first": 8, "second": 6}.get(idea.get("journal_tier"), 5)

        composite = novelty * 0.4 + data_score * 0.3 + publish * 0.3

        idea["composite_score"] = round(composite, 1)
        ranked.append(idea)

    return sorted(ranked, key=lambda x: x["composite_score"], reverse=True)

输出格式

IDEA_REPORT.md 模板
markdown
# 研究想法报告

**研究方向**: [方向]
**生成日期**: [日期]
**想法总数**: N个

## 执行摘要

[3-5句话总结推荐想法]

## TOP 3 推荐想法

### 想法 1: [标题] ⭐⭐⭐
**综合评分**: X.X/10 | **数据可行性**: 🟢 可行

| 维度 | 评分 |
|------|------|
| 新颖性 | X/10 |
| 数据可行性 | X/10 |
| 发表潜力 | X/10 |
| **综合** | **X.X/10** |

- **研究问题**: [一句话]
- **研究缺口**: [对应缺口]
- **识别策略**: [方法]
- **核心数据**: [数据源]
- **边际贡献**: [创新点]
- **文献支持**: [支持假设的已有文献]
- **初步信号**: [支持/不支持/待验证]

---

### 想法 2: [标题] ⭐⭐
**综合评分**: X.X/10 | **数据可行性**: 🟡 部分可行

| 维度 | 评分 |
|------|------|
| 新颖性 | X/10 |
| 数据可行性 | X/10 |
| 发表潜力 | X/10 |
| **综合** | **X.X/10** |

- **研究问题**: [一句话]
- **研究缺口**: [对应缺口]
- **识别策略**: [方法]
- **核心数据**: [数据源]
- **边际贡献**: [创新点]
- **数据缺口**: [缺失的数据]
- **补充方案**: [如何获取]

---

### 想法 3: [标题] ⭐
**综合评分**: X.X/10 | **数据可行性**: 🟡 部分可行

[同上结构]

---

## 所有想法列表

| 排名 | 想法 | 综合评分 | 新颖性 | 数据可行 | 发表潜力 | 状态 |
|------|------|---------|--------|---------|---------|------|
| 1 | 想法1 | 9.2 | 高 | 🟢 可行 | 顶刊 | 推荐 |
| 2 | 想法2 | 8.5 | 高 | 🟡 部分 | 一区 | 推荐 |
| 3 | 想法3 | 8.1 | 中 | 🟢 可行 | 顶刊 | 推荐 |
| 4 | 想法4 | 7.2 | 中 | 🟡 部分 | 一区 | 待补充 |
| 5 | 想法5 | 6.8 | 高 | 🔴 缺口 | 一区 | 待数据 |
| 6 | 想法6 | 5.5 | 中 | 🟠 模拟 | 二区 | 需授权 |
| ... | ... | ... | ... | ... | ... | ... |

## 数据需求汇总

### 🟢 可直接使用
- [数据源]: [描述]

### 🟡 需补充
- [数据源]: [描述] → [如何获取]

### 🔴 需获取
- [数据源]: [描述] → [获取方式]

## 下一步

1. 选择一个想法进入新颖性验证(fin-novelty-check)
2. 或选择多个想法进入实验设计(fin-experiment-design)
3. 或返回补充数据后再评估

## 方法论提示

[针对本领域的常用识别策略建议]

IdeaDataValidator 快速参考

一行调用
python
from scripts.idea_data_checker import quick_check

ideas = [
    {"id": "1", "title": "想法1", "description": "描述", "keywords": ["关键词"]},
    # ...
]

report = quick_check(ideas)
逐个验证
python
from scripts.idea_data_checker import IdeaDataValidator

validator = IdeaDataValidator(ideas)
report = validator.validate_all()
validator.print_report(report)

# 访问结果
for result in report.idea_results:
    print(f"{result.idea['title']}: {result.feasibility.value}")
    print(f"  Score: {result.feasibility_score:.1f}")
    print(f"  Recommendation: {result.recommendation}")
解读可行性状态
Feasibility含义颜色建议操作
AVAILABLE数据完全可行🟢可立即推荐
PARTIALLY_AVAILABLE部分数据缺失🟡可推进但需补充
DATA_GAP数据缺口严重🔴需先获取数据
REQUIRES_AUTH需授权模拟🟠需用户明确授权

MCP 工具快速索引

需求MCP Server工具优先级
NBER 工作论文user-nber-wpsearch_nber_papers高
OpenAlex 论文user-openalexget_openalex_works高
ArXiv 论文user-arxivsemantic_search中
中文文献user-brave-searchbrave_web_search高
论文全文user-context7get_context7_by_query中
研报user-eastmoney-reportsget_research_report低

关键约束

  1. 每个想法必须基于文献:不能凭空生成想法
  2. 数据可行性是硬过滤:无数据路径的想法不进推荐名单
  3. 模拟数据需要授权:未授权的模拟想法必须标记
  4. 评分必须透明:展示所有维度的评分和权重
  5. 中文顶刊不可忽视:A股研究中中文文献是重要先例来源
  6. 新颖性评估必须具体:不能只说"新颖",要指出具体增量贡献

快速命令

bash
# 完整流程
python scripts/research_framework/pipeline.py \
    --topic "研究方向" \
    --mode generate_idea \
    --output output/fin-ideas/

# 仅想法生成
python scripts/research_framework/pipeline.py \
    --topic "研究方向" \
    --mode generate_idea \
    --skip_validation

# 仅数据验证
python scripts/idea_data_checker.py \
    --ideas-file output/fin-ideas/IDEA_REPORT.md

© 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-generate-idea of csmar432/finai-research.

Open the folder on GitHubat commit 47eebb7

Compare with similar skills

Fin Generate Idea 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 Generate Idea compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fin Generate Idea this skillcsmar432/finai-research109—~2.5kAutomated safety check: PassMIT
Idea CreatorAI4Scientist/nano-scientist1284 repos~3.9kAutomated safety check: WarnNone
Aer Statspaibrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~3kAutomated safety check: PassCustom licence
Stata AuditSepineTam/mcp-for-stata264—~1.2kAutomated safety check: PassAGPL-3.0
Diagnostic DofileSepineTam/mcp-for-stata264—~1.2kAutomated safety check: PassAGPL-3.0
Stata DiscoverSepineTam/mcp-for-stata264—~1.7kAutomated safety check: PassAGPL-3.0

Similar skills

  • Idea Creator

    AI4Scientist/nano-scientist

    Generate and rank research ideas given a broad direction. An agent skill from AI4Scientist/nano-scientist.

    128 GitHub starsUsed in 4 repos~3.9k tokens
    Research & ScienceAuto-check: warnings
  • Aer Statspai

    brycewang-stanford/Auto-Empirical-Research-Skills

    A skill your agent uses when aer-identification has fixed the design, after methodology choice and before aer-robustness or aer-tables-figures, to run an AER-track analysis with StatsPAI — the…

    4.6k GitHub stars~3k tokensUpdated 5 days ago
    Research & ScienceAuto-check passed
  • Stata Audit

    SepineTam/mcp-for-stata

    Inspect, validate, summarize, and render local Stata-MCP audit evidence under .statamcp.

    264 GitHub stars~1.2k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Diagnostic Dofile

    SepineTam/mcp-for-stata

    A skill your agent uses when the user needs to inspect, audit, or diagnose the safety of a Stata do-file.

    264 GitHub stars~1.2k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Stata Discover

    SepineTam/mcp-for-stata

    A skill your agent uses when you need to find Stata on the user's machine or configure stata-mcp to use it.

    264 GitHub stars~1.7k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Rfc Impl Generator

    SepineTam/mcp-for-stata

    Generate RFC and IMPL documents from a user-provided feature/fix description.

    264 GitHub stars~1.1k tokensUpdated 4 days ago
    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 4 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 4 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 4 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 4 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 4 days ago
    Auto-check passed
  • Fin Lit Review

    csmar432/finai-research

    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。

    109 GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed

Questions about Fin Generate Idea

What does Fin Generate Idea do?

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。. Fin Generate Idea is an agent skill from csmar432/finai-research.

When should I use Fin Generate Idea?

Fin Generate Idea fits situations like: tasks that involve Brainstorming; tasks that involve Econometrics and empirical research.

How do I install Fin Generate Idea in Claude Code?

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

How do I install Fin Generate Idea in Codex?

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

Can I use Fin Generate Idea 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-generate-idea -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-generate-idea, .gemini/skills/fin-generate-idea, .github/skills/fin-generate-idea and .opencode/skills/fin-generate-idea in your project.

What does Fin Generate Idea need to run?

Going by SKILL.md and its folder, Fin Generate Idea needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Fin Generate Idea 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 Generate Idea 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 Generate Idea use?

Fin Generate Idea 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 Generate Idea use?

About 2.5k tokens (SKILL.md is roughly 9.9k 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 Generate Idea?

Skills that share tags, products or a category with Fin Generate Idea: Idea Creator (AI4Scientist/nano-scientist, 128 stars), Aer Statspai (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Stata Audit (SepineTam/mcp-for-stata, 264 stars) and Diagnostic Dofile (SepineTam/mcp-for-stata, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fin Generate Idea?

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.