Idea Creator
AI4Scientist/nano-scientist
Generate and rank research ideas given a broad direction. An agent skill from AI4Scientist/nano-scientist.
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。
$ npx skills add csmar432/finai-research --skill fin-generate-idea -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install csmar432/finai-research fin-generate-idea --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-srcUse ~/.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/
Install the "fin-generate-idea" agent skill from https://github.com/csmar432/finai-research/tree/main/.agents/skills/fin-generate-idea into .claude/skills/fin-generate-idea/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fin-generate-idea", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/csmar432/finai-research/tree/main/.agents/skills/fin-generate-ideaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add csmar432/finai-research --skill fin-generate-idea -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install csmar432/finai-research fin-generate-idea --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/csmar432/finai-research.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/fin-generate-idea .agents/skills/fin-generate-idea && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fin-generate-idea" agent skill from https://github.com/csmar432/finai-research/tree/main/.agents/skills/fin-generate-idea into .agents/skills/fin-generate-idea/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fin-generate-idea", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add csmar432/finai-research --skill fin-generate-idea -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install csmar432/finai-research fin-generate-idea --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/csmar432/finai-research.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/fin-generate-idea .cursor/skills/fin-generate-idea && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fin-generate-idea" agent skill from https://github.com/csmar432/finai-research/tree/main/.agents/skills/fin-generate-idea into .cursor/skills/fin-generate-idea/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fin-generate-idea", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/csmar432/finai-research.git --path .agents/skills/fin-generate-idea--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add csmar432/finai-research --skill fin-generate-idea -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install csmar432/finai-research fin-generate-idea --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/csmar432/finai-research.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/fin-generate-idea .gemini/skills/fin-generate-idea && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fin-generate-idea" agent skill from https://github.com/csmar432/finai-research/tree/main/.agents/skills/fin-generate-idea into .gemini/skills/fin-generate-idea/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fin-generate-idea", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install csmar432/finai-research fin-generate-ideaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add csmar432/finai-research --skill fin-generate-idea -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/csmar432/finai-research.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/fin-generate-idea .github/skills/fin-generate-idea && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fin-generate-idea" agent skill from https://github.com/csmar432/finai-research/tree/main/.agents/skills/fin-generate-idea into .github/skills/fin-generate-idea/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fin-generate-idea", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add csmar432/finai-research --skill fin-generate-idea -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install csmar432/finai-research fin-generate-idea --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/csmar432/finai-research.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/fin-generate-idea .opencode/skills/fin-generate-idea && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fin-generate-idea" agent skill from https://github.com/csmar432/finai-research/tree/main/.agents/skills/fin-generate-idea into .opencode/skills/fin-generate-idea/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fin-generate-idea", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
fin-generate-idea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. 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.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 47eebb7. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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.
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.
The full file from csmar432/finai-research at commit 47eebb7, republished under its MIT licence (© csmar432). 237 words, ~2,476 tokens.
.claude/skills/fin-generate-idea/SKILL.md (or your agent's skills folder).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。
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当用户明确要求生成具体研究想法时触发,例如:
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)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 |
从用户输入中提取约束条件:
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/...",
}必须按以下顺序执行检索:
# 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 |
对每篇核心文献提取:
## 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]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 |
## 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]
...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)每个想法必须按以下格式输出:
## 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]对每个想法执行数据源检查
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)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
}橙色标签的想法需要用户明确授权才能进入推荐名单
⚠️ 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# 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"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 |
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)# 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]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)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}")| 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 |
| 需求 | MCP Server | 工具 | 优先级 |
|---|---|---|---|
| NBER 工作论文 | user-nber-wp | search_nber_papers | 高 |
| OpenAlex 论文 | user-openalex | get_openalex_works | 高 |
| ArXiv 论文 | user-arxiv | semantic_search | 中 |
| 中文文献 | user-brave-search | brave_web_search | 高 |
| 论文全文 | user-context7 | get_context7_by_query | 中 |
| 研报 | user-eastmoney-reports | get_research_report | 低 |
# 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
Just SKILL.md in .agents/skills/fin-generate-idea of csmar432/finai-research.
Open the folder on GitHubat commit 47eebb7
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fin Generate Idea this skillcsmar432/finai-research | 109 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Idea CreatorAI4Scientist/nano-scientist | 128 | 4 repos | ~3.9k | Automated safety check: Warn | None | |
| Aer Statspaibrycewang-stanford/Auto-Empirical-Research-Skills | 4.6k | — | ~3k | Automated safety check: Pass | Custom licence | |
| Stata AuditSepineTam/mcp-for-stata | 264 | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | |
| Diagnostic DofileSepineTam/mcp-for-stata | 264 | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | |
| Stata DiscoverSepineTam/mcp-for-stata | 264 | — | ~1.7k | Automated safety check: Pass | AGPL-3.0 |
AI4Scientist/nano-scientist
Generate and rank research ideas given a broad direction. An agent skill from AI4Scientist/nano-scientist.
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…
SepineTam/mcp-for-stata
Inspect, validate, summarize, and render local Stata-MCP audit evidence under .statamcp.
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.
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.
SepineTam/mcp-for-stata
Generate RFC and IMPL documents from a user-provided feature/fix description.
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。
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.
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)。
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。
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。
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。
Works with
Categories
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.
Fin Generate Idea fits situations like: tasks that involve Brainstorming; tasks that involve Econometrics and empirical research.
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.
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.
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.
Going by SKILL.md and its folder, Fin Generate Idea needs the command-line tools its instructions call (python). Our summary lists: Python 3.
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.
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.
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.
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.
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.
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.