Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/csmar432/finai-researchnpx agentmods add skills/csmar432/finai-research/fin-generate-ideaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/csmar432/finai-research/fin-generate-idea)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-generate-idea"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-generate-idea/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-generate-idea"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-generate-idea.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Tool Misuse · line 537 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.04699 |
| Opus 5 | $0.00026 | $0.02350 |
| Sonnet 5 | $0.00011 | $0.00940 |
| Haiku 4.5 | $0.00005 | $0.00470 |
Grade A, and why
fin-generate-idea scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
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:
# 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:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 543 lines · 53 tokens per session scan A ea3d5327c530
fin-generate-idea is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 4,699 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
r-econometrics
Run IV, DiD, and RDD analyses in R with proper diagnostics.
econometrics-phd-level
A guide to econometrics, the use of statistics to study relationships in data, based on a 12-part Korean lecture series. It routes questions to explanations of topics such as regression, panel data, instrumental variables, and causal comparisons.
did-causal
Use this Skill when the user needs to estimate causal treatment effects using difference-in-differences (DID) designs: two-way fixed effects (TWFE) regression, parallel trends pre-testing, Callaway-Sant'Anna staggered adoption estimator, and Goodman-Bacon decomposition. Covers both Python (linearmodels) and R (did…
r-econometrics
Generates rigorous, modern, reproducible R code for causal inference and panel econometrics with fixest, heterogeneity-robust DiD estimators (Callaway-Sant'Anna, Sun-Abraham, BJS, de Chaisemartin-D'Haultfoeuille), weak-IV-robust inference, optimal-bandwidth RDD via rdrobust, and wild cluster bootstrap. Use when the…
audit-reproducibility
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
review-paper
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via…