Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add csmar432/finai-research --skill fin-novelty-checkgit clone --depth 1 https://github.com/csmar432/finai-researchWrote 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-novelty-check)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-novelty-check"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-novelty-check/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-novelty-check"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-novelty-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.03060 |
| Opus 5 | $0.00026 | $0.01530 |
| Sonnet 5 | $0.00010 | $0.00612 |
| Haiku 4.5 | $0.00005 | $0.00306 |
Grade A, and why
fin-novelty-check 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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)
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)
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)
server: user-nber-wp
tool: get_nber_papers
params: {
"category": "corporate finance OR financial economics",
"year_from": 2023
}
中文顶刊
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)
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)
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 · 351 lines · 52 tokens per session scan A eabf480a58b3
fin-novelty-check is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 3,060 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…
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…
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.