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-lit-reviewgit 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-lit-review)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-lit-review"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-lit-review/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-lit-review"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-lit-review.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 | $0.00049 | $0.02303 |
| Opus 5 | $0.00024 | $0.01151 |
| Sonnet 5 | $0.00010 | $0.00461 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
fin-lit-review 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 13d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
经济金融系统性文献综述
整合多源学术数据库,构建引文网络,识别研究缺口。
核心功能
- 多源并行检索:OpenAlex / ArXiv / NBER / 百度学术
- PRISMA 筛选流程:Inclusion/Exclusion 标准透明
- 引文网络构建:NetworkX 有向图,可视化知识结构
- 研究缺口识别:LLM 分析 + 人工标注
- 结构化输出:LIT_REVIEW.md / LIT_SUMMARY.md / CITATION_GRAPH.json
工作流程
Step 1: PICO 解析
将研究问题拆解为 PICO 四要素:
P (Population): 研究对象 — 企业/投资者/银行/政府
I (Intervention): 处理变量 — 政策/工具/事件
C (Comparator): 对照组 — 处理前/未受政策影响
O (Outcome): 结果变量 — 创新/绩效/风险/效率
示例输入:"碳排放权交易对企业绿色创新的影响"
→ PICO: P=制造业企业, I=碳排放权交易试点, C=非试点企业, O=绿色专利/研发投入
Step 2: 多源并行检索
使用以下 MCP 工具并行搜索:
OpenAlex(优先,推荐 50 篇)
server: user-openalex
tool: get_openalex_works
params: {
"query": "carbon trading OR carbon emission trading green innovation",
"per_page": 50,
"sort": "citation_count"
}
ArXiv(预印本,最新方法)
server: user-arxiv
tool: semantic_search
params: {
"query": "carbon trading innovation policy effect DID",
"max_results": 30
}
NBER(工作论文,高质量)
server: user-nber-wp
tool: get_nber_papers
params: {
"category": "corporate finance OR environmental economics",
"year_from": 2021
}
中文文献(百度学术 + CNKI)
server: user-brave-search
tool: brave_web_search
params: {
"query": "碳排放权交易 绿色创新 DID 双重差分 经济研究"
}
研报补充(东方财富)
server: user-eastmoney-reports
tool: get_stock_news
params: {
"ts_code": "000001.SZ",
"limit": 20
}
# 用于补充行业背景,不作为核心文献
Step 3: PRISMA 筛选
对检索到的所有文献应用筛选标准:
Inclusion Criteria:
✓ 实证研究(排除纯理论/综述)
✓ 经济金融领域(或跨学科应用)
✓ 英文/中文全文可获取
✓ 2000年后发表
Exclusion Criteria:
✗ 纯工程/技术类研究(非金融视角)
✗ 无DOI/无法溯源
✗ 样本量<100 或 方法严重缺陷
✗ 与研究问题无关
Checkpoint:筛选完成后,向用户展示筛选数量统计:
## PRISMA 筛选结果
- 检索总数: [N]
- 去重后: [N]
- 标题/摘要筛选排除: [N]
- 全文筛选排除: [N]
- 最终纳入: [N]
是否继续生成文献综述?
[1] 继续
[2] 调整筛选标准
[3] 补充更多文献
Step 4: 引文网络构建
使用 scripts/citation_graph.py 构建知识图谱:
from scripts.citation_graph import CitationGraphBuilder
builder = CitationGraphBuilder()
graph = builder.build(papers) # papers: list of dict with title/doi/cite_count
# 提取高影响力文献
influential = builder.get_influential_papers(top_n=20)
# 提取引文聚类(研究主题簇)
clusters = builder.get_citation_clusters()
# 导出 JSON
graph_json = builder.to_json()
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.
- 13d ago First seen · 299 lines · 49 tokens per session scan A 08470494fd5b
fin-lit-review is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 2,303 once invoked, about $0.0002 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
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.
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.
capture-environment
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning…
grant-proposal
Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to /data-management-plan and the facilities statement to /capture-environment, and emits a funder-requirements checklist. Use…