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-paper-draftgit 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-paper-draft)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-paper-draft"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-paper-draft/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-paper-draft"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-paper-draft.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 | $0.10051 |
| Opus 5 | $0.00024 | $0.05025 |
| Sonnet 5 | $0.00010 | $0.02010 |
| Haiku 4.5 | $0.00005 | $0.01005 |
Grade A, and why
fin-paper-draft 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 — 989 lines — stays where its author put it; the contents beside it link to each section on GitHub.
经济金融论文正文写作
根据论文大纲和研究设计,生成完整的论文正文草稿(LaTeX格式)。
触发条件
触发关键词:写章节、生成正文、draft chapter、写Introduction、写Methodology、写Conclusion
指定章节:introduction、literature、methodology、results、robustness、conclusion、abstract
前置条件
读取以下文件(按优先级):
| 优先级 | 文件路径 | 说明 |
|---|---|---|
| 1 | FIN_BRIEF.md |
目标期刊、语言、字数目标 |
| 2 | output/fin-manuscript/PAPER_OUTLINE.md |
论文大纲 |
| 3 | output/fin-refinement/REFINED_DESIGN.md |
研究设计 |
| 4 | output/fin-refinement/VARIABLE_DEFINITIONS.md |
变量定义 |
| 5 | output/fin-refinement/ROBUSTNESS_PLAN.md |
稳健性检验方案 |
| 6 | output/fin-manuscript/FIGURE_PLAN.md |
图表计划 |
| 7 | output/fin-manuscript/TABLE_PLAN.md |
表格计划 |
| 8 | output/fin-literature/LIT_REVIEW.md |
文献综述 |
| 9 | output/fin-novelty/NOVELTY_REPORT.md |
新颖性报告 |
| 10 | output/fin-experiments/DATA_MANIFEST.md |
数据清单 |
| 11 | output/fin-refinement/empirical_package.json 或 output/empirical_package.json |
实证包写稿门 |
政策 DID / 因果主张开写前必须过写稿门:
python -m scripts.core.empirical_package audit output/empirical_package.json --manuscript <草稿>
无包文件的纯写作轨可跳过。有包则四件同时(主栏显著、控制有职务、活机制表、图干净)才许把结果写成「研究发现」。正文禁止备忘录腔(不应解释为 / 升为主结果),参考文献表不写 DOI。
输出文件
output/fin-manuscript/draft_v{N}/
├── introduction.tex # 引言
├── literature.tex # 文献综述与假说
├── methodology.tex # 数据与实证方法
├── results.tex # 实证结果
├── robustness.tex # 稳健性检验
├── conclusion.tex # 结论
├── abstract.tex # 摘要
└── references.bib # 参考文献
论文规格确认
从 FIN_BRIEF.md 提取:
目标期刊: [JF/JFE/RFS/经济研究/金融研究/管理世界]
语言: [English/中文]
字数目标: [X词/字]
LaTeX模板: [aea/jfe/rfs/经济研究/...]
章节写作模板
Abstract / 摘要
英文摘要模板(JF/JFE风格,250 words)
\begin{abstract}
This paper examines whether [RESEARCH QUESTION] using [DATA SOURCE]
covering [SAMPLE PERIOD]. Our identification strategy exploits
[NATURAL EXPERIMENT / IDENTIFICATION STRATEGY], which allows us to
address [ENDOGENEITY CONCERN]. We find that [MAIN FINDING 1],
consistent with [THEORY/PREDICTION]. A one-standard-deviation
increase in [X] is associated with [Y] basis points
[increase/decrease] in [OUTCOME], representing [ECONOMIC MAGNITUDE].
Further analysis reveals that [MECHANISM]: the effect operates
primarily through [CHANNEL]. The result is stronger for [SUBGROUP]
and weaker for [SUBGROUP]. Our results are robust to [ROBUSTNESS
CHECKS] and continue to hold after controlling for [ALTERNATIVE
EXPLANATIONS]. The findings contribute to [LITERATURE STREAMS] and
have implications for [POLICY/INVESTORS/REGULATORS].
\textbf{JEL Classification:} [e.g., G01, G14, G32]
\textbf{Keywords:} [3--5 keywords]
\end{abstract}
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 · 989 lines · 49 tokens per session scan A c104b484e9da
fin-paper-draft is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 10,051 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
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.