fin-ref-paper

fin-ref-paper is a skill for Claude Code, Codex from csmar432/finai-research. It costs 47 tokens per session (2,933 once invoked), scanned A, original, MIT.

A reference-management tool for economics and finance research documents. It extracts citation details from research files and creates a references.bib file in formats such as BibTeX, JF, JFE, RFS, or GB/T 7714.

In plain words
What is it for?
Use it to collect references from files such as LIT_REVIEW.md and IDEA_REPORT.md. It can combine references from several documents, fill in missing publication details through Crossref, and check citation consistency.
Why use it?
It reduces manual copying of author, title, year, journal, DOI, and page information. It also helps keep references consistent across literature reviews, idea reports, novelty checks, and paper drafts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to collect references from files such as LIT_REVIEW.md and IDEA_REPORT.md. It can combine references from several documents, fill in missing publication details through Crossref, and check citation consistency.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/csmar432/finai-research/fin-ref-paper
Install

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.

Any agent
npx skills add csmar432/finai-research --skill fin-ref-paper
Clone the repo
git clone --depth 1 https://github.com/csmar432/finai-research

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fin-ref-paper

README.md
[![agentmods](https://agentmods.dev/badge/skills/csmar432/finai-research/fin-ref-paper/github.svg)](https://agentmods.dev/skills/csmar432/finai-research/fin-ref-paper)
Your own site
<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-ref-paper"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-ref-paper/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.

agentmods 80×15 button for fin-ref-paper

Your own site · 80×15
<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-ref-paper"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-ref-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,933 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, 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 Data Exfiltration · line 69
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 96
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.02933
Opus 5 $0.00023 $0.01466
Sonnet 5 $0.00009 $0.00587
Haiku 4.5 $0.00005 $0.00293

Measured 11d ago against content hash ba74b542b352, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fin-ref-paper scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

resp = requests.get(
.agents/skills/fin-ref-paper/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fin-ref-paper

从LIT_REVIEW.md和IDEA_REPORT.md中提取参考文献,自动生成符合JF/JFE/RFS/GB-T-7714格式的references.bib,并管理引用一致性。

触发条件

  • 关键词: 参考文献 ref bib 引用格式 citation reference 文献引用 BibTeX
  • Skill语法: Skill: fin-ref-paper
  • 前置条件: 已有研究输出文件 (LIT_REVIEW.md, IDEA_REPORT.md 等)

参考文献管理流程

第一步:提取参考文献

从现有文档中自动提取参考文献信息:

from scripts.ref_paper import ReferenceExtractor, ExtractedReference

extractor = ReferenceExtractor()

# 从多个来源提取
extracted = extractor.extract_from_multiple(
    sources=[
        "output/fin-literature/LIT_REVIEW.md",
        "output/fin-ideas/IDEA_REPORT.md",
        "output/fin-novelty/NOVELTY_REPORT.md",
    ]
)

print(f"提取到 {len(extracted)} 条参考文献")
for ref in extracted[:3]:
    print(f"  - {ref.author} ({ref.year}). {ref.title}. {ref.journal}.")

提取的信息:

字段 说明 示例
author 作者 "Zhang, Y. and Li, X."
title 标题 "The Effect of Carbon Trading"
year 年份 2023
journal 期刊 "Journal of Finance"
volume "78"
issue "3"
pages 页码 "1234-1289"
doi DOI "10.1111/jofi.12345"
url URL (optional)

第二步:Enrich元数据

使用CrossRef API自动补全缺失信息:

import requests

def get_crossref_metadata(doi: str) -> dict:
    """通过DOI获取完整的文献元数据"""
    resp = requests.get(
        f"https://api.crossref.org/works/{doi}",
        headers={"User-Agent": "fin-research/1.0 (mailto:[email protected])"}
    )
    if resp.status_code == 200:
        return resp.json()["message"]
    return {}

def enrich_reference(ref: ExtractedReference) -> ExtractedReference:
    """补全缺失字段"""
    if ref.doi:
        meta = get_crossref_metadata(ref.doi)
        ref.volume = meta.get("volume", ref.volume)
        ref.issue = meta.get("issue", ref.issue)
        ref.pages = meta.get("page", ref.pages)
        ref.publisher = meta.get("publisher", "")
        # 规范化作者列表
        authors_raw = meta.get("author", [])
        ref.author = "; ".join([
            f"{a['family']}, {a['given'][0]}." 
            for a in authors_raw
        ])
    return ref

Read the full file on GitHub · 377 lines

Changes

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.

  1. 11d ago First seen · 377 lines · 47 tokens per session scan A ba74b542b352

Subscribe to this mod's changes

fin-ref-paper is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 2,933 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

citation-verification

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed…

Galaxy-Dawn/claude-scholar · 63 tokens

r-econometrics

Run IV, DiD, and RDD analyses in R with proper diagnostics.

brycewang-stanford/Auto-Empirical-Research-Skills · 20 tokens

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.

jayjeo/econometrics-phd-level-skill · 201 tokens

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…

xjtulyc/awesome-rosetta-skills · 75 tokens

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…

JonasWeinert/EconAgentSkills · 138 tokens

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.

pedrohcgs/claude-code-my-workflow · 54 tokens