skills/67-econfin-workflow-toolkit/journal-digest/SKILL.md
经济金融顶刊文献速递与选题建议生成器。通过RSS和网页抓取获取经济学、金融学、会计学顶级期刊的最新论文, 筛选公司金融相关文献,生成中文综述摘要和研究选题建议。 当用户提到"期刊速递"、"文献周报"、"论文速递"、"最新文献"、"journal digest"、"paper digest"、 "选题建议"、"研究选题"、"顶刊追踪"、"文献追踪"、"周报"时触发此技能。 即使用户只是说"帮我看看最近有什么新论文"或"最近顶刊发了什么",也应该触发。
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research journal-digestInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
本技能从经济学、金融学、会计学顶级期刊抓取最新发表/在线发表的论文,筛选与公司金融相关的文献,生成结构化的中文综述周报,并提出研究选题建议。
与用户确认以下参数(如用户未指定则使用默认值):
| 参数 | 默认值 | 说明 |
|------|--------|------|
| 时间范围 | 最近7天 | 抓取论文的时间窗口,用户可指定如"最近两周"、"2026年3月" |
| 精选数量 | 15-25篇 | 最终进入周报的论文数量 |
| 选题数量 | 8-12个 | 研究选题建议数量 |
| 输出路径 | F:\OneDrive\研究发展部\期刊速递\ | 输出文件保存位置 |
| 输出文件名 | 公司金融周报_YYYY-MM-DD.md | 以生成日期命名 |
运行抓取脚本获取最新论文:
python "C:/Users/zhang/.claude/skills/journal-digest/scripts/fetch_papers.py" \
--days <天数> \
--output <临时JSON路径> \
--history "F:/OneDrive/研究发展部/期刊速递/.paper_history.json" \
--enrich
脚本会:
--enrich 参数为RSS抓取但缺少摘要的论文补充Crossref元数据如果脚本执行失败或部分期刊抓取失败,不要中断流程——用已成功抓取的论文继续。在周报末尾注明哪些期刊本次未能成功抓取。
如果脚本不可用或执行环境有问题,可以退化为手动模式:使用 WebFetch 工具逐个抓取期刊RSS/网页,手动收集论文信息。
从候选论文中筛选与公司金融相关的论文。筛选标准:
CF-核心(直接属于公司金融领域):
CF-交叉(与公司金融有交叉的其他领域):
方法/数据可借鉴:
对每篇入选论文,生成约150-250字的中文综述,包含:
[CF-核心]、[CF-交叉] 或 [方法/数据可借鉴]综述写作要求:
基于本期精选论文,提出8-12个研究选题建议。每个选题包含:
选题建议的原则:
按以下模板组装最终Markdown文件:
《公司金融周报》
2026年第XX周 | YYYY-MM-DD
---
## 一、本周精选论文(共XX条)
---
**1. [论文标题]**
[分类标签]
来源:期刊名, 卷期信息(时间)
[综述正文]
---
[... 更多论文 ...]
---
## 二、本周研究选题建议
---
**选题1:[选题标题]**
研究问题:[...]
数据/方法:[...]
关联条目:[...]
---
[... 更多选题 ...]
---
*本周报基于YYYY-MM-DD候选文献库(XX条)精选生成,覆盖[期刊列表]等顶级期刊。*
将本次入选的论文信息追加到历史记录文件 .paper_history.json,确保下次抓取时不会重复。
历史记录格式:
{
"papers": [
{
"title": "论文标题",
"doi": "DOI号(如有)",
"journal": "期刊名",
"date_fetched": "2026-04-15",
"digest_file": "公司金融周报_2026-04-15.md"
}
]
}
完整的期刊列表和RSS配置见 references/journals.json。
期刊按等级分为:
抓取优先级:A+ > A > A- > B+。如果候选论文过多,优先保留高等级期刊的论文。
tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.