scopus-subscription
Skill12 starsChanged 5 months agoMITView on GitHub
Scopus 周更文献自动评分与 Obsidian 推荐笔记生成。当用户说"处理本周文献"、 "文献推送处理"、"生成文献推荐"、"更新 Scopus 推送"或类似表述时触发。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- TengleWang/PaperFlowword for word, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 1
- TengleWang/PaperFlow★ 12100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- paper-readerSkill
The file
Files
scopus-subscription
Scopus 周更文献自动评分与 Obsidian 推荐笔记生成。
前置步骤:读取配置
开始前先读取项目根目录下的 config.yaml(如不存在则读取 config.example.yaml 并提示用户复制修改)。从配置中获取:
paths.scopus_csv_dir— Scopus CSV 下载目录paths.python_exe— Python 解释器路径literature.summary_dir— 推荐笔记输出目录(在 Obsidian Vault 内)
触发条件
当用户说"处理本周文献"、"文献推送处理"、"生成文献推荐"、"更新 Scopus 推送"或类似表述时触发。
核心流程
步骤 1:确认 CSV 文件
从 config.yaml 的 scopus_topics 列表中读取所有主题。对每个主题,拼接路径:
{scopus_csv_dir}/{csv_filename}如果某个 CSV 不存在,跳过该主题并告知用户,继续处理其余文件。全部不存在则报错终止。
步骤 2:运行评分引擎
使用配置文件中的 Python 解释器执行 scripts/score.py:
{python_exe} <SKILL_DIR>/scripts/score.py --config <项目根目录>/config.yaml "csv1" "csv2" "csv3"score.py 输出 JSON 数组,每个元素包含 topic、total(论文总数)、top10(评分最高的 10 篇论文,每篇含 title/authors/journal/year/doi/abstract/score)。
静默执行:禁止向用户展示代码、运行日志或评分细节。
步骤 3:读取输出格式规范
读取 prompt.md,严格按其定义的模板生成 Markdown。核心格式:
- 概览:主题名、处理论文数、Top 10 最高分、新趋势总结(从 Top 10 摘要中提炼 2-3 句)
- Top 3 论文:一句话总结 + 核心贡献(具体数据/方法) + 详细分析(方法亮点、关联启发)
- 第 4-10 篇:作者/期刊/年份/DOI/评分 + 一句话总结 + 核心贡献(不含详细分析)
- 评分维度:相关性 50%(5分)+ 影响力 30%(3分)+ 研究质量 20%(2分)
步骤 4:生成 Markdown 文件
对 score.py 返回的每个主题:
- 计算当前 ISO 周数:
python -c "import datetime; print(datetime.date.today().isocalendar()[1])" - 文件名格式:
W{周数}-{topic}.md,如W24-点蚀预测.md - 保存到
{literature.summary_dir},目录不存在则自动创建 - 同名文件直接覆盖
步骤 5:汇报结果
简洁告知处理结果:
处理完成,已生成 X 个文件:
- {summary_dir}/W24-点蚀预测.md(共 Y 篇文献,Top 10 最高分 Z.Z)
- ...约束
- 评分过程对用户完全透明无感 — 禁止暴露代码或运行日志
- 每篇论文的一句话总结基于摘要内容,禁止凭空编造
- 新趋势总结综合 Top 10 摘要提炼,不简单罗列
- 自然语言内容使用简体中文
- 论文标题和期刊名保留原文,不翻译
- 评分保留一位小数,格式为
X.X/10
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

