daily-paper-generator
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDaily Paper Generator
论文日报生成器
Overview
概述
Automate the workflow of discovering, reviewing, and summarizing recent research papers on arXiv related to EEG decoding, brain-computer interfaces, and neural foundation models.
Core workflow:
- Search arXiv for recent papers (within 3 months) using Chrome browser
- Retrieve paper metadata from arXiv pages
- Evaluate paper quality using structured criteria
- Select top 3 papers
- Generate structured summaries with Chinese and English reviews
- Save results as Markdown files in directory
daily paper/
自动化完成arXiv平台上EEG解码、脑机接口、神经基础模型相关最新研究论文的发现、评审和摘要生成工作流。
核心工作流:
- 使用Chrome浏览器检索arXiv上近3个月内的最新论文
- 从arXiv页面提取论文元数据
- 按照结构化标准评估论文质量
- 筛选出排名前3的论文
- 生成包含中英双语评审的结构化摘要
- 将结果保存为Markdown文件,存放在目录下
daily paper/
When to Use
适用场景
Use this skill when:
- User asks to "generate daily paper" or "find recent EEG papers"
- User wants to discover research on EEG decoding, speech decoding from EEG, or brain foundation models
- User needs paper reviews with both Chinese and English summaries
- User wants to track recent arXiv publications in neuro/AI intersection
符合以下条件时可使用本技能:
- 用户要求「生成论文日报」或「查找最新EEG相关论文」
- 用户需要挖掘EEG解码、EEG语音解码或脑基础模型相关的研究内容
- 用户需要同时包含中英双语摘要的论文评审内容
- 用户想要追踪神经科学与AI交叉领域的arXiv最新发表成果
Output Format
输出格式
Each paper summary follows this structure (see for complete example):
example/daily paper example.md每份论文摘要遵循如下结构(完整示例可参考):
example/daily paper example.md1. Header Section
1. 头部模块
markdown
undefinedmarkdown
undefinedPaper Title
Paper Title
作者及单位
作者及单位
Author list
Institution
Author list
Institution
arXiv 链接
arXiv 链接
发表日期: YYYY-MM-DD
arXiv ID: XXXX.XXXXX
分类: cs.LG, q-bio.NC, eess.SP
undefined发表日期: YYYY-MM-DD
arXiv ID: XXXX.XXXXX
分类: cs.LG, q-bio.NC, eess.SP
undefined2. Review Sections
2. 评审模块
中文评语 (~300 words):
- Background (1-2 sentences): Research context and importance
- Challenges (2-3 sentences): Problems with existing methods
- Contribution (1-2 sentences): Core contribution of this work
- Method (2-3 sentences): Key technical details
- Results (2-3 sentences): Main findings and metrics
- Analysis & Limitations (1-2 sentences): Significance and limitations
English Review (fluent academic English):
- Concise summary following the same structure as Chinese review
- Use natural academic prose (avoid AI-like patterns)
- Apply scientific writing best practices
中文评语(约300字):
- 研究背景(1-2句话):研究的上下文与重要性
- 现存挑战(2-3句话):现有方法存在的问题
- 核心贡献(1-2句话):本工作的核心创新点
- 实现方法(2-3句话):关键技术细节
- 实验结果(2-3句话):核心发现与指标表现
- 分析与局限(1-2句话):研究意义与存在的局限性
英文评审(流畅的学术英语):
- 遵循和中文评审相同的结构输出简洁摘要
- 使用自然的学术表述(避免AI生成式的模板化内容)
- 遵循科学写作的最佳实践
3. Main Figure Section
3. 主图模块
markdown
undefinedmarkdown
undefined主图
主图
[预留论文主图位置]
undefined[预留论文主图位置]
undefined4. Metadata Table
4. 元数据表格
markdown
undefinedmarkdown
undefined论文元数据
论文元数据
| 项目 | 内容 |
|---|---|
| 标题 | Paper Title |
| 第一作者 | First Author Name |
| 作者列表 | Full author list |
| 第一作者单位 | Institution |
| 发表日期 | YYYY-MM-DD |
| arXiv 链接 | https://arxiv.org/abs/ID |
| PDF 链接 | https://arxiv.org/pdf/ID |
| 分类 | cs.LG, q-bio.NC, eess.SP |
undefined| 项目 | 内容 |
|---|---|
| 标题 | Paper Title |
| 第一作者 | First Author Name |
| 作者列表 | Full author list |
| 第一作者单位 | Institution |
| 发表日期 | YYYY-MM-DD |
| arXiv 链接 | https://arxiv.org/abs/ID |
| PDF 链接 | https://arxiv.org/pdf/ID |
| 分类 | cs.LG, q-bio.NC, eess.SP |
undefined5. Integrated Format (for publishing)
5. 整合格式(用于发布)
markdown
undefinedmarkdown
undefined整合格式
整合格式
Daily Paper MMDD
Paper Title
[Chinese Review]
[English Review]
undefinedDaily Paper MMDD
Paper Title
[Chinese Review]
[English Review]
undefined6. Appendix
6. 附录
markdown
undefinedmarkdown
undefined附录
附录
github连接: [Available/Not Available]
补充说明
[Key insights, impact points]
Sources:
- arXiv Abstract
- arXiv HTML
- Paperverse Review (if available)
undefinedgithub连接: [Available/Not Available]
补充说明
[Key insights, impact points]
Sources:
- arXiv Abstract
- arXiv HTML
- Paperverse Review (if available)
undefinedQuick Reference
快速参考
| Task | Method |
|---|---|
| Search arXiv | Use Chrome MCP tools (chrome-mcp-helper) |
| Get paper details | Navigate to arXiv pages and extract metadata |
| Evaluate quality | Use criteria in |
| Write Chinese review | Follow style in |
| Write English review | Apply scientific-writing skill best practices |
| Create output | Use template in |
| 任务 | 实现方法 |
|---|---|
| 检索arXiv | 使用Chrome MCP工具 (chrome-mcp-helper) |
| 获取论文详情 | 跳转到arXiv论文页面并提取元数据 |
| 质量评估 | 参照 |
| 撰写中文评审 | 遵循 |
| 撰写英文评审 | 遵循科学写作技能的最佳实践 |
| 生成输出文件 | 使用 |
Workflow
工作流
Step 1: Search arXiv Using Chrome
步骤1:使用Chrome检索arXiv
Search keywords (see for full list):
references/keywords.md- EEG decoding: ,
EEG decoding,brain decodingneural decoding - Speech decoding: ,
speech decoding from EEGEEG speech reconstruction - Foundation models: ,
EEG foundation model,large EEG modelbrain foundation model
Method: Use Chrome browser with arXiv search
-
Navigate to arXiv search using Chrome MCP tools:
- URL:
https://arxiv.org/search/ - Add search parameters:
?searchtype=all&query=KEYWORDS&abstracts=show&order=-announced_date_first
- URL:
-
Search URL pattern:
https://arxiv.org/search/?searchtype=all&query=EEG+decoding&abstracts=show&order=-announced_date_first https://arxiv.org/search/?searchtype=all&query=EEG+foundation+model&abstracts=show&order=-announced_date_first -
Time filtering: Use date filters or sort byto get recent papers
announced_date_first -
Extract paper information from search results:
- Paper title
- Authors
- arXiv ID
- Abstract preview
- Publication date
检索关键词(完整列表见):
references/keywords.md- EEG解码:,
EEG decoding,brain decodingneural decoding - 语音解码:,
speech decoding from EEGEEG speech reconstruction - 基础模型:,
EEG foundation model,large EEG modelbrain foundation model
方法:使用Chrome浏览器访问arXiv进行检索
-
通过Chrome MCP工具跳转到arXiv检索页面:
- URL:
https://arxiv.org/search/ - 添加检索参数:
?searchtype=all&query=KEYWORDS&abstracts=show&order=-announced_date_first
- URL:
-
检索URL示例:
https://arxiv.org/search/?searchtype=all&query=EEG+decoding&abstracts=show&order=-announced_date_first https://arxiv.org/search/?searchtype=all&query=EEG+foundation+model&abstracts=show&order=-announced_date_first -
时间筛选:使用日期过滤器或按排序获取最新论文
announced_date_first -
从检索结果中提取论文信息:
- 论文标题
- 作者
- arXiv ID
- 摘要预览
- 发表日期
Step 2: Retrieve Paper Details
步骤2:获取论文详情
For each candidate paper, navigate to its arXiv abs page and extract:
URL pattern:
https://arxiv.org/abs/ARXIV_IDExtract from page:
- Title (from tag)
<h1> - Authors (from element)
.authors - Abstract (from )
blockquote.abstract - Submission date (from )
.dateline - arXiv ID (from URL or page)
- Categories (from )
.subjects - Comments (if present)
- First author institution (if available in comments or author affiliations)
针对每篇候选论文,跳转到对应的arXiv摘要页面并提取以下内容:
URL格式:
https://arxiv.org/abs/ARXIV_ID从页面提取的内容:
- 标题(来自标签)
<h1> - 作者(来自元素)
.authors - 摘要(来自)
blockquote.abstract - 提交日期(来自)
.dateline - arXiv ID(来自URL或页面内容)
- 分类(来自)
.subjects - 备注(如果存在)
- 第一作者单位(如果备注或作者 affiliations 中有提供)
Step 3: Evaluate Paper Quality
步骤3:评估论文质量
Review each paper using the 5-dimension criteria in :
references/quality-criteria.md| Dimension | Weight | Key Points |
|---|---|---|
| Innovation | 30% | Novelty of contribution |
| Method Completeness | 25% | Clarity and reproducibility |
| Experimental Thoroughness | 25% | Validation depth |
| Writing Quality | 10% | Clarity of expression |
| Relevance & Impact | 10% | Domain importance |
Scoring: Rate each dimension 1-5, calculate weighted sum.
Process:
- Screen by title/abstract for relevance
- Navigate to full paper page for detailed review
- Score each dimension
- Rank by total score
- Select top 3
使用中的5维度标准评审每篇论文:
references/quality-criteria.md| 维度 | 权重 | 核心评估点 |
|---|---|---|
| 创新性 | 30% | 贡献的新颖度 |
| 方法完整性 | 25% | 表述清晰度与可复现性 |
| 实验充分性 | 25% | 验证深度 |
| 写作质量 | 10% | 表述清晰度 |
| 相关性与影响力 | 10% | 领域重要性 |
评分规则: 每个维度按1-5分打分,计算加权总分。
流程:
- 通过标题/摘要筛选相关性
- 跳转到完整论文页面进行详细评审
- 为每个维度打分
- 按总分排序
- 筛选出排名前3的论文
Step 4: Generate Paper Summaries
步骤4:生成论文摘要
For each selected paper, create a summary following the structure in :
example/daily paper example.mdRequired sections:
- Title (H1 heading)
- 作者及单位 (Authors and Institution)
- arXiv 链接 (with metadata: date, ID, categories)
- 中文评语 (Chinese review, ~300 words)
- English Review (fluent academic English)
- 主图 (placeholder for main figure)
- 论文元数据 (metadata table)
- 整合格式 (integrated format for publishing)
- 附录 (appendix with github link,补充说明, sources)
Writing Chinese review (see ):
references/writing-style.md- Background: 研究背景和重要性
- Challenges: 现有方法的不足
- Contribution: 本工作的核心贡献
- Method: 关键技术细节
- Results: 主要发现和指标
- Analysis & Limitations: 意义和局限性
Writing English review:
- Apply scientific-writing skill best practices
- Use anti-AI writing principles (natural, varied sentence structure)
- Keep concise and direct
- Avoid formulaic transitions ("furthermore", "moreover", "additionally")
针对每篇入选论文,按照中的结构生成摘要:
example/daily paper example.md必填模块:
- 标题(H1级标题)
- 作者及单位 (Authors and Institution)
- arXiv 链接(包含元数据:日期、ID、分类)
- 中文评语(约300字)
- English Review(流畅的学术英语)
- 主图(主图占位符)
- 论文元数据(元数据表格)
- 整合格式(用于发布的整合格式)
- 附录(包含github链接、补充说明、来源)
中文评审撰写要求(参考):
references/writing-style.md- 背景: 研究背景和重要性
- 挑战: 现有方法的不足
- 贡献: 本工作的核心贡献
- 方法: 关键技术细节
- 结果: 主要发现和指标
- 分析 & 局限性: 意义和局限性
英文评审撰写要求:
- 遵循科学写作技能的最佳实践
- 使用反AI写作原则(自然、句式多样)
- 保持简洁直接
- 避免公式化过渡词(如"furthermore", "moreover", "additionally")
Step 5: Save Output
步骤5:保存输出结果
Create Markdown files in the directory:
daily paper/daily paper/
├── 2025-01-26-1430-paper-1.md
├── 2025-01-26-1430-paper-2.md
└── 2025-01-26-1430-paper-3.mdFilename format:
YYYY-MM-DD-HHMM-paper-N.mdImportant: 使用时间戳(精确到分钟)避免覆盖之前生成的文件。
在目录下创建Markdown文件:
daily paper/daily paper/
├── 2025-01-26-1430-paper-1.md
├── 2025-01-26-1430-paper-2.md
└── 2025-01-26-1430-paper-3.md文件名格式:
YYYY-MM-DD-HHMM-paper-N.mdImportant: 使用时间戳(精确到分钟)避免覆盖之前生成的文件。
Example Output
输出示例
See for a complete example of the DeeperBrain paper summary with all sections properly formatted.
example/daily paper example.md完整的DeeperBrain论文摘要示例可参考,所有模块格式均已正确配置。
example/daily paper example.mdAdditional Resources
额外资源
Reference Files
参考文件
- - Complete search keyword list and arXiv URL patterns
references/keywords.md - - Detailed 5-dimension evaluation criteria with scoring rubrics
references/quality-criteria.md - - Chinese review structure, templates, and example analysis
references/writing-style.md
- - 完整的检索关键词列表与arXiv URL格式
references/keywords.md - - 包含评分细则的5维度详细评估标准
references/quality-criteria.md - - 中文评审结构、模板与示例分析
references/writing-style.md
Example Files
示例文件
- - Complete output example with all sections
example/daily paper example.md - - Legacy Python script (deprecated, use Chrome instead)
scripts/arxiv_search.py
- - 包含所有模块的完整输出示例
example/daily paper example.md - - 旧版Python脚本(已废弃,建议使用Chrome)
scripts/arxiv_search.py
Chrome MCP Tools
Chrome MCP 工具
Use Chrome MCP tools for browser automation:
- Navigation: Open arXiv search and paper pages
- Screenshot: Capture pages for analysis
- Tabs: Manage multiple arXiv pages
- Content extraction: Parse paper metadata from HTML
使用Chrome MCP工具实现浏览器自动化:
- 页面跳转:打开arXiv检索页与论文页面
- 截图:捕获页面用于分析
- 标签页管理:管理多个arXiv页面
- 内容提取:从HTML中解析论文元数据
Important Notes
注意事项
- Time range: Search focuses on papers from the last 3 months (check submission dates)
- Link format: Use arXiv abs page links (https://arxiv.org/abs/ID), not direct PDF links
- Review length: Chinese reviews should be approximately 300 words
- Quality focus: Prioritize content quality (innovation, method, experiments) over quantitative metrics
- Bilingual output: Both Chinese and English reviews are required for each paper
- Chrome required: This workflow uses Chrome browser automation via MCP tools
- Complete format: Ensure all 9 sections are included in each summary
- Consistent naming: Use Daily Paper MMDD format in integrated section
- 时间范围:检索范围为近3个月内的论文(检查提交日期)
- 链接格式:使用arXiv摘要页链接(https://arxiv.org/abs/ID),不要直接使用PDF链接
- 评审长度:中文评审长度约为300字
- 质量优先:优先保障内容质量(创新性、方法、实验),而非量化指标
- 双语输出:每篇论文都需要同时提供中文和英文评审
- Chrome依赖:本工作流通过MCP工具使用Chrome浏览器自动化能力
- 格式完整性:确保每份摘要都包含全部9个模块
- 命名一致性:在整合格式中使用的命名规范
Daily Paper MMDD