daily-paper-digest每日 AI 论文速递,自动聚合 arXiv 和 HuggingFace 的最新论文并推送到聊天应用。
Install via ClawdBot CLI:
clawdbot install qjymary/daily-paper-digest每天自动从 arXiv 和 HuggingFace 抓取最新 AI 论文,格式化后推送到你的聊天应用(飞书、Slack、Discord 等)。
fetch_daily_papers获取今日最新论文速递。
用法:
python3 main.py
参数:
config/sources.json 中的配置)返回:
search_arxiv_papers搜索特定主题的 arXiv 论文。
用法:
python3 arxiv_fetcher.py
参数(在代码中修改):
query:搜索关键词,如 "large language model"max_results:最大返回数量(默认 5)返回:
fetch_huggingface_papers获取 HuggingFace 每日热门论文。
用法:
python3 huggingface_fetcher.py
参数:
https://huggingface.co/papers)返回:
编辑 config/sources.json 来自定义信息源和过滤规则:
{
"sources": [
{
"name": "arxiv",
"enabled": true,
"categories": ["cs.AI", "cs.CL", "cs.CV", "cs.LG"],
"max_results": 10
},
{
"name": "huggingface",
"enabled": true,
"max_results": 10
}
],
"filter": {
"keywords": ["LLM", "transformer"],
"exclude_keywords": []
}
}
| 代码 | 含义 |
|------|------|
| cs.AI | 人工智能 |
| cs.CL | 计算语言学/NLP |
| cs.CV | 计算机视觉 |
| cs.LG | 机器学习 |
| cs.NE | 神经网络 |
| cs.RO | 机器人 |
| stat.ML | 统计机器学习 |
pip3 install -r requirements.txt
python3 test.py
python3 main.py
在 OpenClaw 中配置 Cron 表达式(例如每天 9:00):
0 9 * * *
在聊天应用中发送以下任意内容即可触发:
论文速递今日论文最新论文/papers/digestarxiv — arXiv 官方 Python 客户端requests — HTTP 请求beautifulsoup4 — HTML 解析feedparser — RSS/Atom 解析╔══════════════════════════════════════════════════════════╗
║ 🎓 AI 论文每日速递 - 2026年02月20日 ║
╚══════════════════════════════════════════════════════════╝
📊 今日共收录 15 篇论文
============================================================
📄 论文 1
============================================================
📌 标题: Attention Is All You Need
👥 作者: Ashish Vaswani, Noam Shazeer 等 8 人
🏷️ 来源: ARXIV | 日期: 2026-02-20
📝 摘要:
The dominant sequence transduction models are based on...
🔗 arXiv: http://arxiv.org/abs/1706.03762
📥 PDF: http://arxiv.org/pdf/1706.03762
daily-paper-digest/
├── SKILL.md ← 本文件(ClawHub 规范)
├── main.py ← 主程序
├── arxiv_fetcher.py ← arXiv 模块
├── huggingface_fetcher.py ← HuggingFace 模块
├── requirements.txt ← Python 依赖
└── config/
├── sources.json ← 默认配置
└── sources_llm.json ← LLM 专用配置
Generated Feb 24, 2026
AI research labs use this skill to automatically fetch and share the latest arXiv papers in specific categories like cs.AI or cs.CL daily, keeping team members informed without manual searching. It integrates with Slack or Discord for real-time notifications, streamlining literature review and sparking discussions on new findings.
Technology companies employ this skill to monitor AI advancements by aggregating papers from arXiv and HuggingFace, filtering for keywords like LLM or transformer to track competitors and innovations. The formatted outputs are pushed to internal chat apps like Lark, aiding strategic planning and product development.
Universities and online learning platforms use this skill to curate daily paper digests for students and instructors in AI courses, providing up-to-date resources and examples. It supports custom configurations to focus on topics like computer vision or NLP, enhancing curriculum relevance and engagement.
Venture capital firms and investors leverage this skill to track emerging AI trends by fetching daily papers, helping identify promising startups and technologies. The skill's filtering by categories and keywords enables quick insights into areas like robotics or neural networks, informing investment decisions.
News outlets and tech blogs use this skill to automate the discovery of breaking AI research, generating summaries for articles or newsletters. By integrating with scheduling tools via OpenClaw, it ensures timely updates on topics like large language models, reducing manual effort in content creation.
Offer a premium version with advanced features like custom filtering, priority support, and integration with more chat platforms (e.g., Microsoft Teams). Revenue is generated through monthly or annual subscriptions from research teams and enterprises seeking enhanced paper curation.
Provide a free basic version for individual users and charge for API access or high-volume usage by companies. Revenue comes from API calls for automated paper fetching, enabling integration into custom workflows and applications.
License the skill as a white-label product for universities, corporations, or media companies to rebrand and use internally. Revenue is generated through one-time licensing fees or ongoing support contracts, catering to organizations needing branded AI research tools.
💬 Integration Tip
Use OpenClaw's scheduling feature to set up daily automated runs, and customize config/sources.json to filter papers by relevant categories and keywords for your specific needs.
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.
This skill should be used when the user asks for news updates, daily briefings, or what's happening in the world. Fetches news from trusted international RSS feeds and can create voice summaries.
Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides concise news briefs with direct links to original articles. Activates when user asks for 'today's AI news', 'AI updates', 'latest AI developments', or mentions wanting a 'daily AI briefing'.
Generates a warm, compact daily briefing with weather, calendar, reminders, birthdays, and important emails for cron or chat delivery.
Provides a personalized morning report with today's reminders, undone Notion tasks, and vault storage summary for daily planning.