← Back to Skills Marketplace
qjymary

Daily Paper Digest

by QIN JIAYUE · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
1574
Downloads
9
Stars
14
Active Installs
1
Versions
Install in OpenClaw
/install daily-paper-digest
Description
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。
README (SKILL.md)

📚 每日 AI 论文速递

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)。

工具(Tools)

fetch_daily_papers

获取今日最新论文速递。

用法:

python3 main.py

参数:

  • 无(自动读取 config/sources.json 中的配置)

返回:

  • 格式化的论文列表,包含标题、作者、摘要、链接

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:

  • 匹配的论文列表

fetch_huggingface_papers

获取 HuggingFace 每日热门论文。

用法:

python3 huggingface_fetcher.py

参数:

  • 无(直接爬取 https://huggingface.co/papers

返回:

  • 热门论文列表,含点赞数

配置

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": []
  }
}

arXiv 常用分类

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

安装与使用

1. 安装依赖

pip3 install -r requirements.txt

2. 运行测试

python3 test.py

3. 获取今日论文

python3 main.py

4. 定时自动运行(配合 OpenClaw 调度器)

在 OpenClaw 中配置 Cron 表达式(例如每天 9:00):

0 9 * * *

在 OpenClaw 中触发

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
  • /digest

依赖

  • arxiv — arXiv 官方 Python 客户端
  • requests — HTTP 请求
  • beautifulsoup4 — HTML 解析
  • feedparser — RSS/Atom 解析

示例输出

╔══════════════════════════════════════════════════════════╗
║           🎓 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

文件结构

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
Usage Guidance
This skill is internally coherent and appears to do what it says: fetch and format papers from arXiv and HuggingFace. Before installing, consider the following: (1) origin verification — the repo/homepage field is a placeholder (https://github.com/your-username/...), so confirm the source or maintainer before deploying widely; (2) run the included test.py and first run the skill in a sandbox or isolated environment to confirm behavior and network traffic; (3) scraping HuggingFace relies on page structure and may break or be rate-limited — respect site robots and rate limits; (4) install dependencies into a virtualenv to avoid interfering with system packages; (5) if you plan to integrate with a chat app, ensure any chat webhook/credentials are provided only when necessary and stored securely (this skill does not request those by default).
Capability Analysis
Type: OpenClaw Skill Name: daily-paper-digest Version: 1.0.0 The skill bundle is designed to fetch and format AI papers from arXiv and HuggingFace. All code (`main.py`, `arxiv_fetcher.py`, `huggingface_fetcher.py`, `test.py`) uses standard Python libraries for web scraping and API interaction, without any evidence of malicious intent such as data exfiltration, unauthorized execution, or persistence mechanisms. The `SKILL.md` and `README.md` files contain clear, benign instructions for the AI agent and users, with no prompt injection attempts. While some internal methods (e.g., `huggingface_fetcher.fetch_paper_details` or `arxiv_fetcher.search_papers`) could present vulnerabilities like SSRF if exposed to unsanitized user input by a poorly designed agent interaction layer, the skill's defined tools and execution paths in `SKILL.md` do not expose these methods for dynamic user input, making the skill itself benign.
Capability Assessment
Purpose & Capability
Name/description (daily arXiv + HuggingFace digest) align with code and dependencies: the repository contains fetchers for arXiv and HuggingFace and a main runner. Required binaries (python3, pip3) and Python packages (arxiv, requests, beautifulsoup4, feedparser) are appropriate for the stated functionality.
Instruction Scope
SKILL.md instructs running main.py and editing config/sources.json. The runtime instructions only reference the skill's own config file and the two web sources. There are no instructions to read unrelated system files, environment secrets, or to transmit data to unexpected endpoints.
Install Mechanism
Dependencies are standard PyPI packages listed in requirements.txt (no arbitrary binary downloads). The install spec uses 'uv' as the kind for package installation which is atypical/ambiguous in the metadata, but the requirements.txt matches the listed packages so practical installation would use pip3 install -r requirements.txt. No high-risk external download URLs or archive extraction were found.
Credentials
The skill requests no environment variables, no credentials, and no config paths outside its own directory. All external network access is to public services (arXiv APIs and huggingface.co). The lack of requested secrets is proportionate to the task.
Persistence & Privilege
always is false and the skill does not request elevated system privileges or modify other skills' configurations. It is a scheduled/triggered skill with normal scope for periodic execution.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install daily-paper-digest
  3. After installation, invoke the skill by name or use /daily-paper-digest
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of daily-paper-digest. - Automatically aggregates the latest AI papers from arXiv and HuggingFace. - Supports formatted daily paper digests delivered to chat applications (Feishu, Slack, Discord, etc). - Includes tools for fetching daily papers, searching arXiv by topic, and getting top HuggingFace papers. - Provides customizable sources and filtering via config/sources.json. - Easy setup with clear installation and usage instructions.
Metadata
Slug daily-paper-digest
Version 1.0.0
License
All-time Installs 14
Active Installs 14
Total Versions 1
Frequently Asked Questions

What is 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。 It is an AI Agent Skill for Claude Code / OpenClaw, with 1574 downloads so far.

How do I install Daily Paper Digest?

Run "/install daily-paper-digest" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Daily Paper Digest free?

Yes, Daily Paper Digest is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Daily Paper Digest support?

Daily Paper Digest is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Daily Paper Digest?

It is built and maintained by QIN JIAYUE (@qjymary); the current version is v1.0.0.

💬 Comments