Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计通过

arxiv-watcharxiv 观察

Agent Skill

arxiv-watch 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

8,605

周安装

355

GitHub Stars

1

下载量

2,812
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:arxiv-watch(arxiv 观察)
来源仓库:https://github.com/constx1337/arxiv-watch
安装命令:
openclaw skills install arxiv-watch
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install arxiv-watch

简介

按类别监控最新 arXiv 论文,自动生成摘要并管理加星标论文供参考。

  • 适合科研人员跟踪特定领域动态,实现自动化文献管理与知识沉淀。
  • 在 OpenClaw 环境中通过 clawhub 安装,使用命令 openclaw skills install arxiv-watch。
  • 可能持续联网获取更新,需评估后台运行对系统资源的占用情况。
  • 建议检查是否支持自定义推送频率与分类过滤规则。

SKILL.md

name
arxiv-watcher
description
Monitor new papers on arXiv by category. Use when user wants to check latest papers, track research topics, or manage reading lists. Trigger phrases: "check arxiv", "new papers", "arxiv category", "watch arxiv", "latest papers on".

ArXiv Watcher

Monitor and track new papers on arXiv.org by category.

Overview

This skill helps you:

  • Fetch latest papers from specific arXiv categories
  • Generate formatted Markdown summaries
  • Star/bookmark papers for later reading

Quick Start

# Check latest papers in a category
/arxiv-watcher cs.AI

# Multiple categories
/arxiv-watcher cs.AI cs.CL cs.LG

# View starred papers
/arxiv-watcher --starred

Available Categories

Computer Science (cs.*)

CategoryDescription
cs.AIArtificial Intelligence
cs.CLComputation and Language
cs.CVComputer Vision
cs.LGMachine Learning
cs.NENeural and Evolutionary Computing
cs.RORobotics
cs.SESoftware Engineering

Physics (physics.*)

CategoryDescription
astro-phAstrophysics
cond-matCondensed Matter
hep-exHigh Energy Physics - Experiment
hep-thHigh Energy Physics - Theory
quant-phQuantum Physics

Mathematics (math.*)

CategoryDescription
math.AGAlgebraic Geometry
math.COCombinatorics
math.DGDifferential Geometry
math.NTNumber Theory
math.STStatistics Theory

Statistics (stat.*)

CategoryDescription
stat.MLMachine Learning
stat.THStatistics Theory

Full category list: https://arxiv.org/category_taxonomy

Commands

Fetch Latest Papers

python scripts/arxiv_watcher.py fetch <category> [--limit N]

Fetches recent papers from arXiv. Outputs Markdown format with:

  • Paper title and arXiv ID
  • Authors
  • Abstract preview (first 200 chars)
  • Link to full paper

Star Papers

python scripts/arxiv_watcher.py star <arxiv_id>

Adds a paper to starred list for later reference.

Unstar Papers

python scripts/arxiv_watcher.py unstar <arxiv_id>

Removes a paper from starred list.

View Starred Papers

python scripts/arxiv_watcher.py starred

Lists all starred papers with their details.

Output Format

Papers are displayed in Markdown format:

## [2403.12345] Paper Title Here

**Authors:** John Doe, Jane Smith
**Category:** cs.AI
**Submitted:** 2024-03-15

**Abstract:**
This paper presents a novel approach to...

**Links:**
- arXiv: https://arxiv.org/abs/2403.12345
- PDF: https://arxiv.org/pdf/2403.12345.pdf

---

Starred papers include a ⭐ marker for easy identification.

Workflow

When user asks to check arXiv:

  1. Identify categories - Parse user request for category names
  2. Fetch papers - Run arxiv_watcher.py fetch <category>
  3. Format output - Present papers in readable Markdown
  4. Offer actions - Ask if user wants to star any papers

Example Interactions

User: "check new papers in cs.AI"

Assistant: Runs fetch command, displays 5-10 recent papers, asks if any should be starred.

User: "star the second one"

Assistant: Parses the arxiv_id from previous output, runs star command, confirms action.

User: "show my starred papers"

Assistant: Runs starred command, displays list with details.

Resources

scripts/

  • arxiv_watcher.py - Main CLI for fetching and managing papers

assets/

  • starred.json - Persistent storage for starred papers (auto-created)

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

89.38%
按下载量换算2,513

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills