跳到正文
TakoAPI
返回技能列表

agentic-paper-digest-skill

由 matanle51 提供

Search & Research
2.7k下载量由 clawskills.sh 提供
5星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Fetches and summarizes recent arXiv.

描述

该技能的功能

Fetches recent papers from arXiv and Hugging Face, filters them by topic using an LLM relevance classifier, and produces summaries. Runs as a one-off CLI command or a persistent local API server. Results are stored in a SQLite database.

Combines source fetching, LLM-based relevance filtering, and summarization in a single configurable pipeline instead of requiring separate tools for each step.

何时使用

  • Daily digest of new ML/AI papers filtered to your research topics
  • Feeding filtered paper metadata into a downstream agent pipeline
  • Polling arXiv overnight and saving results for async review
  • Tracking papers in specific arXiv categories over a custom time window
  • Running a local API so a UI or cron job can query recent papers

示例工作流

输入

User asks: Get me today's papers on LLM safety from arXiv

智能体
  1. 1

    Bootstrap the repo using the provided bootstrap script

  2. 2

    Set OPENAI_API_KEY in the .env file

  3. 3

    Update config/topics.json with an LLM safety topic entry including relevant keywords

  4. 4

    Run the CLI with --window-hours 24 --sources arxiv

  5. 5

    Read the JSON output for run_id, seen, kept counts and query /api/papers for summaries

输出

A filtered list of arXiv papers matching the LLM safety topic, each with title, abstract summary, and metadata stored in papers.sqlite3

前置要求

  • OPENAI_API_KEY environment variable (or LITELLM_API_KEY with LITELLM_API_BASE for non-OpenAI providers)

安装

clawhub install matanle51/agentic-paper-digest-skill

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接