360 Secure SkillHub
360 安全技能中心

papers

核心功能：通过arXiv、Semantic Scholar等多数据源检索学术文献，获取开放获取版本，将PDF转为结构化markdown，提取摘要、研究方法、结果等关键学术信息，还提供付费文献获取建议。典型场景：查找学术论文、构建文献综述、追踪引用链。输入为相关关键词或触发词，输出检索结果、转换后的markdown及提取信息。

athola
athola
热度 62.80
最近更新 2026-08-26 21:24:40
分类：搜索依赖：第三方 API / MCP 服务 / 联网浏览搜索 / 读写文件 / 内部调用大模型应用场景：研究 / 摘要总结 / 报告撰写

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add nm-tome-papers
Metadata
name
papers
description
Searches academic literature via arXiv, Semantic Scholar, and open-access PDFs
version
1.9.8
triggers
["arxiv","semantic-scholar","academic","papers","pdf","building literature reviews or finding formal research on a topic"]
metadata
{"openclaw":{"homepage":"https://github.com/athola/claude-night-market/tree/master/plugins/tome","emoji":"🦞","requires":{"config":["night-market.leyline:document-conversion"]}}}
source
claude-night-market
source_plugin
tome

Night Market Skill — ported from claude-night-market/tome. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Academic Papers Search

When To Use

  • Finding academic papers, citations, or formal research
  • Building literature reviews or citation chains

When NOT To Use

  • Community opinions (use /tome:discourse)
  • Code implementations (use /tome:code-search)

Search arXiv, Semantic Scholar, and open-access sources.

Sources (Priority Order)

  1. arXiv API (free, unlimited metadata)
  2. Semantic Scholar API (100 req/5min, citation graphs)
  3. Unpaywall (legal free version discovery)
  4. CORE.ac.uk (open-access aggregator)
  5. PubMed Central (biomedical)
  6. Author preprint pages (WebSearch fallback)

PDF Processing

After acquiring a paper URL or local file path, convert the PDF to markdown for better extraction quality.

Conversion (prefer markitdown)

Apply the leyline:document-conversion protocol:

  1. Try markitdown first: call the MCP convert_to_markdown tool with the PDF URL or file:// path. This produces structured markdown preserving tables, equations, figures, and section hierarchy.

  2. Fall back to Read tool if markitdown is unavailable:

    • Read with pages: "1-20" for the first chunk
    • Continue with pages: "21-40" for longer papers
    • Continue in 20-page increments as needed
    • Note: tables and figures will not extract as cleanly

Extraction Targets

From the converted markdown, extract:

  • Abstract and key findings
  • Methodology and experimental setup
  • Results tables and figures
  • Citation information (authors, year, venue)
  • Key equations or formal definitions

Fallback Guidance

When a paper is paywalled and no open version exists:

  • Public library JSTOR/ProQuest access via library card
  • DeepDyve article rental
  • Inter-library loan request
  • Direct author email template