mcpbeat

Papers

athola/papers

Searches academic literature via arXiv, Semantic Scholar, and open-access PDFs. Use when building literature reviews or finding formal research on a topic.

718 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
324
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/athola/claude-night-market --skill papers

The instruction itself

9 sections, as written by the author

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)

  • arXiv API (free, unlimited metadata)
  • Semantic Scholar API (100 req/5min, citation graphs)
  • Unpaywall (legal free version discovery)
  • CORE.ac.uk (open-access aggregator)
  • PubMed Central (biomedical)
  • 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:

  • 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.

  • 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

Exit Criteria

  • [ ] At least one academic source queried in priority order

(arXiv first, then Semantic Scholar, then Unpaywall/CORE/PubMed)

  • [ ] PDF content converted via leyline:document-conversion

protocol: markitdown MCP attempted first, Read-tool fallback

used if markitdown is unavailable

  • [ ] Each paper result includes citation info (authors, year, venue)

and an abstract or key findings summary

  • [ ] Paywalled papers with no open version trigger the fallback

guidance (library, DeepDyve, ILL, author contact) rather than

returning an empty result

  • [ ] If all sources return zero results, this is stated explicitly

rather than generating fabricated paper entries

How to use it

Copy the folder

Take athola/papers from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.