mcpField
P
papers

papers

github.com/atholaProductivity34399 installsUpdated 1d ago
Repository

About papers

papers is a research skill for finding academic papers, citations, and formal research, then extracting structured findings. It searches several scholarly and open-access sources and specifies a PDF-to-Markdown workflow.

Key features

  1. 01Search arXiv, Semantic Scholar, and open-access sources
  2. 02Follow prioritized source order
  3. 03Convert PDFs to Markdown
  4. 04Extract findings, methods, and citation details
  5. 05Handle paywalled-paper fallbacks

Use cases

  1. 01Finding papers for a literature review
  2. 02Tracing citation chains
  3. 03Extracting methods and results from PDFs

MCP support

The skill directs users to try the `leyline:document-conversion` MCP `convert_to_markdown` tool first when processing a PDF, with the Read tool as fallback.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/athola/claude-night-market --skill papers

After installing, type/papersin Claude Code to confirm it loaded.

Details

From the project README

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 Skill(tome:discourse))
  • Code implementations (use Skill(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

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

Comments

Markdown supported