Nm Tome Papers

>- Search academic literature via arXiv, Semantic Scholar, and open-access discovery chains. Fetches and parses PDFs for key findings

Security Scan

The skill's instructions, required config, and capabilities are consistent with its stated purpose of finding and parsing academic papers; no unrelated credentials or installers are requested.

Purpose & Capability

Name/description (searching arXiv/Semantic Scholar and converting PDFs) match what the SKILL.md instructs. The single declared requirement (night-market.leyline:document-conversion) is directly used for PDF->markdown conversion and is appropriate for the task.

Instruction Scope

Instructions are narrowly focused on fetching paper metadata and converting PDFs to markdown via the Leyline MCP tools (convert_to_markdown / Read). They explicitly accept PDF URLs and file:// paths for local files — this is expected for handling user-provided PDFs but means the conversion tool may be given access to local files if a file path is supplied. If you plan to allow the agent to process local files, verify the conversion backend's behavior and trustworthiness.

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded by the skill itself.

Credentials

No environment variables, binaries, or credentials are requested. The single required config path (document-conversion) is proportional to converting PDFs and extracting text/structure.

Persistence & Privilege

always:false and no special system-wide privileges are requested. The skill does not modify other skills or request persistent system presence.

Assessment

This skill appears coherent for searching and extracting academic papers. Before installing: 1) Confirm the identity and behavior of the night-market.leyline:document-conversion provider (the conversion service will receive PDFs and may upload them to external services). 2) Avoid supplying sensitive local file:// paths unless you trust the conversion backend. 3) Test with non-sensitive PDFs to observe how files are handled. 4) Because the agent can invoke the skill autonomously (normal default), consider restricting autonomous runs if you want tighter control over what gets sent to the conversion service.

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