paper-lookup

Search 10 academic paper databases via REST APIs for scholarly literature retrieval.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/hanasho744/codex --skill paper-lookup-hanasho744
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: paper-lookup
Source: https://github.com/hanasho744/codex/tree/main/.agents/skills/scientific-toolkit-skill/references/scientific-skills/paper-lookup
Command: npx skills add https://github.com/hanasho744/codex --skill paper-lookup-hanasho744

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Finding research papers, preprints, citations, and open access PDFs requires querying many separate scholarly databases with different APIs, identifier formats, and rate limits. This Skill routes each literature query to the right database(s) and returns structured results without manual API research. ## Core Features & Use Cases - Multi-database search: Query PubMed, PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, and Unpaywall through their REST APIs with per-database reference guides. - Identifier handling and conversion: Work with DOI, PMID, PMCID, arXiv ID, OpenAlex ID, and ORCID, including cross-database ID translation via the PMC ID Converter. - Open access and full text retrieval: Locate OA PDFs via Unpaywall and CORE, and fetch full text from PMC (JATS XML) or the BioC API. - Use Case: Ask to find recent papers on CRISPR gene therapy and get open access PDFs; the Skill searches PubMed and OpenAlex, then checks Unpaywall for each DOI's free PDF link. ## Quick Start Find recent papers on CRISPR gene therapy and check which ones have open access PDFs available.

Frequently Asked Questions about paper-lookup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search for academic papers across multiple databases?▼

Match your query intent to the right database: PubMed for biomedical topics, arXiv for physics/CS preprints, OpenAlex or Semantic Scholar for cross-field search. The Skill's selection guide maps use cases to databases, and multi-need queries can hit several databases in parallel.

How do I find an open access PDF for a paper by DOI?▼

Query the Unpaywall API with the DOI and an email parameter. Check the is_oa field; if true, use best_oa_location.url_for_pdf for the direct PDF link. CORE and PMC are alternatives for full text retrieval.

Which academic paper APIs require an API key?▼

CORE requires a key for full text access. NCBI (PubMed/PMC), Semantic Scholar, and OpenAlex work without keys but at lower rate limits. bioRxiv, medRxiv, arXiv, Crossref, and Unpaywall need no authentication.

Can I convert between PMID, PMCID, and DOI identifiers?▼

Yes, the PMC ID Converter API translates between PMID, PMCID, and DOI for articles indexed in PMC. Semantic Scholar and OpenAlex also accept multiple identifier prefixes like DOI:, PMID:, and ARXIV: directly in lookups.

Why does my arXiv API query return XML instead of JSON?▼

The arXiv API only returns Atom XML; there is no JSON option. Parse the <entry> elements for title, abstract, authors, and PDF links, or pipe curl output through an XML parser.

What are the rate limits for PubMed and arXiv APIs?▼

PubMed E-utilities allow 3 requests per second without an API key and 10 with one. arXiv enforces a hard limit of one request every 3 seconds on a single connection. HTTP 429 responses indicate you should wait and retry.