paper-lookup

Search ten academic paper databases via REST APIs for papers, citations, and full text.

Updated Sep 2, 2026
One-click install
npx skills add https://github.com/ricfulop/cba-agentic-engineering-bootstrap --skill paper-lookup-ricfulop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-lookup
Source: https://github.com/ricfulop/cba-agentic-engineering-bootstrap/tree/main/skills/paper-lookup
Command: npx skills add https://github.com/ricfulop/cba-agentic-engineering-bootstrap --skill paper-lookup-ricfulop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Finding scholarly literature requires juggling many databases with different APIs, identifier formats, and rate limits. This Skill routes a research query to the right academic databases, executes the REST API calls, and returns raw results with full provenance. ## 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 a selection guide matching intent to database. - Identifier handling and cross-referencing: Work with DOI, PMID, PMCID, arXiv ID, OpenAlex ID, and ORCID, including ID conversion via the PMC ID Converter and prefixed lookups in Semantic Scholar and OpenAlex. - Open access and full text retrieval: Locate OA PDFs via Unpaywall, full text via PMC (JATS XML) and CORE, and citation graphs via Semantic Scholar. - Use Case: Ask to find recent papers on CRISPR gene therapy and get open access PDFs; the Skill searches PubMed and OpenAlex in parallel, then checks Unpaywall per DOI for free copies. ## 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?

Describe your topic or provide an identifier, and the Skill selects the appropriate databases using its selection guide. For broad coverage it queries PubMed, OpenAlex, and Semantic Scholar in parallel, then returns raw JSON results with the endpoints used.

Which database should I use to find an open access PDF of a paper?

Use Unpaywall with the paper's DOI to check OA status and get a direct PDF link from best_oa_location. CORE and PMC also provide full text, with PMC covering biomedical articles in JATS XML format.

Can I search bioRxiv or medRxiv by keyword?

No, the bioRxiv and medRxiv APIs only support date-range browsing and DOI lookup, with no keyword search. For keyword searches of preprint content, use Semantic Scholar, OpenAlex, or CORE instead.

Do I need API keys to use these scholarly databases?

Most databases work without keys at lower rate limits. CORE requires a key for full text, while NCBI, Semantic Scholar, and OpenAlex optionally accept keys via environment variables like NCBI_API_KEY for higher rate limits.

Why did my paper lookup fail with an identifier error?

Each database accepts specific identifier formats, such as PMIDs for PubMed or arXiv IDs for arXiv. Use the PMC ID Converter to translate between PMID, PMCID, and DOI, or try prefixed identifiers like DOI: or ARXIV: in Semantic Scholar.

How do I get the citation graph for a specific paper?

Query Semantic Scholar's citations and references endpoints with the paper's DOI or other supported ID. OpenAlex also provides referenced_works and cited_by_count data for citation analysis.