Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Paper Lookup

Search 11 scholarly APIs — PubMed, arXiv, OpenAlex, Semantic Scholar and more — for papers, citations, and open-access full text, with reproducible provenance.

Web & APIIntermediate★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Routes your question to the right database among 11 academic APIs: PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, and Unpaywall.
  • Resolves and converts identifiers (DOI, PMID, PMCID, arXiv ID, OpenAlex ID, ORCID) and cross-references them across sources.
  • Retrieves citation graphs, author bibliographies, open-access PDF links, and sectioned full text parsed from JATS XML.
  • Built around a hard truth: these APIs fail with HTTP 200. Bundled scripts detect bodyless PMC articles, arXiv Error feeds, Europe PMC errCode bodies, and bad pagination steps instead of reporting confident nonsense.
  • Every answer ships with endpoints, parameters, access date, and count reconciliation so a human or another agent can repeat it.

Who it's for

  • Researchers, grad students, and clinicians doing frequent literature lookups.
  • Anyone running a systematic review or survey who needs auditable, exhaustive retrieval.
  • Teams building citation analyses or checking open-access availability at scale.

Examples

  1. Topic search: "Find recent preprints on organoids" → since bioRxiv has no keyword search, it queries Europe PMC with SRC:"PPR" and returns DOIs plus the exact query used.
  2. Identifier lookup: "Get metadata and a free PDF for 10.1038/nature12373" → Crossref for metadata, Unpaywall for OA status and the best PDF link.
  3. Citation analysis: "Who cites Attention Is All You Need?" → Semantic Scholar via arXiv ID, paginated with bounded calls and expected-vs-retrieved reconciliation.

Notes

Requires Bash/curl access. API keys are optional (except CORE full text) but strongly raise rate limits.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/paper-lookup folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/paper-lookup/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/paper-lookup ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, WSL or Git Bash on Windows).
  2. Verify prerequisites: python3 --version should report 3.11 or newer, and curl --version should work.
  3. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  4. Install the skill: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/paper-lookup ~/.claude/skills/
  5. (Optional) Export API keys for higher rate limits: export NCBI_API_KEY=..., export S2_API_KEY=..., export OPENALEX_API_KEY=..., export CORE_API_KEY=... — everything works without them except CORE full text.
  6. Restart Claude Code and try a prompt like "find papers on CRISPR base editing" or "look up this DOI and get me the PDF".
  7. If something misbehaves, run python3 ~/.claude/skills/paper-lookup/scripts/paginate.py --list-apis to confirm the bundled scripts execute correctly.
View source on GitHub ↗License: MIT