agentsclimarketplace

Semantic scholar api

Skill brycewang-stanford/Auto-Empirical-Research-Skills/skills/43-wentorai-research-plugins/skills/literature/search/semantic-scholar-api

Search papers and analyze citation graphs via OpenAlex and CrossRef APIsFrom its SKILL.md

Install
npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill semantic-scholar-api

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

5.2 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it

OpenAlex & CrossRef API Guide

Overview

OpenAlex is a free, open catalog of the global research system, indexing over 250 million academic works across all fields of science. It provides structured access to papers, authors, institutions, concepts, and citation networks. OpenAlex is the successor to Microsoft Academic Graph and is maintained by OurResearch (the team behind Unpaywall).

CrossRef is the official DOI registration agency for scholarly content, providing metadata for over 150 million DOIs across all publishers and disciplines. Together, OpenAlex and CrossRef provide comprehensive coverage for academic search, citation analysis, and bibliometric research.

Both APIs are free to use without authentication. OpenAlex requests a polite User-Agent header; CrossRef requests a User-Agent with contact email for access to the polite pool (faster rate limits).

Authentication

No authentication is required for either API.

OpenAlex: Include a User-Agent header for polite access:

User-Agent: ResearchPlugins/1.0 (https://wentor.ai)

CrossRef: Include a User-Agent header with contact email for polite pool:

User-Agent: ResearchPlugins/1.0 (https://wentor.ai; mailto:[email protected])

Core Endpoints

OpenAlex: Search Works

  • URL: GET https://api.openalex.org/works
  • Parameters:
    ParamTypeRequiredDescription
    searchstringNoFull-text search query
    filterstringNoFilter expression (e.g., from_publication_date:2024-01-01)
    sortstringNoSort field (e.g., cited_by_count:desc, publication_date:desc)
    per_pageintegerNoResults per page (default: 25, max: 200)
    pageintegerNoPage number (default: 1)
  • Example:
    curl "https://api.openalex.org/works?search=attention+is+all+you+need&per_page=5"
    
  • Response: JSON with meta (count, page info) and results array containing work objects.

OpenAlex: Get Work Details

  • URL: GET https://api.openalex.org/works/{id}
  • Parameters:
    ParamTypeRequiredDescription
    idstringYesOpenAlex ID (e.g., W2741809807), DOI URL, or other identifier
  • Example:
    curl "https://api.openalex.org/works/W2741809807"
    
  • Response: JSON with full work metadata including id, title, abstract_inverted_index, publication_year, cited_by_count, authorships, concepts, referenced_works.

OpenAlex: Search Authors

  • URL: GET https://api.openalex.org/authors
  • Parameters:
    ParamTypeRequiredDescription
    searchstringNoAuthor name search
    filterstringNoFilter expression
    per_pageintegerNoResults per page (max: 200)
  • Example:
    curl "https://api.openalex.org/authors?search=Yoshua+Bengio&per_page=5"
    
  • Response: JSON with author profiles including works_count, cited_by_count, summary_stats.h_index, affiliations.

CrossRef: Resolve DOI

  • URL: GET https://api.crossref.org/works/{doi}
  • Parameters:
    ParamTypeRequiredDescription
    doistringYesDOI to resolve (e.g., 10.1038/nature12373)
  • Example:
    curl "https://api.crossref.org/works/10.18653/v1/N19-1423"
    
  • Response: JSON with full bibliographic metadata including title, authors, journal, dates, references count, and citation count.

Rate Limits

OpenAlex: No strict rate limit, but use polite User-Agent header. Recommended: max 10 requests per second. The API returns HTTP 429 when limits are exceeded.

CrossRef: Without polite pool: ~50 requests per second. With polite pool (contact email in User-Agent): higher limits. The API returns HTTP 429 when limits are exceeded.

Common Patterns

Build a Citation Network

Retrieve a paper and find all works that cite it:

# Get paper details
curl "https://api.openalex.org/works/W2741809807"

# Get works citing this paper, sorted by citation count
curl "https://api.openalex.org/works?filter=cites:W2741809807&sort=cited_by_count:desc&per_page=20"

Find Influential Papers on a Topic

Search for highly cited works on a topic:

curl "https://api.openalex.org/works?search=graph+neural+networks&sort=cited_by_count:desc&per_page=20"

Batch Paper Lookup via CrossRef

Search CrossRef for papers matching a query, sorted by citation count:

curl "https://api.crossref.org/works?query=graph+neural+networks&sort=is-referenced-by-count&order=desc&rows=20"

References

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.