skills/43-wentorai-research-plugins/skills/literature/search/semantic-scholar-api/SKILL.md
Search papers and analyze citation graphs via OpenAlex and CrossRef APIs
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research semantic-scholar-apiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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).
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])
GET https://api.openalex.org/worksfrom_publication_date:2024-01-01) |
| sort | string | No | Sort field (e.g., cited_by_count:desc, publication_date:desc) |
| per_page | integer | No | Results per page (default: 25, max: 200) |
| page | integer | No | Page number (default: 1) |curl "https://api.openalex.org/works?search=attention+is+all+you+need&per_page=5"
meta (count, page info) and results array containing work objects.GET https://api.openalex.org/works/{id}W2741809807), DOI URL, or other identifier |curl "https://api.openalex.org/works/W2741809807"
id, title, abstract_inverted_index, publication_year, cited_by_count, authorships, concepts, referenced_works.GET https://api.openalex.org/authorscurl "https://api.openalex.org/authors?search=Yoshua+Bengio&per_page=5"
works_count, cited_by_count, summary_stats.h_index, affiliations.GET https://api.crossref.org/works/{doi}10.1038/nature12373) |curl "https://api.crossref.org/works/10.18653/v1/N19-1423"
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.
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"
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"
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"
tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.