Menu
Academic metadata search via CrossRef API. Use when: user needs DOI resolution, citation counts, journal metadata, or publisher info. NOT for: full-text access or downloading papers.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
# Academic Literature Search — 学术文献检索与引用管理
Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.
Search arXiv for preprints in physics, math, CS, quantitative biology, quantitative finance, statistics, electrical engineering, economics. Use when: (1) finding preprints by topic, (2) searching by author, (3) browsing arXiv categories, (4) getting paper metadata/abstracts. NOT for: published journal articles (use crossref-search), biomedical (use pubmed-search).
Screen papers for systematic reviews using ASReview active learning. Use when: user has a large set of papers to screen for inclusion/exclusion, wants to prioritize relevant papers, or needs to reduce manual screening workload. NOT for: searching papers (use literature-search) or meta-analysis (use meta-analysis).
Analyzes astronomical observations and cosmological models including telescope data processing, celestial mechanics calculations, stellar evolution, galaxy classification, and cosmological parameter estimation; trigger when users discuss stars, galaxies, exoplanets, dark matter, or the universe's large-scale structure.
| name | crossref-search |
| description | Academic metadata search via CrossRef API. Use when: user needs DOI resolution, citation counts, journal metadata, or publisher info. NOT for: full-text access or downloading papers. |
| metadata | {"openclaw":{"emoji":"🔗","requires":{"bins":["curl"]}}} |
Academic metadata search and DOI resolution via the public CrossRef REST API.
curl -s "https://api.crossref.org/works/10.1038/nature12373" | python3 -c "
import sys, json
data = json.load(sys.stdin)['message']
title = data.get('title', [''])[0]
authors = ', '.join(f\"{a.get('given','')} {a.get('family','')}\" for a in data.get('author', []))
journal = data.get('container-title', [''])[0]
cited = data.get('is-referenced-by-count', 0)
print(f'Title: {title}')
print(f'Authors: {authors}')
print(f'Journal: {journal} | Citations: {cited}')
"
# Search by query terms
curl -s "https://api.crossref.org/works?query=machine+learning+protein+folding&rows=5&mailto=user@example.com" | python3 -c "
import sys, json
data = json.load(sys.stdin)['message']
for item in data['items']:
title = item.get('title', [''])[0]
doi = item.get('DOI', '')
cited = item.get('is-referenced-by-count', 0)
print(f'{title}')
print(f' DOI: {doi} | Citations: {cited}')
"
# Filter by date, type, and sort by citations
curl -s "https://api.crossref.org/works?query=CRISPR&filter=from-pub-date:2023-01-01,type:journal-article&rows=10&sort=is-referenced-by-count&order=desc&mailto=user@example.com"
# Search by author
curl -s "https://api.crossref.org/works?query.author=Jennifer+Doudna&rows=10&sort=published&order=desc&mailto=user@example.com"
# Search journals by title
curl -s "https://api.crossref.org/journals?query=nature+biotechnology&rows=5" | python3 -c "
import sys, json
for j in json.load(sys.stdin)['message']['items']:
print(f\"{j['title']} (ISSN: {', '.join(j.get('ISSN', []))})\")
"
# Get journal metadata by ISSN
curl -s "https://api.crossref.org/journals/0028-0836"
# Recent works from a journal
curl -s "https://api.crossref.org/journals/0028-0836/works?rows=5&sort=published&order=desc"
curl -s "https://api.crossref.org/funders?query=national+institutes+of+health&rows=5" | python3 -c "
import sys, json
for f in json.load(sys.stdin)['message']['items']:
print(f\"{f['name']} (ID: {f['id']})\")
"
# Works funded by a specific funder
curl -s "https://api.crossref.org/funders/100000002/works?rows=5&sort=is-referenced-by-count&order=desc"
curl -s "https://api.crossref.org/works/10.1038/nature12373" | python3 -c "
import sys, json
refs = json.load(sys.stdin)['message'].get('reference', [])
for r in refs[:10]:
doi = r.get('DOI', 'no DOI')
text = r.get('unstructured', r.get('article-title', 'N/A'))
print(f' [{doi}] {text[:100]}')
"
Filters: type:journal-article, from-pub-date:YYYY-MM-DD, until-pub-date:YYYY-MM-DD,
has-abstract:true, is-referenced-by-count:>100, funder:FUNDER_ID.
Sorting: sort=published|is-referenced-by-count|relevance, order=asc|desc.
Pagination: rows=N (max 1000), offset=N, or cursor=* for deep paging.
mailto=user@example.com to join the polite pool (faster, more reliable).+ or %20).select=DOI,title,author to reduce payload size.cursor=* pagination for result sets larger than 10,000 items.NEVER fabricate results from training data. Every paper title, author, DOI, PMID, citation count, and metadata detail presented to the user MUST come from an actual API response in this conversation. If the API returns no results or partial data, report exactly what was returned. Do not "fill in" missing details from memory.