openalex-database
Skill80 starsChanged 8 months agoMITView on GitHub
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
- Installs packages
9 other projects use a version of this, 7 of them edited.
Adopted by
Most recently taken up by
- Ivan-propio/claude-skillsedited, first seen Nov 16, 2026
- BrightGold70/skillsedited, first seen Nov 8, 2026
- MarieLynneBlock/arcanum-artifexedited, first seen Nov 1, 2026
- garri333/Skillsedited, first seen Oct 11, 2026
- wu-yc/LabClawedited, first seen Oct 8, 2026
- jaechang-hits/SciAgent-Skillstheir own version, first seen Jul 24, 2026
Other versions9 projects use a version of this.
Word for word · 1
- LeonChaoX/qinyan-academic-skills★ 910100% same
Edited · 7
- wu-yc/LabClaw★ 1.1k92% same
- SoFarSoGoodya/math-history-paper★ 17100% same
- MarieLynneBlock/arcanum-artifex★ 497% same
- BrightGold70/skills★ 192% same
- garri333/Skills★ 192% same
- yf8578/claude-skills-collection★ 192% same
- Ivan-propio/claude-skills★ 0100% same
Wrote their own version · 1
- jaechang-hits/SciAgent-Skills★ 386same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository180 other files it gives its agents.
- bgpt-paper-searchSkill
- biorxiv-databaseSkill
- citation-managementSkill
- literature-reviewSkill
- parallel-webSkill
- perplexity-searchSkill
- pubmed-databaseSkill
- pyzoteroSkill
- research-lookupSkill
- medical-imaging-reviewSkill
- paper-2-webSkill
- peer-reviewSkill
- research-proposalSkill
- scientific-writingSkill
- venue-templatesSkill
- generate-imageSkill
- infographicsSkill
- latex-postersSkill
- markdown-mermaid-writingSkill
- paper-slide-deckSkill
- pptx-postersSkill
- scientific-schematicsSkill
- scientific-slidesSkill
- scientific-visualizationSkill
- consciousness-councilSkill
- dhdna-profilerSkill
- hypothesis-generationSkill
- research-grantsSkill
- scholar-evaluationSkill
- scientific-brainstormingSkill
- scientific-critical-thinkingSkill
- what-if-oracleSkill
- anndataSkill
- arboretoSkill
- biopythonSkill
- bioservicesSkill
- cellxgene-censusSkill
- deeptoolsSkill
- etetoolkitSkill
- flowioSkill
- genimlSkill
- ggetSkill
- gtarsSkill
- lamindbSkill
- phylogeneticsSkill
- pydeseq2Skill
- pysamSkill
- scanpySkill
- scikit-bioSkill
- scveloSkill
- scvi-toolsSkill
- tiledbvcfSkill
- zarr-pythonSkill
- datamolSkill
- deepchemSkill
- diffdockSkill
- matchmsSkill
- medchemSkill
- molecular-dynamicsSkill
- molfeatSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. 17 are common, 0 are distinctive, and 5 are very specific to this project.
17
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 19
Always initialize the client with an email address to access the polite pool (10x rate limit boost):
- Common: line 35
No API key required - OpenAlex is completely open.
- Common: line 65
Use the two-step pattern (entity name → ID → works):
- Common: line 281
Add email to get 10x rate limit (1 req/sec → 10 req/sec):
- Common: line 287
Never filter by entity names directly - always get ID first:
- Very specific: line 298
Always use per-page=200 for efficient data retrieval:
- Common: line 304
Use batch_lookup() for multiple IDs instead of individual requests:
- Very specific: line 315
Use sample_works() with seed for reproducible random sampling:
- Common: line 401
Use external identifiers directly:
- Common: line 445
Use for direct API access with full control.
- Common: line 456
Use for common research queries with simplified interfaces.
- Common: line 462
Ensure email is added to requests
- Common: line 463
Verify not exceeding 10 req/sec
- Common: line 467
If searches return no results:
- Very specific: line 468
Check filter syntax (see references/api_guide.md)
- Common: line 469
Use two-step pattern for entity lookups (don't filter by names)
- Common: line 470
Verify entity IDs are correct format
- Very specific: line 474
Use pagination with per-page=200
- Very specific: line 475
Use select= to limit returned fields
- Common: line 483
Always use polite pool for production workflows by providing email to client.
- Common: line 488
All data is open and free
- Common: line 490
Use LitLLM with OpenRouter if LLM-based analysis is needed (don't use Perplexity API directly)
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenAlex Database
Overview
OpenAlex is a comprehensive open catalog of 240M+ scholarly works, authors, institutions, topics, sources, publishers, and funders. This skill provides tools and workflows for querying the OpenAlex API to search literature, analyze research output, track citations, and conduct bibliometric studies.
Quick Start
Basic Setup
Always initialize the client with an email address to access the polite pool (10x rate limit boost):
from scripts.openalex_client import OpenAlexClient
client = OpenAlexClient(email="your-email@example.edu")Installation Requirements
Install required package using uv:
uv pip install requestsNo API key required - OpenAlex is completely open.
Core Capabilities
1. Search for Papers
Use for: Finding papers by title, abstract, or topic
# Simple search
results = client.search_works(
search="machine learning",
per_page=100
)
# Search with filters
results = client.search_works(
search="CRISPR gene editing",
filter_params={
"publication_year": ">2020",
"is_oa": "true"
},
sort="cited_by_count:desc"
)2. Find Works by Author
Use for: Getting all publications by a specific researcher
Use the two-step pattern (entity name → ID → works):
from scripts.query_helpers import find_author_works
works = find_author_works(
author_name="Jennifer Doudna",
client=client,
limit=100
)Manual two-step approach:
# Step 1: Get author ID
author_response = client._make_request(
'/authors',
params={'search': 'Jennifer Doudna', 'per-page': 1}
)
author_id = author_response['results'][0]['id'].split('/')[-1]
# Step 2: Get works
works = client.search_works(
filter_params={"authorships.author.id": author_id}
)3. Find Works from Institution
Use for: Analyzing research output from universities or organizations
from scripts.query_helpers import find_institution_works
works = find_institution_works(
institution_name="Stanford University",
client=client,
limit=200
)4. Highly Cited Papers
Use for: Finding influential papers in a field
from scripts.query_helpers import find_highly_cited_recent_papers
papers = find_highly_cited_recent_papers(
topic="quantum computing",
years=">2020",
client=client,
limit=100
)5. Open Access Papers
Use for: Finding freely available research
from scripts.query_helpers import get_open_access_papers
papers = get_open_access_papers(
search_term="climate change",
client=client,
oa_status="any", # or "gold", "green", "hybrid", "bronze"
limit=200
)6. Publication Trends Analysis
Use for: Tracking research output over time
from scripts.query_helpers import get_publication_trends
trends = get_publication_trends(
search_term="artificial intelligence",
filter_params={"is_oa": "true"},
client=client
)
# Sort and display
for trend in sorted(trends, key=lambda x: x['key'])[-10:]:
print(f"{trend['key']}: {trend['count']} publications")7. Research Output Analysis
Use for: Comprehensive analysis of author or institution research
from scripts.query_helpers import analyze_research_output
analysis = analyze_research_output(
entity_type='institution', # or 'author'
entity_name='MIT',
client=client,
years='>2020'
)
print(f"Total works: {analysis['total_works']}")
print(f"Open access: {analysis['open_access_percentage']}%")
print(f"Top topics: {analysis['top_topics'][:5]}")8. Batch Lookups
Use for: Getting information for multiple DOIs, ORCIDs, or IDs efficiently
dois = [
"https://doi.org/10.1038/s41586-021-03819-2",
"https://doi.org/10.1126/science.abc1234",
# ... up to 50 DOIs
]
works = client.batch_lookup(
entity_type='works',
ids=dois,
id_field='doi'
)9. Random Sampling
Use for: Getting representative samples for analysis
# Small sample
works = client.sample_works(
sample_size=100,
seed=42, # For reproducibility
filter_params={"publication_year": "2023"}
)
# Large sample (>10k) - automatically handles multiple requests
works = client.sample_works(
sample_size=25000,
seed=42,
filter_params={"is_oa": "true"}
)10. Citation Analysis
Use for: Finding papers that cite a specific work
# Get the work
work = client.get_entity('works', 'https://doi.org/10.1038/s41586-021-03819-2')
# Get citing papers using cited_by_api_url
import requests
citing_response = requests.get(
work['cited_by_api_url'],
params={'mailto': client.email, 'per-page': 200}
)
citing_works = citing_response.json()['results']11. Topic and Subject Analysis
Use for: Understanding research focus areas
# Get top topics for an institution
topics = client.group_by(
entity_type='works',
group_field='topics.id',
filter_params={
"authorships.institutions.id": "I136199984", # MIT
"publication_year": ">2020"
}
)
for topic in topics[:10]:
print(f"{topic['key_display_name']}: {topic['count']} works")12. Large-Scale Data Extraction
Use for: Downloading large datasets for analysis
# Paginate through all results
all_papers = client.paginate_all(
endpoint='/works',
params={
'search': 'synthetic biology',
'filter': 'publication_year:2020-2024'
},
max_results=10000
)
# Export to CSV
import csv
with open('papers.csv', 'w', newline='', encoding='utf-8') as f:
writer = csv.writer(f)
writer.writerow(['Title', 'Year', 'Citations', 'DOI', 'OA Status'])
for paper in all_papers:
writer.writerow([
paper.get('title', 'N/A'),
paper.get('publication_year', 'N/A'),
paper.get('cited_by_count', 0),
paper.get('doi', 'N/A'),
paper.get('open_access', {}).get('oa_status', 'closed')
])Critical Best Practices
Always Use Email for Polite Pool
Add email to get 10x rate limit (1 req/sec → 10 req/sec):
client = OpenAlexClient(email="your-email@example.edu")Use Two-Step Pattern for Entity Lookups
Never filter by entity names directly - always get ID first:
# ✅ Correct
# 1. Search for entity → get ID
# 2. Filter by ID
# ❌ Wrong
# filter=author_name:Einstein # This doesn't work!Use Maximum Page Size
Always use per-page=200 for efficient data retrieval:
results = client.search_works(search="topic", per_page=200)Batch Multiple IDs
Use batch_lookup() for multiple IDs instead of individual requests:
# ✅ Correct - 1 request for 50 DOIs
works = client.batch_lookup('works', doi_list, 'doi')
# ❌ Wrong - 50 separate requests
for doi in doi_list:
work = client.get_entity('works', doi)Use Sample Parameter for Random Data
Use sample_works() with seed for reproducible random sampling:
# ✅ Correct
works = client.sample_works(sample_size=100, seed=42)
# ❌ Wrong - random page numbers bias results
# Using random page numbers doesn't give true random sampleSelect Only Needed Fields
Reduce response size by selecting specific fields:
results = client.search_works(
search="topic",
select=['id', 'title', 'publication_year', 'cited_by_count']
)Common Filter Patterns
Date Ranges
# Single year
filter_params={"publication_year": "2023"}
# After year
filter_params={"publication_year": ">2020"}
# Range
filter_params={"publication_year": "2020-2024"}Multiple Filters (AND)
# All conditions must match
filter_params={
"publication_year": ">2020",
"is_oa": "true",
"cited_by_count": ">100"
}Multiple Values (OR)
# Any institution matches
filter_params={
"authorships.institutions.id": "I136199984|I27837315" # MIT or Harvard
}Collaboration (AND within attribute)
# Papers with authors from BOTH institutions
filter_params={
"authorships.institutions.id": "I136199984+I27837315" # MIT AND Harvard
}Negation
# Exclude type
filter_params={
"type": "!paratext"
}Entity Types
OpenAlex provides these entity types:
- works - Scholarly documents (articles, books, datasets)
- authors - Researchers with disambiguated identities
- institutions - Universities and research organizations
- sources - Journals, repositories, conferences
- topics - Subject classifications
- publishers - Publishing organizations
- funders - Funding agencies
Access any entity type using consistent patterns:
client.search_works(...)
client.get_entity('authors', author_id)
client.group_by('works', 'topics.id', filter_params={...})External IDs
Use external identifiers directly:
# DOI for works
work = client.get_entity('works', 'https://doi.org/10.7717/peerj.4375')
# ORCID for authors
author = client.get_entity('authors', 'https://orcid.org/0000-0003-1613-5981')
# ROR for institutions
institution = client.get_entity('institutions', 'https://ror.org/02y3ad647')
# ISSN for sources
source = client.get_entity('sources', 'issn:0028-0836')Reference Documentation
Detailed API Reference
See references/api_guide.md for:
- Complete filter syntax
- All available endpoints
- Response structures
- Error handling
- Performance optimization
- Rate limiting details
Common Query Examples
See references/common_queries.md for:
- Complete working examples
- Real-world use cases
- Complex query patterns
- Data export workflows
- Multi-step analysis procedures
Scripts
openalex_client.py
Main API client with:
- Automatic rate limiting
- Exponential backoff retry logic
- Pagination support
- Batch operations
- Error handling
Use for direct API access with full control.
query_helpers.py
High-level helper functions for common operations:
find_author_works()- Get papers by authorfind_institution_works()- Get papers from institutionfind_highly_cited_recent_papers()- Get influential papersget_open_access_papers()- Find OA publicationsget_publication_trends()- Analyze trends over timeanalyze_research_output()- Comprehensive analysis
Use for common research queries with simplified interfaces.
Troubleshooting
Rate Limiting
If encountering 403 errors:
- Ensure email is added to requests
- Verify not exceeding 10 req/sec
- Client automatically implements exponential backoff
Empty Results
If searches return no results:
- Check filter syntax (see
references/api_guide.md) - Use two-step pattern for entity lookups (don't filter by names)
- Verify entity IDs are correct format
Timeout Errors
For large queries:
- Use pagination with
per-page=200 - Use
select=to limit returned fields - Break into smaller queries if needed
Rate Limits
- Default: 1 request/second, 100k requests/day
- Polite pool (with email): 10 requests/second, 100k requests/day
Always use polite pool for production workflows by providing email to client.
Notes
- No authentication required
- All data is open and free
- Rate limits apply globally, not per IP
- Use LitLLM with OpenRouter if LLM-based analysis is needed (don't use Perplexity API directly)
- Client handles pagination, retries, and rate limiting automatically
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

