openalex

Query the OpenAlex catalog to enrich bibliographic metadata, recover abstracts, and traverse citations.

1|Updated Jul 13, 2026
One-click install
npx skills add https://github.com/thurlow-research/ResearchClaudeCodeSkills --skill openalex-thurlow-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openalex
Source: https://github.com/thurlow-research/ResearchClaudeCodeSkills/tree/main/desktop/skills/openalex
Command: npx skills add https://github.com/thurlow-research/ResearchClaudeCodeSkills --skill openalex-thurlow-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Imported or snowballed reference records often arrive with missing authors, DOIs, venues, URLs, or abstracts, and fixing them by hand across hundreds of papers is impractical. This Skill queries the OpenAlex open scholarly catalog (~250M works) to backfill and normalize bibliographic records at scale, with on-disk caching so repeated lookups are free. ## Core Features & Use Cases - Metadata enrichment: Normalize works by DOI, arXiv id, OpenAlex id, PMID, or title into clean records with authors, venue, date, type, URL, and citation counts via the enrich command. - Abstract recovery: Reconstruct readable abstracts from OpenAlex's inverted-index format, covering preprints and works where other sources have no abstract. - Citation traversal: List works that cite a paper (forward) or the works it references (backward) for snowballing searches. - Use Case: Pipe a list of DOIs from thin Zotero or Semantic Scholar records into enrich, receive normalized JSON records, and PATCH the missing fields back into your reference library. ## Quick Start Ask Claude to backfill missing authors, DOIs, and abstracts for the DOIs in your reference list using OpenAlex.

Frequently Asked Questions about openalex

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I backfill missing metadata for a list of DOIs?

Pipe the DOIs, one per line, into the enrich command: printf '10.1145/3610721\n' | python3 scripts/openalex.py enrich. It outputs a JSON list of normalized records with authors, DOI, venue, URL, date, and abstract that you can patch into your reference manager.

Does the OpenAlex API require an API key?

OpenAlex works without a key but is credit-metered, so anonymous use is throttled to roughly 100 requests per day. A free account key from openalex.org/settings/api raises the quota about 10x, and adding your email via OPENALEX_MAILTO joins the polite pool.

OpenAlex vs Semantic Scholar for metadata enrichment?

OpenAlex generally has broader abstract, DOI, and venue coverage and works key-less, making it better for metadata backfill. Semantic Scholar offers richer citation-influence signals and TLDRs, so it suits influential-citation snowballing instead.

Why am I getting HTTP 429 errors from OpenAlex?

HTTP 429 means the credit-based rate limit is exhausted; the script reads the reset headers and reports when the quota renews instead of hanging. Register a free API key, set OPENALEX_MAILTO, and rely on the disk cache to avoid repeat requests.

Can I recover an abstract for an arXiv preprint?

Yes, pass the identifier as ARXIV:<id>, for example python3 scripts/openalex.py abstract ARXIV:2107.03374. The tool resolves it through the arXiv DOI and reconstructs readable text from OpenAlex's abstract inverted index, returning an empty string if none exists.

What Python packages does the OpenAlex CLI need?

None beyond the standard library. The script uses only urllib, json, hashlib, and argparse, so it runs on any Python 3.9+ installation without pip installs, and responses are cached under ~/.cache/claude-openalex.