Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/wikidata-api-guide
Query Wikidata SPARQL for scholarly metadata, authors, and entities
Passed 22 of 23 test cases with the skill, and 19 of 23 without it.
and 1 more in the full report
3 fixed19 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need a SPARQL query and cURL command to retrieve academic publications and their associated DOIs for a researcher identified by their ORCID '0000-0002-1825-0097'. Please output the query so it retrieves the paper entity, its English title, and the DOI, along with an HTTP request snippet ready to run against the Wikidata SPARQL endpoint.
| Checked | Without skill | With skill |
|---|---|---|
| Uses property wdt:P496 for filtering by ORCID iD. | Passed | Passed |
| Includes a LIMIT clause in the SPARQL query. | Missed | Passed |
| Includes SERVICE wikibase:label for entity label resolution. | Missed | Passed |
The instructions your model reads when the skill loads.
Wikidata is a free, collaborative, multilingual knowledge base maintained by the Wikimedia Foundation. It contains structured data about millions of entities including scholarly articles, academic journals, researchers, universities, and scientific concepts. Each entity has a unique QID and properties linking it to other entities, forming a rich knowledge graph.
For academic researchers, Wikidata serves as a powerful tool for bibliometric analysis, disambiguation of author names, mapping institutional relationships, and linking scholarly outputs across different identifier systems (DOI, ORCID, PubMed ID, arXiv ID, etc.). The SPARQL query service provides a flexible, standards-based interface for complex graph queries.
The Wikidata Query Service is entirely free, requires no authentication, and supports the full SPARQL 1.1 query language. It is especially powerful for cross-referencing scholarly metadata that spans multiple databases and identifier systems.
No authentication is required. The Wikidata SPARQL endpoint is free and open.
# No API key needed -- set a descriptive User-Agent header as courtesy
curl -G "https://query.wikidata.org/sparql" \
--data-urlencode "query=SELECT ?item WHERE { ?item wdt:P31 wd:Q5 } LIMIT 5" \
-H "Accept: application/json" \
-H "User-Agent: ResearchClaw/1.0 (academic research tool)"
GET https://query.wikidata.org/sparql?query={SPARQL}&format=json
Parameters:
query (required): URL-encoded SPARQL queryformat: Response format (json, xml, csv, tsv)curl -G "https://query.wikidata.org/sparql" \
--data-urlencode 'query=
SELECT ?paper ?paperLabel ?doi WHERE {
test cases passed, vs 19 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.