Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/doi-resolution-guide
DOI content negotiation and metadata retrieval techniques
Passed 20 of 21 test cases with the skill, and 18 of 21 without it.
2 fixed19 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
When inspecting work metadata returned from the CrossRef API message object, where is the license URL located in the JSON structure?
| Checked | Without skill | With skill |
|---|---|---|
| Extracts the URL from the first object inside the license array list | Missed | Passed |
The instructions your model reads when the skill loads.
Master DOI content negotiation to programmatically retrieve structured metadata, citation data, and formatted references from any Digital Object Identifier.
Every DOI (e.g., 10.1038/s41586-021-03819-2) resolves to a landing page by default. However, the DOI system supports HTTP content negotiation: by sending different Accept headers, you can retrieve structured metadata in various formats instead of an HTML page.
The DOI resolver endpoint is https://doi.org/{doi} or equivalently https://dx.doi.org/{doi}.
| Accept Header | Format | Use Case |
|---|---|---|
application/vnd.citationstyles.csl+json | CSL-JSON | Programmatic metadata extraction |
text/x-bibliography; style=apa | Formatted citation | Ready-to-paste APA reference |
text/x-bibliography; style=bibtex | BibTeX | LaTeX bibliography import |
application/x-bibtex | BibTeX (alt) | LaTeX bibliography import |
application/rdf+xml | RDF/XML | Linked data applications |
text/turtle | Turtle RDF | Linked data applications |
application/vnd.crossref.unixref+xml | CrossRef Unixref | Full CrossRef metadata |
curl -LH "Accept: application/vnd.citationstyles.csl+json" \
https://doi.org/10.1038/s41586-021-03819-2
import requests
doi = "10.1038/s41586-021-03819-2"
headers = {"Accept": "application/vnd.citationstyles.csl+json"}
response = requests.get(f"https://doi.org/{doi}", headers=headers, allow_redirects=True)
metadata = response.json()
print(f"Title: {metadata['title']}")
test cases passed, vs 18 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.