Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/citation-management
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Passed 16 of 19 test cases with the skill, and 11 of 19 without it.
and 3 more in the full report
5 fixed13 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Here is our current references.bib: @article{Vaswani2017, author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki}, title = {Attention Is All You Need}, year = {2017}, journal = {Advances in Neural Information Processing Systems}, volume = {30}, pages = {5998--6008} } Please add this paper to references.bib: Title "Attention Is All You Need", Author "Vaswani, Ashish and Shazeer, Noam", Year 2017. Many researchers use 'Vaswani2017_NIPS' as the key.
| Checked | Without skill | With skill |
|---|---|---|
| The response identifies the incoming paper as a duplicate of Vaswani2017. | Missed | Passed |
| The response refrains from adding a duplicate entry to references.bib. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill manages the project's references.bib directly, using the CrossRef API to resolve DOIs into complete BibTeX entries. It does not require Zotero, any external CLI, or any desktop application. Everything happens through standard tools: curl (or equivalent HTTP client) and text editing of the .bib file.
Resolve every DOI via CrossRef. Call https://api.crossref.org/works/{doi}. Extract: title, full author list, year, journal, volume, issue, pages, publisher, and DOI. Do not invent fields missing from the API response — leave them out instead.
Generate a BibTeX entry with complete fields. Required for articles: author, title, year, journal, volume, pages, doi. For books: author (or editor), title, year, publisher, doi. For chapters: add booktitle and editor.
Citation key format: FirstAuthorLastnameYear, e.g., Santos2024. Disambiguate collisions with lowercase letters: Santos2024a, Santos2024b. Strip accents and non-ASCII characters from the key — BibTeX tooling does not always handle Unicode in keys.
Check for duplicates before adding. Duplicate definition: same DOI, OR same title (case-insensitive, normalized whitespace) AND same first author AND same year. If duplicate, skip and report the existing key.
Keep references.bib sorted alphabetically by citation key. Sort after every insert so the file stays stable across commits.
Preserve existing entries. Do not rewrite fields of existing entries unless the user explicitly asks. Append new entries in the correct sorted position.
curl -s 'https://api.crossref.org/works/10.1257/aer.84.4.772' \
| jq '.message | {title, author, issued, container-title, volume, page, DOI}'
The response provides all fields needed to build a complete BibTeX entry. Parse the author array to extract each author's given and family name, then format as Family, Given and Family2, Given2.
test cases passed, vs 11 / 19 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.