
Bib Search Citation
If you've ever stared at a 2,000-entry Zotero export trying to remember which paper had that Mamba forecasting code, this is for you. It's a research-oriented search tool for local BibTeX files that understands compact filters like `author:Cheng year>=2024 has:code` and returns JSON results with citation snippets for both LaTeX and Typst. The workflow is clean: point it at your .bib file, describe what you need, and it handles the scoring and filtering without fabricating metadata. It won't write your related work section or validate citations in a manuscript, but for digging through large bibliography libraries with mixed Zotero fields like annotations and keywords, it beats grep by a mile.
- skills.sh installs
- 1.8K
- GitHub stars
- 543
- last updated
- Aug 21, 2026
Install
$ npx -y skills add bahayonghang/academic-writing-skills --skill bib-search-citation --agent claude-codeInstalls into .claude/skills of the current project.
Files
Bib Search Citation
Capability Summary
Research-oriented retrieval over a local .bib file (BibTeX/BibLaTeX, including
Zotero exports with fields like shorttitle, annotation, keywords,
abstract, file, DOI, URL, eprint). Searches by topic and field filters,
returns stable JSON, renders compact previews, emits LaTeX/Typst citation
snippets, and returns raw BibTeX only when exact export or manual verification
requires it.
Triggering
Requests such as: "Search my .bib file for recent Mamba forecasting papers",
"Find entries by Cheng after 2024 that have code and return cite snippets",
"Show the raw BibTeX for the best match", "Filter Zotero-exported entries whose
annotation mentions CodeAvailable", "Preview the JSON output from a saved
search". For a natural-language request, infer a conservative search spec and
state the assumptions. If the user gives a compact filter expression, preserve
it closely instead of translating it into vague prose.
Do Not Use
Sponsors
Details
- Repository
- github.com/bahayonghang/academic-writing-skills
- Categories
- Documentation, Skill Development, Data Science & ML
- First seen
- Jun 3, 2026