reference-manager-interop

Name: reference-manager-interop
Author: kalarislabs

github.com/kalarislabsDocuments7355 installsUpdated 3d ago

About reference-manager-interop

reference-manager-interop is a research skill for exchanging citation libraries across reference managers and writing tools. It converts BibTeX/BibLaTeX, RIS, and CSL-JSON files and includes migration and citation-rendering guidance.

Key features

01Convert BibTeX, RIS, and CSL-JSON files
02Guidance for reference manager exports and imports
03Migration checks for counts and citation fields
04CSL citation rendering with Pandoc or Quarto

Use cases

01Moving references from Mendeley or EndNote to another tool
02Converting BibTeX libraries for Pandoc or Quarto
03Checking a reference library after format conversion
04Rendering citations in a target CSL style

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kalarislabs/research-agent-skills --skill reference-manager-interop

After installing, type/reference-manager-interopin Claude Code to confirm it loaded.

Bundled filesscripts/convert_refs.py

Details

From the project README

Reference Manager Interoperability

Every reference manager speaks at least one of three interchange formats:

Format	Best for	Notes
BibTeX / BibLaTeX (`.bib`)	LaTeX, Overleaf, JabRef	BibLaTeX adds `@online`, `@dataset`, `@software`, UTF-8 via biber
RIS (`.ris`)	EndNote, Mendeley, Scopus/WoS/PubMed exports	Tag-per-line, loses some structure (e.g. corporate authors)
CSL-JSON (`.json`)	Pandoc, Quarto, Zotero, citeproc-js, Word/Docs plugins	The richest interchange format, native to citation styles

Convert between formats

python scripts/convert_refs.py library.ris references.bib        # EndNote/Mendeley -> LaTeX
python scripts/convert_refs.py references.bib references.json    # LaTeX -> Pandoc/Quarto
python scripts/convert_refs.py export.json out.ris --from csljson --to ris

Conversion is lossy for exotic fields. Always diff counts (grep -c "^@" refs.bib, grep -c "^TY -" lib.ris) and spot-check authors with particles (van, de, von) and corporate authors. Then run the bibtex-hygiene linter on any produced .bib.

Tool-specific recipes

Zotero (recommended hub)

Install the Better BibTeX plugin, then right-click a collection → Export → Keep updated to write an auto-refreshing .bib next to the manuscript with stable citation keys.
Programmatic access: the pyzotero skill (Zotero Web API; needs a user API key).
Word/Google Docs: the Zotero connector plugins insert live citations and bibliography.

Mendeley Reference Manager

Export: select references → Export → BibTeX (.bib), RIS or EndNote XML.
To migrate to Zotero: import the .ris/.bib export, or use Zotero's built-in Mendeley importer.
Don't build new automation against Mendeley's web API. Work from exported files instead.

EndNote

Export: File → Export with output style "RefMan (RIS) Export" (.ris) or XML.
Import .ris back with the "Reference Manager (RIS)" filter. Check the encoding is UTF-8.

JabRef: native BibTeX/BibLaTeX. Use Quality → Cleanup entries and Check integrity before submission.

Overleaf: link a Zotero/Mendeley account or upload the .bib. With an auto-exported Better BibTeX file, re-upload it or sync via Git.

Rendering citations with CSL styles (Pandoc / Quarto)

pandoc paper.md --citeproc --bibliography references.json --csl nature.csl -o paper.docx

Quarto front matter:

bibliography: references.json
csl: apa.csl          # fetch from https://github.com/citation-style-language/styles

Pick the exact style file for the target journal from the CSL repository (over 10,000 styles). Never approximate a journal's style by editing a similar one unless none exists.

Migration checklist

Export from the source tool in its richest format (CSL-JSON or native XML > RIS > BibTeX).
Record the reference count before and after.
Convert with scripts/convert_refs.py if the target cannot import the source format.
Import, then check 10 random entries for authors, title case, container, year, DOI.
Re-attach PDFs separately. Attachments never travel inside RIS/BibTeX/CSL-JSON.
Rebuild citation keys only if the manuscript does not already cite the old keys.

Related skills

bibtex-hygiene, citation-verification, citation-management, pyzotero.

Comments

Markdown supported

Details

Author: kalarislabs
Repository: kalarislabs/research-agent-skills
Category: Documents
Installs: 55
GitHub stars: 73

Report

More skills

All skills

handoff

github.com/mattpocock

1.1M

Compact the current conversation into a handoff document for another agent to pick up

lark-doc

open.feishu.cn

823.9k

Operate on Feishu cloud documents (Docx / Wiki): read, create, and edit documents; insert or download image attachments; and work with mind notes. Use when the user provides a document URL/token (including /docx/ or /wiki/ on doubao.com); route by URL path/token rather than domain. `/page/<token>` is a Miaoda app, not a Feishu cloud document. Route embedded document resources according to the unified rules in the reading reference. Use lark-drive for standalone comment operations; use docs +fetch to read comments alongside the main text. Operations on spreadsheet or Base internal data are outside this skill.

lark-drive

open.feishu.cn

823.2k

Feishu cloud storage (Drive): manage Drive files and folders, including uploads/downloads, folder creation, copying/moving/deleting, viewing metadata, checking permission settings, comments/permissions/subscriptions, titles, versions, Feishu document security labels (secure labels), and local file imports. Use when users need to organize Drive folders, handle cloud storage resource URLs/tokens, identify link types/actual tokens/titles, or import Word/Markdown/Excel/CSV/PPTX/.base as docx/sheet/bitable/slides. Route doubao.com cloud storage URLs/tokens by resource path and token too; do not fall back to WebFetch. Not responsible for: editing document content (use lark-doc), spreadsheet/Base table data operations (use lark-sheets/lark-base), knowledge space node/member management (use lark-wiki), or native Markdown file read/write/patch/diff (use lark-markdown).

lark-sheets

open.feishu.cn

821.8k

Feishu Spreadsheets: create and operate spreadsheets. Supports worksheets and row/column structures (add/delete/merge/size/hide/freeze/group), cell read/write (values/formulas/styles/comments/cell images), range copy/move/sort/fill, find and replace, bulk updates, and creating and maintaining objects such as charts, pivot tables, conditional formatting, filters and filter views, dropdown lists, sparklines, and floating images. Also supports formula validation, restoring historical versions, and importing/exporting local Excel/CSV files and Feishu spreadsheets. Use when users need to create or edit spreadsheets, summarize and visualize data, format spreadsheets, calculate formulas (including migrating Excel formulas), or build financial models (DCF, three statements, budgets, Sensitivity, etc.). For multidimensional tables (Base/bitable), use lark-base. If users want to search for spreadsheet files in cloud storage (Drive/cloud storage) by name or keyword, use lark-drive's drive +search to locate resources first. When users provide a doubao.com /sheets/ URL/token, use this skill directly; do not fall back to WebFetch because the domain is not Feishu. Routing is based on the URL path pattern and token, not the domain.