Bibtex Hygiene logo

Bibtex Hygiene

Organization
KalarisLabs
bibtex-hygiene

Clean, deduplicate and validate BibTeX/BibLaTeX bibliographies before submission. Use when a .bib file has duplicate keys or works, missing fields, broken DOIs, lost acronym capitalization (e.g. "bert" instead of "BERT"), inconsistent page dashes, arXiv preprints that now have published versions, or when LaTeX/biber emits bibliography warnings. Includes a zero-dependency linter and normalizer.

Overview

PublisherKalarisLabs
Repositoryresearch-agent-skills
Skill namebibtex-hygiene
Stars
91
Forks
8
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by KalarisLabs on GitHub. Read the source before you install it.

Installation

Install the Bibtex Hygiene AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/KalarisLabs/research-agent-skills/tree/main/skills/bibtex-hygiene
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/KalarisLabs/research-agent-skills.git /tmp/research-agent-skills
mkdir -p .claude/skills
cp -r /tmp/research-agent-skills/skills/bibtex-hygiene .claude/skills/bibtex-hygiene
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bibtex Hygiene in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bibtex Hygiene on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bibtex Hygiene is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

BibTeX Hygiene

A clean bibliography is a correctness issue, not cosmetics: duplicate entries inflate reference counts, missing fields render as "?" in the PDF, lowercase acronyms signal carelessness to reviewers, and a wrong DOI sends readers to someone else's paper.

Workflow

  1. Lint. Run the bundled linter on every .bib the manuscript uses:

    bash
    python scripts/bib_lint.py references.bib
    python scripts/bib_lint.py references.bib --json > bib-report.json   # for programmatic triage

    Exit code 0 clean, 1 findings, 2 unparseable input.

  2. Fix errors first, in this order:

    • duplicate-key: two entries share a key, so LaTeX silently uses the first. Rename one and update \cite{} calls (grep -rn "\\cite.*{oldkey" *.tex).
    • duplicate-work: the same paper under two keys (same DOI or title). Keep one, repoint citations.
    • missing-field: add the field from the publisher page or Crossref, never from memory.
    • doi-format / year-format / author-format: correct from the authoritative record.
  3. Then warnings:

    • title-case: wrap acronyms, proper nouns and chemical/gene symbols in braces: title = {{BERT}: Pre-training of Deep Bidirectional Transformers}, {Bayesian}, {CRISPR}-{Cas9}, {\textit{E. coli}}. Brace the word, not the whole title. Whole-title braces defeat sentence-case styles.
    • doi-url: store bare DOIs (10.1038/s41586-021-03819-2). Styles add the resolver.
    • author-others: list every author when there are fewer than three.
  4. Resolve preprints. For every preprint note, check whether a peer-reviewed version exists (search the title on Crossref/OpenAlex or use the citation-verification skill). Cite the published version and keep the arXiv ID in eprint if the venue allows.

  5. Normalize (optional, safe mechanical fixes only: bare DOIs, -- page ranges, consistent field order):

    bash
    python scripts/bib_lint.py references.bib --fix references.clean.bib
    diff references.bib references.clean.bib   # review before replacing
  6. Verify the build. Compile and read the log: grep -i "warning.*citation\|undefined" main.log. Every \cite must resolve and no entry should render with ??.

Conventions worth enforcing

TopicRule
KeysauthorYEARword, lowercase ASCII, e.g. vaswani2017attention. Never reuse a key for a different work
AuthorsLast, First and Last, First. Corporate authors in double braces: {{World Health Organization}}
VenuesOne spelling per venue across the file (pick full name or ISO4 abbreviation per the journal's style)
Conference papers@inproceedings with booktitle, not @article with journal
Software/data@software / @dataset (BibLaTeX) or @misc with version, doi/url, year
UnicodeKeep UTF-8 with biber; for classic BibTeX escape accents ({\"u})
URLs + DOIIf a DOI exists, drop the publisher URL; keep url only for web-only sources (+ urldate)

Anti-patterns

  • Generating BibTeX from memory or from an LLM. Always export from the publisher, Crossref (https://api.crossref.org/works/{doi}/transform/application/x-bibtex), DBLP or a reference manager.
  • Copying Google Scholar BibTeX blindly: it often lacks DOIs, uses wrong entry types and mangles capitalization.
  • Wrapping the whole title in double braces to "fix" capitalization.
  • Leaving note = {Accessed ...} on DOI-bearing articles.

Related skills

  • citation-verification: checks that every entry matches a real record (catches hallucinated references).
  • reference-manager-interop: converts between Zotero/Mendeley/EndNote exports, RIS, CSL-JSON and BibTeX.
  • citation-management: search and retrieve references from literature databases.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bibtex Hygiene AI skill do?

Clean, deduplicate and validate BibTeX/BibLaTeX bibliographies before submission. Use when a .bib file has duplicate keys or works, missing fields, broken DOIs, lost acronym capitalization (e.g. "bert" instead of "BERT"), inconsistent page dashes, arXiv preprints that now have published versions, or when LaTeX/biber emits bibliography warnings. Includes a zero-dependency linter and normalizer.

Why use Bibtex Hygiene on TypingMind?

Because you install it once and use it with any model. Bibtex Hygiene is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bibtex Hygiene in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KalarisLabs/research-agent-skills/tree/main/skills/bibtex-hygiene. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bibtex Hygiene?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bibtex Hygiene?

As many as you like. As long as a model supports skills, you can use Bibtex Hygiene with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bibtex Hygiene AI skill free?

Yes. It is published on GitHub by KalarisLabs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇