How do I install the PDF To Bibtex skill?

Run npx skillmds@latest add jabref/pdf-to-bibtex in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is PDF To Bibtex safe to use?

SkillMD's automated safety review verdict for this skill is WARNING. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with PDF To Bibtex?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is PDF To Bibtex free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published PDF To Bibtex?

jabref (@jabref) published this skill. Their other Agent Skills are listed on their SkillMD profile.

PDF To Bibtex by jabref — Agent Skill

Name: PDF To Bibtex
Author: jabref

PDF To Bibtex

Turns a PDF paper into a BibTeX entry describing that paper, using JabRef's jabkit CLI - merges XMP, embedded BibTeX, GROBID, and text heuristics, then enriches the result via DOI/arXiv/ISBN lookup; builds a bibliography from a whole folder of papers. Not for extracting the reference list cited by a paper.

jabref 974a9ff 3.0 KB Updated Sep 17, 2026

File contents

PDF to BibTeX

Produce a BibTeX entry describing a PDF paper (its own title, authors, year, ...) using jabkit, JabRef's command-line toolkit.

This skill is about metadata of the PDF. Extracting the entries a paper cites (its "References" section) is a different task, not covered by this skill.

Setup

jabkit runs via JBang — no JDK setup needed. Install JBang if missing:

curl -Ls https://sh.jbang.dev | bash -s - app setup   # Linux/macOS

iex "& { $(iwr -useb https://ps.jbang.dev) } app setup"   # Windows

Then install jabkit on the PATH (the same command also updates it):

jbang app install --fresh --force jabkit@jabref

One-off run without installation:

jbang --fresh jabkit@jabref --help

Basic usage

jabkit convert --input paper.pdf --input-format pdfMerged --output paper.bib

Omit --output to print BibTeX to stdout. Add --porcelain before the subcommand for script-friendly output:

jabkit -p convert --input paper.pdf --input-format pdfMerged

PDF importer formats

Pass one of these as --input-format:

Format id	Strategy
`pdfMerged`	Merges results of the other importers into one best-effort entry — use this by default
`pdfXmp`	Reads XMP metadata stored in the PDF
`pdfEmbeddedBibFile`	Reads a BibTeX file embedded as PDF attachment
`pdfVerbatimBibtex`	Parses BibTeX printed verbatim on the first page
`pdfContent`	Heuristic extraction from the text of the first page
`pdfGrobid`	Sends the PDF to a GROBID service (requires GROBID to be enabled/reachable)

--input-format "*" auto-detects the format (also works for non-PDF inputs).

Recommended workflow

Run with pdfMerged first. Besides merging the other importers' results, it looks up any DOI, arXiv eprint, or ISBN found in the PDF online and merges the fetched metadata into the entry — no separate DOI lookup is needed.
Validate the resulting library:
```
jabkit check paper.bib
```

Batch conversion

for f in papers/*.pdf; do
  jabkit -p convert --input "$f" --input-format pdfMerged >> library.bib
done

Afterwards generate citation keys for all entries:

jabkit citationkeys generate library.bib --output library.bib

Extract the works a paper cites (its "References" section): the pdf-extract-references skill.
Write metadata back into PDFs (reverse direction): jabkit pdf update --citation-key <key> --input library.bib --input-format bibtex
Full CLI reference: the jabkit skill in this repository.

---name: pdf-to-bibtexdescription: Turns a PDF paper into a BibTeX entry describing that paper, using JabRef's jabkit CLI - merges XMP, embedded BibTeX, GROBID, and text heuristics, then enriches the result via DOI/arXiv/ISBN lookup; builds a bibliography from a whole folder of papers. Not for extracting the reference list cited by a paper.license: MIT---# PDF to BibTeXProduce a BibTeX entry describing a PDF paper (its own title, authors, year, ...) using `jabkit`, JabRef's command-line toolkit.This skill is about metadata *of* the PDF. Extracting the entries a paper *cites* (its "References" section) is a different task, not covered by this skill.## Setup`jabkit` runs via [JBang](https://www.jbang.dev/) — no JDK setup needed. Install JBang if missing:```bashcurl -Ls https://sh.jbang.dev | bash -s - app setup # Linux/macOS``````powershelliex "& { $(iwr -useb https://ps.jbang.dev) } app setup" # Windows```Then install `jabkit` on the PATH (the same command also updates it):```bashjbang app install --fresh --force jabkit@jabref```One-off run without installation:```bashjbang --fresh jabkit@jabref --help```## Basic usage```bashjabkit convert --input paper.pdf --input-format pdfMerged --output paper.bib```Omit `--output` to print BibTeX to stdout. Add `--porcelain` before the subcommand for script-friendly output:```bashjabkit -p convert --input paper.pdf --input-format pdfMerged```## PDF importer formatsPass one of these as `--input-format`:| Format id | Strategy ||---|---|| `pdfMerged` | Merges results of the other importers into one best-effort entry — **use this by default** || `pdfXmp` | Reads XMP metadata stored in the PDF || `pdfEmbeddedBibFile` | Reads a BibTeX file embedded as PDF attachment || `pdfVerbatimBibtex` | Parses BibTeX printed verbatim on the first page || `pdfContent` | Heuristic extraction from the text of the first page || `pdfGrobid` | Sends the PDF to a [GROBID](https://github.com/kermitt2/grobid) service (requires GROBID to be enabled/reachable) |`--input-format "*"` auto-detects the format (also works for non-PDF inputs).## Recommended workflow1. Run with `pdfMerged` first. Besides merging the other importers' results, it looks up any DOI, arXiv eprint, or ISBN found in the PDF online and merges the fetched metadata into the entry — no separate DOI lookup is needed.2. Validate the resulting library: ```bash jabkit check paper.bib ```## Batch conversion```bashfor f in papers/*.pdf; do jabkit -p convert --input "$f" --input-format pdfMerged >> library.bibdone```Afterwards generate citation keys for all entries:```bashjabkit citationkeys generate library.bib --output library.bib```## Related- Extract the works a paper *cites* (its "References" section): the `pdf-extract-references` skill.- Write metadata back into PDFs (reverse direction): `jabkit pdf update --citation-key <key> --input library.bib --input-format bibtex`- Full CLI reference: the `jabkit` skill in this repository.

Frequently asked questions