extract-references

Extract structured bibliographic references from PDF files via GROBID.

10|Updated Jul 22, 2025
One-click install
npx skills add https://github.com/bdambrosio/Cognitive_workbench --skill extract-references-bdambrosio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: extract-references
Source: https://github.com/bdambrosio/Cognitive_workbench/tree/main/src/tools/extract-references
Command: npx skills add https://github.com/bdambrosio/Cognitive_workbench --skill extract-references-bdambrosio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the extraction of structured bibliographic information from PDF documents, saving researchers and academics significant time and effort in compiling reference lists.

Core Features & Use Cases

  • Automated Reference Extraction: Parses PDF files to identify and extract individual references.
  • Structured Data Output: Returns each reference as a structured Note, containing fields like title, authors, year, venue, and DOI.
  • Compatibility: Output Notes are designed to be compatible with citation formatting tools.
  • Use Case: When analyzing a research paper, use this Skill to automatically extract all cited references, which can then be formatted into a bibliography.

Quick Start

Use the extract-references skill to get the references from the PDF file located at /path/to/paper.pdf.

Frequently Asked Questions about extract-references

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract references from a PDF automatically?

To extract references from a PDF automatically, this Skill parses the document using the GROBID service to identify and structure individual citations into detailed metadata fields.

How does GROBID extract bibliographic data from academic papers?

GROBID extracts bibliographic data from academic papers by parsing the PDF structure to isolate individual references and returning them as structured Notes containing titles, authors, years, venues, and DOIs.

Do I need a GROBID service running to extract citations from PDFs?

Yes, you need a GROBID service integration to extract citations from PDFs, as the Skill relies on this external service to process the documents and return structured bibliographic references.

What metadata fields are included when extracting references from academic papers?

Extracting references from academic papers yields structured Notes containing detailed metadata fields such as title, authors, year, venue, and DOI for each individual citation.

Can I use the extracted references to automatically generate a bibliography?

You can use the extracted references to generate a bibliography because the output Notes are designed to be compatible with standard citation formatting tools for literature review workflows.

What is the best way to compile a reference list from multiple research papers?

The best way to compile a reference list from multiple research papers is to use this Skill to automate the extraction of structured bibliographic information from each PDF, saving significant manual effort.