extract-struct

Extract title, authors, year, venue, and abstract from academic paper text into JSON.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the extraction of key metadata from academic paper text, saving researchers and students the time and effort of manually identifying and recording titles, authors, publication years, and venues.

Core Features & Use Cases

  • Structured Metadata Extraction: Leverages LLM analysis to identify and extract title, authors, year, venue, and abstract from paper text.
  • Input Flexibility: Accepts a Note ID or variable containing the full text or initial pages of a paper.
  • Use Case: After using a tool to download the full text of a research paper, this Skill can automatically parse it to populate a structured database entry with all essential bibliographic information.

Quick Start

Use the extract-struct skill to get the metadata from the paper text stored in the variable paper_text.

Frequently Asked Questions about extract-struct

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

FAQPage Schema
How do I extract structured metadata from academic paper text?

To extract structured metadata from academic paper text, this Skill parses unstructured text using LLM analysis to identify and output the title, authors, year, venue, and abstract into a defined JSON schema.

Can I automatically parse research paper abstracts and authors from full text?

Yes, you can automatically parse research paper abstracts and authors by providing a Note ID or variable containing the full text, which the LLM analysis then processes to catalog the scholarly article.

What is the best way to catalog scholarly articles for a research database?

The best way to catalog scholarly articles for a research database is to use LLM analysis to extract bibliographic information like title, authors, year, and venue, populating a structured JSON schema automatically.

Does metadata extraction require a specific file format or input type?

Metadata extraction does not require a specific file format, but accepts a Note ID or a variable containing the full text or initial pages of the academic paper to process the unstructured text.

How does LLM analysis handle unstructured text to identify publication years and venues?

LLM analysis handles unstructured text to identify publication years and venues by parsing the provided paper text and mapping the extracted bibliographic information into a defined JSON schema.

What limitations exist when extracting abstracts from initial paper pages?

A key limitation when extracting abstracts from initial paper pages is that the LLM analysis relies entirely on the provided text input; if the text lacks explicit venue or author details, the JSON schema output will be incomplete.