Literature Parsing Skill

Name: Literature Parsing Skill
Availability: InStock
Author: TianGzlab

Parse scientific literature to extract GEO dataset metadata and download associated data.

155|26|Updated Mar 14, 2026

Search Tags:#bioinformatics #scientific papers #omics #literature #data download #geo

Ready to run

npx skills add https://github.com/TianGzlab/OmicsClaw --skill literature-parsing-skill

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Literature Parsing Skill
Source: https://github.com/TianGzlab/OmicsClaw/tree/main/skills/literature
Command: npx skills add https://github.com/TianGzlab/OmicsClaw --skill literature-parsing-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, requests, beautifulsoup4, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of finding and downloading omics datasets mentioned in scientific literature, streamlining the initial steps of bioinformatics research.

Core Features & Use Cases

Input Flexibility: Accepts URLs, DOIs, PubMed IDs, local PDFs, or raw text as input.
Metadata Extraction: Identifies and extracts key information like GEO accessions (GSE, GSM), organism, tissue, and technology.
Automated Download: Downloads relevant datasets from GEO based on extracted accessions.
Use Case: You find a promising new paper on bioRxiv. Paste the URL into OmicsClaw, and it will automatically extract the GEO accession number, download the associated data, and prepare it for analysis.

Quick Start

Use the literature skill to parse the URL https://pubmed.ncbi.nlm.nih.gov/12345.

Frequently Asked Questions about Literature Parsing Skill

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

FAQPage Schema

How do I extract GEO accessions from scientific papers automatically?▼

You can extract GEO datasets from bioinformatics literature by inputting a URL, DOI, PubMed ID, or PDF. The Skill parses the text to identify GEO accessions like GSE and GSM, then retrieves associated expression matrices and metadata.

Can I parse a PubMed ID to download omics datasets?▼

Yes, you can use a PubMed ID to download omics datasets. The Skill accepts PubMed IDs as valid input, extracts the referenced GEO accessions, and automatically downloads the associated expression matrices and related files.

What metadata is extracted when parsing literature for GEO data?▼

When parsing literature for GEO data, the extracted metadata includes GEO accessions like GSE and GSM, along with organism, tissue, and technology. This information is identified directly from the input text to prepare the data for bioinformatics analysis.

Does the literature parsing tool support local PDF files as input?▼

Yes, the literature parsing tool supports local PDF files as input. It processes the document to extract omics dataset metadata such as GEO accessions, organism, tissue, and technology directly from the PDF content.

What is the best way to download expression matrices mentioned in a bioRxiv URL?▼

To download expression matrices from a bioRxiv URL, paste the URL as input. The Skill parses the page content to find GEO accession numbers and automatically retrieves the associated expression matrices and related dataset files.