Searching Scientific Literature

Search PubMed and extract paper metadata into structured JSON.

118|12|Updated Oct 11, 2025
One-click install
npx skills add https://github.com/kthorn/research-superpower --skill searching-scientific-literature
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Searching Scientific Literature
Source: https://github.com/kthorn/research-superpower/tree/main/skills/research/searching-literature
Command: npx skills add https://github.com/kthorn/research-superpower --skill searching-scientific-literature

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solves? Manually crafting effective PubMed queries and parsing results can be time-consuming and requires expertise in search operators. This skill automates the process of searching scientific literature, optimizing keywords, and extracting key metadata, so you get relevant results quickly.

Core Features & Use Cases

  • Intelligent Query Construction: Parses user queries for keywords, data types, and constraints to build precise PubMed queries.
  • Automated Search Execution: Executes searches via the PubMed E-utilities API, handling rate limits and result parsing.
  • Metadata Extraction: Extracts essential paper details like title, authors, journal, publication date, abstract, PMID, and DOI.
  • Use Case: Instead of manually building complex PubMed queries, simply tell Claude, "Find recent papers on CRISPR gene editing in cardiomyocytes." This skill will automatically construct an optimized query, execute it, and return a structured list of relevant papers, ready for further evaluation.

Quick Start

Example: Search PubMed for specific research

"Search PubMed for papers on 'CRISPR gene editing in cardiomyocytes'."

Frequently Asked Questions about Searching Scientific Literature

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

FAQPage Schema
How do I search PubMed for scientific papers without building complex queries manually?

PubMed search automation parses your natural language request into optimized Boolean queries with field tags, executes the search via E-utilities API, and returns structured metadata including title, authors, journal, abstract, PMID, and DOI—eliminating manual query syntax work.

Can I extract metadata like DOI and PMID when searching for scientific literature?

Yes, automated literature search retrieves and structures essential metadata: title, authors, journal, publication date, abstract, PMID, and DOI for each result, ready for further analysis or export.

What's the best way to find papers across multiple research domains like methods, compounds, and diseases?

Query optimization with synonym handling and Boolean construction targets papers across methods, compounds, diseases, and techniques in a single search, returning relevant results without crafting separate queries for each domain.

How does literature search handle rate limits and errors when querying PubMed?

Built-in rate-limit and error handling ensures reliable API operation, preventing failures during large searches and managing E-utilities request throttling automatically.

Can I use this for building an initial paper set on a specific research topic quickly?

Yes, automated query parsing and execution constructs precise searches for specific topics—like 'CRISPR gene editing in cardiomyocytes'—and builds an initial structured paper set in minutes rather than hours of manual searching.