pubmed-database

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.

Install

Hot:8

Download and extract to your skills directory

Copy command and send to OpenClaw for auto-install:

Download and install this skill https://openskills.cc/api/download?slug=k-dense-ai-scientific-skills-pubmed-database&locale=en&source=copy

PubMed Database Skill Details

Skill Overview

The PubMed Database skill provides direct REST API access to the U.S. National Library of Medicine's PubMed biomedical literature database, supporting the construction of advanced Boolean/MeSH search queries, batch processing of literature data, and automated citation management.

Use Cases

1. Systematic Reviews and Meta-Analyses

When conducting systematic literature reviews, it's necessary to build comprehensive and reproducible search strategies. This skill supports creating complex queries using MeSH terms, Boolean operators, and field tags, covering multiple study designs and population types to ensure the comprehensiveness and accuracy of literature retrieval.

2. Automated Literature Data Extraction

For large-scale acquisition of PubMed literature data, the E-utilities API can be used for programmatic access. It supports searching with ESearch, retrieving full records with EFetch, and discovering related articles with ELink—suitable for building literature monitoring, data analysis, and visualization workflows.

3. Biomedical Literature Research

When researchers need to quickly find the latest work in a specific field, they can use advanced search syntax to filter by author, journal, publication date, article type, and other dimensions, and use the similar articles feature to expand the search scope.

Core Features

1. Advanced Search Query Construction

Supports building precise queries using Boolean operators (AND, OR, NOT), field tags ([au], [tiab], [mh], etc.), phrase searches, and wildcards. MeSH subject headings and subheadings (e.g., /therapy, /diagnosis) can be combined for targeted searches, enabling structured clinical question queries using the PICO framework.

2. E-utilities REST API Access

Provides direct HTTP/REST access to the NCBI E-utilities API, including core endpoints such as ESearch (search and retrieve PMIDs), EFetch (download full records), ESummary (retrieve document summaries), ELink (find related articles), among nine core endpoints. Supports JSON and XML response formats, making it easy to integrate into data analysis workflows in Python, R, and other environments.

3. Reference Management and Export

Supports multiple export formats (.nbib, MEDLINE, CSV, XML) and can be used with reference management tools like Zotero, Mendeley, and EndNote. Offers clipboard (temporary storage) and collections (permanent storage) features, and supports creating RSS feeds to track newly published literature.

Frequently Asked Questions

What is the difference between PubMed and MEDLINE?

PubMed is a freely accessible search engine that covers MEDLINE (the National Library of Medicine's primary bibliographic database) as well as additional content from life science journals and online books. MEDLINE is the core component of PubMed and contains indexed journal literature records. PubMed also includes some recent articles not yet indexed in MEDLINE and open-access full text from PubMed Central (PMC).

What are the limitations of using the E-utilities API?

Without an API key, the limit is 3 requests per second; with a registered API key, this can be increased to 10 requests per second. It is recommended to include User-Agent information in the request header. For large result sets (over 500 records), use the history server (Web Environment) to process in batches and avoid timeouts. Always implement rate limiting and error handling mechanisms.

How do I construct a search strategy for a systematic review?

It is recommended to use the PICO framework (Population, Intervention, Comparison, Outcome) to build search queries. Use both MeSH terms and free-text terms, and consider synonyms, spelling variants, and related concepts. Example search string: (diabetes mellitus, type 2[mh] OR "type 2 diabetes"[tiab]) AND (metformin[nm] OR lifestyle modification[tiab]) AND glycemic control[tiab] AND randomized controlled trial[pt]. It is recommended to save the search history in PubMed Advanced Search and record the search date and strategy to ensure reproducibility.

    PubMed Database Skills - Biomedical Literature Retrieval and the E-utilities API - Open Skills