ncbi-datasets

Retrieve genomic, gene, and taxonomy data from NCBI Datasets.

1|Updated Apr 29, 2026
One-click install
npx skills add https://github.com/cultivarium/hermes-starter-kit --skill ncbi-datasets
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ncbi-datasets
Source: https://github.com/cultivarium/hermes-starter-kit/tree/main/skills/ncbi-datasets
Command: npx skills add https://github.com/cultivarium/hermes-starter-kit --skill ncbi-datasets

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

NCBI Datasets provides a fast way to retrieve genome data, genome metadata, gene information, and taxonomy data, removing the need for manual downloads and scattered sources.

Core Features & Use Cases

  • Summarize data with datasets summary (genome metadata, gene info, and taxonomy) to inspect datasets quickly.
  • Download data with datasets download (genomes, genes, annotations, and metadata) for offline analysis.
  • Export results in common formats via dataformat (JSON Lines, TSV) for downstream pipelines.
  • Real-world use cases include genome assembly validation, gene annotation retrieval, and taxonomic surveys across taxa.

Quick Start

Install the ncbi-datasets-cli, then run a datasets summary or download workflow to fetch your first dataset.

Frequently Asked Questions about ncbi-datasets

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

FAQPage Schema
How do I download genome data and metadata from NCBI for offline analysis?

Download genome data from NCBI by running the datasets download command to fetch genomes, annotations, and metadata, which removes the need for scattered manual downloads and outputs files for offline analysis.

What's the best way to summarize NCBI genome metadata before downloading a full dataset?

Summarize NCBI genome metadata using the datasets summary command, which allows you to quickly inspect genome, gene, and taxonomy information across multiple taxa before initiating a full download.

Can I export NCBI genomic data to TSV or JSON Lines for downstream pipelines?

Yes, export NCBI genomic data to TSV or JSON Lines using the dataformat command, which structures the retrieved datasets summary and download outputs for seamless integration into downstream pipelines.

Does retrieving NCBI taxonomy and gene information require any specific command line tools?

Retrieving NCBI taxonomy and gene information requires the ncbi-datasets-cli, which provides the datasets and dataformat utilities needed to execute summarize and download workflows.

What use cases does fetching NCBI genomics data support for comparative analyses?

Fetching NCBI genomics data supports comparative analyses, genome assembly validation, gene annotation retrieval, and taxonomic surveys across multiple taxa and project scopes.

How do I get gene annotation data from NCBI using command line operations?

Get gene annotation data from NCBI by running the datasets download workflow for genes, which retrieves annotation information and metadata directly from the NCBI Datasets database.