tooluniverse-microbial-genome-characterization

Discovers, quality-controls, and maps genome assemblies and replicons via NCBI Datasets.

1.7k|254|Updated Mar 3, 2025
One-click install
npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-microbial-genome-characterization
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tooluniverse-microbial-genome-characterization
Source: https://github.com/mims-harvard/ToolUniverse/tree/main/plugins/tooluniverse/skills/tooluniverse-microbial-genome-characterization
Command: npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-microbial-genome-characterization

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Researchers often need to know which genome assemblies exist for an organism, which one is the designated reference, and how complete or contiguous it is, but manually navigating NCBI records is slow and error-prone. This Skill resolves an organism name or taxid to assemblies, pulls QC metrics, and maps chromosomes and plasmids using keyless NCBI Datasets tools.

Core Features & Use Cases

  • Assembly Discovery & Selection: Resolve an organism name to a tax id, list available assemblies, and select the reference or best-quality assembly using RefSeq category, assembly level, N50, and contig count.
  • Assembly QC Metrics: Retrieve total length, contig/scaffold N50, contig count, GC%, assembly level, and RefSeq category for any GCF_/GCA_ accession.
  • Replicon Mapping: Enumerate chromosomes and plasmids per assembly via sequence reports, correctly distinguishing plasmids from chromosomes by name and role.
  • Use Case: Ask how many plasmids E. coli O157:H7 Sakai has, and the Skill resolves the reference assembly GCF_000008865.2 and reports one chromosome plus two plasmids (pOSAK1 and pO157) with their accessions and lengths.

Quick Start

Ask the agent to find the reference genome for Escherichia coli and report its assembly stats, GC content, and plasmid count.

Frequently Asked Questions about tooluniverse-microbial-genome-characterization

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

FAQPage Schema
How do I find the reference genome for an organism in NCBI?

Resolve the organism name to a tax id with NCBIDatasets_suggest_taxonomy, then call NCBIDatasets_list_genomes_by_taxon with reference_only set to true. The assembly with refseq_category 'reference genome' is NCBI's designated reference; otherwise prefer representative genomes or the highest assembly level.

How do I get assembly stats like N50 and GC content for a GCF accession?

Call NCBIDatasets_get_genome_assembly with the GCF_ or GCA_ accession. It returns total sequence length, contig and scaffold N50, contig count, GC percent, assembly level, RefSeq category, and release date from live NCBI Datasets records.

How do I count plasmids in a bacterial genome assembly?

Use NCBIDatasets_get_sequence_reports on the accession and count replicons whose name or role indicates a plasmid rather than a chromosome. The number_of_chromosomes field counts all assembled molecules, so the sequence report is the authoritative source.

What is the difference between GCF and GCA accessions?

GCF accessions are RefSeq assemblies curated by NCBI with consistent annotation, while GCA accessions are the original GenBank submissions. They share the same numeric core, and the GCF version is preferred when both exist.

Can this skill assemble a genome from raw sequencing reads?

No, de novo assembly from FASTQ reads is not supported by any ToolUniverse tool. This skill only characterizes assemblies already deposited in NCBI Datasets, and it also does not compute BUSCO or CheckM completeness scores.