tooluniverse-sequence-retrieval

Retrieve DNA, RNA, and protein sequences from NCBI and ENA with accession-based disambiguation.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill tooluniverse-sequence-retrieval-avatar-arts
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tooluniverse-sequence-retrieval
Source: https://github.com/AvaTar-ArTs/.Agent-skills/tree/main/skills/tooluniverse-sequence-retrieval
Command: npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill tooluniverse-sequence-retrieval-avatar-arts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tooluniverse.

What problem does it solve? Finding the correct biological sequence is error-prone: gene names map to multiple organisms, accession prefixes determine which database tools work, and RefSeq accessions fail on ENA. This Skill handles gene/organism disambiguation, accession-type routing, and produces complete sequence profile reports with metadata, annotations, and download options. ## Core Features & Use Cases - Accession-Aware Retrieval: Routes RefSeq accessions (NC_, NM_, NP_) to NCBI tools and GenBank/EMBL accessions to NCBI or ENA, avoiding 404 errors. - Gene Disambiguation: Resolves organism, strain, and sequence type (genomic, mRNA, protein) before searching NCBI Nucleotide. - Structured Sequence Profiles: Generates reports with length, GC content, curation level tiers, GenBank annotations, cross-database references, and FASTA/GenBank download commands. - Use Case: A researcher asks for the E. coli K-12 reference genome; the Skill searches NCBI, identifies NC_000913.3 as the RefSeq reference, and returns a full profile with annotations and download instructions. ## Quick Start Retrieve the complete genome sequence for Escherichia coli K-12 and show its annotations and download options.

Frequently Asked Questions about tooluniverse-sequence-retrieval

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

FAQPage Schema
How do I retrieve a gene sequence from NCBI by gene name?▼

Search NCBI Nucleotide with the organism and gene symbol, convert the returned UIDs to accession numbers, then fetch the sequence in FASTA or GenBank format. Specifying strain and sequence type such as mRNA or complete genome narrows results.

What is the difference between RefSeq and GenBank accessions?▼

RefSeq accessions (NC_, NM_, NP_, XM_) are NCBI-curated reference sequences, while GenBank accessions are direct submitter entries. RefSeq records only work with NCBI tools; GenBank records are also available through ENA.

Why does ENA return a 404 error for my accession?▼

ENA does not host RefSeq accessions such as NC_, NM_, or NP_, so queries for them return 404 errors. Use NCBI tools for any RefSeq accession and reserve ENA tools for GenBank or EMBL format records.

Can I get sequence annotations along with the FASTA sequence?▼

Yes, request the GenBank format instead of FASTA to receive feature annotations such as CDS, gene, tRNA, and rRNA counts along with the sequence. FASTA format contains only the raw sequence and header.

What happens when a sequence search returns no results?▼

Broaden the search by removing strain filters, checking organism spelling, or trying alternative gene synonyms and keywords. English scientific names should be used in queries, with original-language terms only as a fallback.