Tooluniverse Sequence Retrieval

This handles the messy reality of pulling sequences from NCBI and ENA when you don't want to remember which database accepts RefSeq accessions or whether that gene name is ambiguous across species. It runs the disambiguation logic (organism, gene symbol, accession type), picks the right database, and assembles a report with sequence metadata, curation levels, and cross-references. The workflow is organized around quality tiers (RefSeq curated beats predicted beats GenBank submissions) and includes fallback chains when databases don't cooperate. Useful when you need to grab sequences programmatically without writing the same accession-routing logic for the hundredth time or explaining to users why their ENA query failed on a RefSeq ID.

skills.sh installs: 1.7K
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-sequence-retrieval --agent claude-code

Installs into .claude/skills of the current project.

Files

Biological Sequence Retrieval

Retrieve DNA, RNA, and protein sequences with proper disambiguation and cross-database handling.

IMPORTANT: Always use English terms in tool calls. Only try original-language terms as fallback. Respond in the user's language.

LOOK UP DON'T GUESS: Never assume accession numbers or sequence versions. Always retrieve and verify from NCBI or ENA.

Domain Reasoning

Sequence quality hierarchy: RefSeq (NM_/NP_ = curated) > RefSeq predicted (XM_/XP_) > GenBank (submitted). Prefer the MANE Select transcript for human canonical isoforms. Check version numbers -- annotations improve across versions.

Workflow

Phase 0: Clarify (if needed) → Phase 1: Disambiguate Gene/Organism → Phase 2: Search & Retrieve → Phase 3: Report

Phase 0: Clarification (When Needed)

Ask ONLY if: gene exists in multiple organisms, sequence type unclear, or strain matters. Skip for: specific accessions, clear organism+gene combos, complete genome requests with organism.