uniprot-database

Search UniProt proteins, retrieve FASTA sequences, and map identifiers via REST API.

1|Updated Jan 14, 2026
One-click install
npx skills add https://github.com/Sologa/codex-pipeline --skill uniprot-database-sologa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: uniprot-database
Source: https://github.com/Sologa/codex-pipeline/tree/main/.codex/skills/uniprot-database
Command: npx skills add https://github.com/Sologa/codex-pipeline --skill uniprot-database-sologa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides direct access to the UniProt protein database, enabling users to search for proteins, retrieve sequences, map identifiers, and access detailed annotations programmatically.

Core Features & Use Cases

  • Protein Search: Find proteins by name, gene, accession, or organism using UniProt's powerful query syntax.
  • Sequence Retrieval: Download protein sequences in various formats (FASTA, TXT).
  • ID Mapping: Translate protein identifiers between UniProt and other major biological databases.
  • Batch Operations: Efficiently retrieve or map multiple entries at once.
  • Use Case: A researcher needs to find all human proteins associated with a specific gene, retrieve their sequences, and map their UniProt IDs to corresponding PDB entries for structural analysis.

Quick Start

Search for human insulin proteins using the uniprot-database skill.

Frequently Asked Questions about uniprot-database

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

FAQPage Schema
How do I retrieve protein sequences from UniProt in FASTA format?

To retrieve protein sequences in FASTA format, you can use this Skill to directly query the UniProt REST API by protein name, gene, or accession number, downloading the sequence data programmatically.

What is UniProt ID mapping and how does cross-database identifier resolution work?

UniProt ID mapping translates protein identifiers between UniProt and other major biological databases, allowing you to programmatically resolve cross-database identifiers for structural or functional analysis workflows.

Can I use UniProt's query syntax to find all human proteins associated with a specific gene?

Yes, you can execute advanced protein searches using UniProt's powerful query syntax to find all human proteins associated with a specific gene and retrieve their detailed annotations.

Does this Skill support batch operations for retrieving multiple Swiss-Prot or TrEMBL entries?

Yes, the Skill supports batch operations to efficiently retrieve or map multiple Swiss-Prot and TrEMBL entries at once, streamlining programmatic workflows requiring specific UniProt data.

What's the best way to programmatically map UniProt IDs to corresponding PDB entries for structural analysis?

The best way to map UniProt IDs to PDB entries is using the Skill's direct REST API access for ID mapping, which efficiently translates protein identifiers across databases for structural analysis.

How do I download UniProt protein annotations in TXT format via API?

You can download detailed protein annotations in TXT format by querying the UniProt database through the Skill's direct REST API access, retrieving specific entry data programmatically.