gene-list-curator

Curate literature-backed gene lists into a structured table with references.

64|12|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/MDhewei/bioinfor-claw --skill gene-list-curator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gene-list-curator
Source: https://github.com/MDhewei/bioinfor-claw/tree/main/gene-list-analysis/curate-gene-list-by-function
Command: npx skills add https://github.com/MDhewei/bioinfor-claw --skill gene-list-curator

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Curate literature-backed gene or protein lists for a requested function, pathway, molecular class, or regulator type, then normalize them into a structured table or workbook.

Core Features & Use Cases

  • Build populated candidate lists by querying authoritative databases (UniProt for high-confidence entries and NCBI Gene for aliases).
  • Merge and normalize data into a unified schema with fields like Gene name, Protein ID, Organism, Functional class, Evidence or role, PMID, References, and Notes.
  • Use cases include transcription factors, pathway gene sets, receptor families, chromatin regulators, and methylation readers.

Quick Start

Generate a curated, publication-ready gene list for transcription factors in Homo sapiens with identifiers and references, exported as a CSV.

Frequently Asked Questions about gene-list-curator

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

FAQPage Schema
How do I curate a literature-backed gene list for a specific pathway or functional class?

To curate a literature-backed gene list, this Skill queries UniProt and NCBI Gene to identify candidates for a requested function, then normalizes them into a structured table with Gene name, Protein ID, Organism, and PMID references.

What is the output format for normalized gene sets curated from UniProt and NCBI Gene?

The normalized gene sets are output as a structured table or workbook containing fixed schema fields: Gene name, Protein ID, Organism, Functional class, Evidence or role, PMID, References, and Notes, with an optional UniProt accession.

Can I build a publication-ready transcription factor list for Homo sapiens with references?

Yes, you can generate a curated, publication-ready transcription factor list for Homo sapiens that includes gene names, protein identifiers, and literature references, exported as a structured CSV file.

Does this gene list curation tool support chromatin regulators and receptor families across organisms?

Yes, this gene list curation tool applies to function-specific gene sets including chromatin regulators, receptor families, transcription factors, and methylation readers across organisms, merging data into a unified schema.

Do I need openpyxl installed to export curated gene lists as a workbook?

Yes, openpyxl is a required dependency to export the curated and normalized gene lists as a structured workbook, as the Skill relies on this library for workbook generation and formatting.

What's the best way to normalize gene aliases from NCBI Gene into a structured dataset?

The best way to normalize gene aliases is to query NCBI Gene for alias data, merge them with high-confidence UniProt entries, and map them into a structured dataset with functional class, evidence, and reference fields.