lamindb

Manage, annotate, and track lineage of biological datasets with LaminDB.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing complex biological datasets, ensuring they are queryable, traceable, reproducible, and FAIR (Findable, Accessible, Interoperable, Reusable).

Core Features & Use Cases

  • Data Management: Organize, version, and query diverse biological data types (scRNA-seq, spatial, etc.).
  • Lineage Tracking: Automatically track computational workflows and data provenance.
  • Ontology Integration: Standardize annotations using biological ontologies (genes, cell types, diseases).
  • Use Case: A researcher needs to analyze scRNA-seq data, track the analysis pipeline, and ensure all metadata is standardized using gene and cell type ontologies for reproducibility. This Skill provides the framework to achieve this.

Quick Start

Use the lamindb skill to initialize a new LaminDB instance with S3 storage and PostgreSQL.

Frequently Asked Questions about lamindb

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

FAQPage Schema
How do I manage biological data with FAIR principles?

To manage biological data with FAIR principles, you can organize, version, and query datasets using the LaminDB framework, ensuring data remains findable, accessible, interoperable, and reusable.

How do I track data lineage for scRNA-seq analysis pipelines?

You can track scRNA-seq data lineage automatically by capturing computational workflows and data provenance through LaminDB, which records transformations to ensure your biological analysis remains fully reproducible.

Does LaminDB support ontology integration for standardizing biological annotations?

Yes, LaminDB supports ontology integration via Bionty, allowing you to standardize biological annotations for genes, cell types, and diseases to ensure metadata consistency across omics datasets.

What is the best way to version spatial transcriptomics datasets?

The best way to version spatial transcriptomics datasets is by using LaminDB to manage and query your data, which automatically captures workflow lineage and integrates biological ontologies for standardized metadata.

Can I initialize a LaminDB instance with S3 storage and PostgreSQL?

Yes, you can initialize a LaminDB instance configured with S3 storage and PostgreSQL to manage your biological datasets, leveraging the framework's automated lineage capture and ontology integration features.