One-click install
npx skills add https://github.com/dralkh/seerai --skill lamindb-dralkh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lamindb
Source: https://github.com/dralkh/seerai/tree/main/skills/lamindb
Command: npx skills add https://github.com/dralkh/seerai --skill lamindb-dralkh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

LaminDB turns scattered research files, metadata, and analysis runs into a traceable, queryable lakehouse so biological datasets are easier to validate, reproduce, and share.

Core Features & Use Cases

  • Register and version artifacts such as DataFrames, AnnData, Parquet, and Zarr files.
  • Query metadata, filter by features, and follow lineage from inputs to outputs across runs and transforms.
  • Validate datasets with schemas and curators, then standardize labels with Bionty ontologies for cells, genes, tissues, diseases, and more.
  • Integrate with local or cloud storage, workflow managers, and MLOps tools for production research pipelines.

Quick Start

Ask me to help you set up LaminDB for a research project, register a dataset, validate it against a schema, and annotate it with ontology-backed metadata.

Frequently Asked Questions about lamindb

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

FAQPage Schema
How do I track lineage for biological datasets across workflow runs?

Lineage tracking for biological datasets works by registering artifacts and transforms in LaminDB, allowing users to follow inputs to outputs across analysis runs. It connects local and cloud storage to maintain reproducible research pipelines.

How do I validate biological data against a schema before analysis?

Biological data is validated against schemas using LaminDB curator workflows, which standardize labels and ensure datasets meet defined criteria. This schema validation guarantees research artifacts are reproducible before downstream analysis.

What is the best way to annotate biological data with ontology metadata?

Ontology annotation for biological data is done using Bionty ontologies within LaminDB to standardize metadata for cells, genes, tissues, and diseases. This process ensures datasets remain FAIR compliant and queryable by features.

Can I use cloud storage to manage versioned biological artifacts?

Cloud storage supports versioned biological artifact management in LaminDB for formats like DataFrames, AnnData, Parquet, and Zarr files. Integrating local or cloud storage allows production research pipelines to query metadata seamlessly.

Does LaminDB integrate with existing workflow managers for research pipelines?

LaminDB integrates with existing workflow managers and MLOps tools to connect scattered research files and metadata into a queryable lakehouse. This workflow integration supports production research pipelines across local and cloud environments.

What biological data formats are supported for artifact registration?

Artifact registration in LaminDB supports biological data formats including DataFrames, AnnData, Parquet, and Zarr files. Registering these versioned artifacts turns scattered research files into a traceable and queryable lakehouse.