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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

LaminDB removes the manual overhead of making biological datasets, models, and analysis runs traceable, queryable, and reproducible. It helps you keep provenance, validation, and annotations connected so experiments do not become disconnected files and notebooks.

Core Features & Use Cases

  • Lineage tracking: Record inputs, outputs, parameters, code, and environments for notebooks, scripts, functions, and pipelines.
  • Data validation and annotation: Validate DataFrame, AnnData, MuData, SpatialData, and TileDB-SOMA objects with schemas and ontology-backed metadata.
  • Queryable storage: Register artifacts, search by features, browse collections, and manage local or cloud-backed storage with versioning.
  • Use case: A researcher curates single-cell RNA-seq data, standardizes cell types with Bionty, saves a validated artifact, and later retrieves all datasets linked to the same workflow or ontology term.

Quick Start

Ask the assistant to help you set up LaminDB for a biological data workflow, validate a dataset, and register it with lineage and ontology annotations.

Frequently Asked Questions about lamindb

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

FAQPage Schema
How do I track biological dataset lineage for scRNA-seq analysis?

Track scRNA-seq biological dataset lineage by registering artifacts, validating schemas, and logging inputs, outputs, parameters, and code to ensure full reproducibility across local and cloud storage.

Can I validate AnnData or SpatialData objects with ontology annotations?

Yes, you can validate AnnData, MuData, SpatialData, and TileDB-SOMA objects using schemas and ontology-backed metadata to standardize biological annotations like cell types.

Does LaminDB integrate with Nextflow, Snakemake, MLflow, and Weights & Biases?

LaminDB integrates with notebooks, scripts, Nextflow, Snakemake, MLflow, and Weights & Biases to record lineage and provenance for pipeline execution and model training workflows.

What is the best way to prevent lost provenance in biological research workflows?

Prevent lost provenance in biological research workflows by registering datasets and models in an artifact registry that queries features, browses collections, and manages versioned storage.

How do I standardize cell types when curating single-cell RNA-seq data?

Standardize cell types in single-cell RNA-seq data by applying ontology-backed curation with Bionty, saving validated artifacts with linked metadata for later retrieval by ontology terms.

What are the limitations of manual biological dataset provenance tracking?

Manual biological dataset provenance tracking creates disconnected files and notebooks, risking lost lineage, unvalidated annotations, and hard-to-reproduce analysis outputs across complex research workflows.