Lamindb

If you're wrangling biological datasets (scRNA-seq, spatial, flow cytometry) and need more than a file system, this gives you queryable data with automatic lineage tracking. It's built around artifacts, transforms, and runs, letting you trace any result back to the code and raw data that produced it. The ontology integration through Bionty is solid for standardizing genes, cell types, diseases across datasets. Works with Nextflow, Snakemake, Weights & Biases, the usual suspects. The curation workflow validates schemas before you save anything, which beats discovering broken metadata six months later. Deployed on SQLite locally or PostgreSQL plus S3 for production teams.

skills.sh installs: 2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill lamindb --agent claude-code

Installs into .claude/skills of the current project.

Files

LaminDB

When to use

Use for registering biological datasets, curating DataFrame/AnnData metadata, querying annotated artifacts, and tracking scientific scripts or workflows. LaminDB stores metadata in SQLite/PostgreSQL and files in configured storage; registration alone does not establish scientific validity or FAIR compliance.

This skill targets LaminDB 2.10.0 and Bionty 2.5.0. The local examples were executed on Python 3.12, pandas 3.0.6, and AnnData 0.13.2. The LaminDB release caps AnnData at 0.13.2; preserve its dependency constraints. Install IPython for registry synonym helpers (add_synonym() imports it in this release).