lamindb

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

1.32x

Quality

71%

Does it follow best practices?

Impact

74%

1.32x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/lamindb/SKILL.md

Evaluation results

62%

19%

Single-Cell RNA-seq Data Curation Pipeline

AnnData curation with ontology validation

Criteria

Without context

With context

uv pip install

ln.track and ln.finish

100%

Ontology import_source

100%

Typed Feature definitions

90%

100%

Schema with otype and slots

100%

AnnDataCurator usage

100%

curator.cat.standardize

20%

curator.cat.add_ontology

Hierarchical artifact key

100%

feature_sets.add_ontology

92%

31%

Reproducible Multi-Run Preprocessing Pipeline

Lineage tracking and parameterized run management

Criteria

Without context

With context

ln.track with params

100%

ln.track with project

100%

ln.finish called

100%

Double-underscore param query

100%

Project-based query

100%

Versioning over duplication

100%

Hierarchical artifact keys

100%

Lineage inspection

87%

Report contains parameters

100%

Multiple distinct param sets

100%

70%

Biological Data Lakehouse with Advanced Queries

Advanced querying, collections, and streaming

Criteria

Without context

With context

Q objects for OR/NOT

100%

Double-underscore cross-registry query

100%

ln.Collection created

100%

Collection name and description

44%

55%

backed or open streaming

100%

External ID stored as feature

100%

to_dataframe include features

Hierarchical artifact keys

100%

ln.track and ln.finish

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Single-Cell RNA-seq Data Curation Pipeline Reproducible Multi-Run Preprocessing Pipeline Biological Data Lakehouse with Advanced Queries

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.