lamindb

8.3

117

429

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.

bioinformatics

8.3

Rating

Installs

Data & Analytics

Quick Review

Exceptional skill for biological data management with LaminDB. The description is comprehensive and clearly articulates when to use the skill. The SKILL.md provides excellent high-level structure with clear signposting to detailed reference files for each capability area (core concepts, data management, annotation, ontologies, integrations, setup). Code examples are practical and cover real-world use cases (scRNA-seq, ML pipelines, Nextflow integration). Task knowledge is strong with concrete workflows and best practices. Structure is exemplary—concise overview with organized references preventing clutter. Novelty is solid: LaminDB's specialized biological data framework, ontology integration, and lineage tracking would require significant tokens and domain knowledge for a CLI agent to replicate. The skill meaningfully reduces complexity for biological data workflows that combine data management, validation, ontology mapping, and computational reproducibility. Minor point: while highly specialized, the core data management patterns may overlap with general database/data engineering skills, but the biological context and ontology integration provide clear differentiation.