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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and highly actionable with concrete executable code and clear install/setup guidance, but it is somewhat verbose and lacks explicit validation feedback loops in its workflows. Its progressive-disclosure design is undercut by a missing references/ bundle whose files are referenced but absent.

Suggestions

Create the six referenced files under references/ (core-concepts.md, data-management.md, annotation-validation.md, ontologies.md, integrations.md, setup-deployment.md) so the signaled progressive-disclosure paths actually resolve.

Add explicit validation checkpoints with error-recovery branches to the curation and registry workflows (e.g., what to do when curator.validate() fails) to satisfy feedback-loop expectations for batch/data operations.

Trim redundancy by consolidating the 'Core Value Proposition', 'Key Principles', and 'Getting Started Checklist' sections, and remove restatements of the FAIR acronym and overview that the description already covers.

Dimension	Reasoning	Score
Conciseness	The body re-explains what LaminDB and 'FAIR' mean and restates the description via a 'Core Value Proposition' block and a 10-item 'Key Principles' section that overlap with the 'Getting Started Checklist' and 'Reference Files', so it is mostly efficient but padded and could be tightened; it is not a level-3 lean body and not a level-1 wall of obvious explanations.	2 / 3
Actionability	Provides four complete, executable Python examples with real API calls (ln.track(), bt.CellType.import_source(), ln.curators.AnnDataCurator, artifact.features.add_values) plus concrete install and CLI commands ('uv pip install lamindb', 'lamin init'), matching the level-3 anchor for copy-paste-ready guidance.	3 / 3
Workflow Clarity	Sequenced steps appear in the use cases and the getting-started checklist, but curation/registry workflows involve batch writes and ontology mapping with no explicit validate->fix->retry checkpoints; curator.validate() is called with no branch for failure, so per the guideline validation gaps cap this at 2 rather than 3.	2 / 3
Progressive Disclosure	The body is organized into six capability areas each signaling a 'references/<file>.md' reference, but the references/ directory does not exist, so the referenced paths do not resolve and the promised one-level-deep structure is incomplete; organization is present (not level 1) but the broken bundle keeps it from level 3.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it names the tool and domain, lists many concrete capabilities, and provides an explicit 'Use when' trigger clause with natural user vocabulary. It answers both what and when with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'managing biological datasets (scRNA-seq, spatial, flow cytometry)', 'curating and validating data with biological ontologies', 'building data lakehouses', and 'integrations with workflow managers (Nextflow, Snakemake)', matching the level-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers 'what' (an open-source data framework for biology making data queryable, traceable, reproducible, and FAIR) and 'when' via a clear 'Use when...' clause enumerating triggers, satisfying the level-3 anchor for both what AND when.	3 / 3
Trigger Term Quality	Includes natural user-facing terms like 'scRNA-seq', 'spatial', 'flow cytometry', 'Nextflow, Snakemake', 'W&B, MLflow', 'data lakehouses', and 'biological datasets', giving good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The named tool 'LaminDB' plus the biology-data niche (ontologies, lineage, lakehouses, single-cell modalities) form a clear, distinct trigger set that is unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 18 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/lamindb/SKILL.md
Commit: df37802

Reviewed: about 2 hours ago

Table of Contents

Discovery Implementation Validation

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.