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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/lamindb/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

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

The content is well-structured with strong progressive disclosure (a clean overview pointing to six real reference files) and mostly actionable code examples. Its weaknesses are verbosity from restating capabilities across multiple sections and missing validate-fix-retry feedback loops in the curation/batch workflows.

Suggestions

Tighten the Overview, When-to-Use, Core Capabilities, Key Principles, and Getting Started sections — they restate the same capability bullets; consolidate to reduce token cost.

Add explicit validate->fix->retry feedback loops (e.g., handling curator.validate() failures) in the curation and batch-save workflows to reach full workflow clarity.

Replace or define placeholders in code examples (schema, data_files, tissues[i], train_model) so the examples are copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with bullet lists and concrete code, but the Overview, When-to-Use, Core Capabilities, Key Principles, and Getting Started Checklist sections restate capability bullets and the frontmatter description, adding padding that could be trimmed without losing information.	3 / 5
Actionability	Four concrete, mostly executable Python examples with real API calls (ln.track, bt.CellType.import_source, ln.Artifact.filter, .cat.standardize) cover common cases, but several rely on undefined placeholders (schema, data_files, tissues[i], train_model), leaving minor gaps.	4 / 5
Workflow Clarity	A reasonable sequence exists (When-to-Use, capability areas, Getting Started Checklist, ordered code examples), but curation/batch workflows lack explicit validate->fix->retry feedback loops or error-recovery checkpoints, which caps workflow clarity at 3 for these batch/validation operations.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references to six reference files (core-concepts, data-management, annotation-validation, ontologies, integrations, setup-deployment), all of which exist on disk, plus a Reference Files index for easy navigation.	5 / 5
	Total	15 / 20 Passed

Description

95%Weight 40%Scale 1-5

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 concisely states what LaminDB does and gives explicit, concrete 'Use when...' triggers with excellent natural keyword coverage and clear niche distinctiveness. Specificity is the only dimension slightly below maximum, as a few capability areas are described at a high level.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('managing biological datasets', 'curating and validating data with biological ontologies', 'building data lakehouses', 'ensuring data lineage') plus a 'Covers...' clause enumerating validation, integrations, and deployment, but a few items like 'deployment strategies' remain slightly high-level, keeping it just below fully comprehensive.	4 / 5
Completeness	Explicitly answers 'what' (open-source data framework for biology making data queryable/traceable/reproducible/FAIR, covering management, annotation, ontologies, validation, integrations, deployment) and 'when' via a concrete 'Use when...' clause enumerating trigger scenarios.	5 / 5
Trigger Term Quality	Comprehensive natural terms users would actually say — 'scRNA-seq, spatial, flow cytometry', 'data lakehouses', 'data lineage and reproducibility', plus synonyms and concrete tool names (Nextflow, Snakemake, W&B, MLflow, genes, cell types, diseases, tissues).	5 / 5
Distinctiveness Conflict Risk	LaminDB combined with biology, scRNA-seq, biological ontologies, and lakehouse lineage defines a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/lamindb/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.