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

78%

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

57%

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

A well-organized, mostly actionable body with excellent progressive disclosure through six verified reference files. Its main weaknesses are token redundancy across sections and code examples that are not fully self-contained, plus the absence of validation feedback loops in batch workflows.

Suggestions

Remove redundancy: drop or shrink 'When to Use This Skill' and 'Key Principles' since they restate the description and code examples, and consolidate the standalone 'Reference Files' list with the per-section reference pointers.

Make the code examples self-contained by defining or stubbing the undefined symbols (schema, data_files, tissues, conditions, train_model) so snippets are copy-paste ready.

Add explicit validation/verification checkpoints to the batch and curation workflows (e.g., 'validate() -> on failure, fix and re-validate -> only then save_artifact') to lift workflow clarity above 2.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but padded with redundancy: the 'When to Use' section restates the description's triggers, 'Key Principles' rehashes workflow advice already shown in code, and the 'Reference Files' section duplicates the per-section references. Not score-3 lean, but not verbose enough to drop to 1.	2 / 3
Actionability	Provides concrete API calls and four worked Python examples, but several snippets rely on undefined placeholders (schema, data_files, tissues, conditions, train_model), so they are not fully copy-paste ready — matching the 'incomplete / missing key details' anchor.	2 / 3
Workflow Clarity	Sequences exist (Getting Started checklist, curation steps, step-by-step use cases), but batch/destructive operations like the loop-registration in Use Case 2 lack explicit validation checkpoints or fix-and-retry feedback loops, which caps workflow clarity at 2 per the rubric notes.	2 / 3
Progressive Disclosure	A clear overview with well-signaled, one-level-deep references — each capability section points to a real file in references/ ('Reference: references/core-concepts.md ...'), and all six referenced files exist on disk. Content is appropriately split with easy navigation.	3 / 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.

A strong, specific description that clearly states both the framework's purpose and the concrete situations in which to invoke it, using natural domain terms. It is third-person and free of vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions such as 'managing biological datasets (scRNA-seq, spatial, flow cytometry)', 'curating and validating data with biological ontologies', 'building data lakehouses', and 'schema validation', matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both 'what' ('open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR') and 'when' with an explicit 'Use when managing biological datasets...' trigger clause.	3 / 3
Trigger Term Quality	Includes natural terms a user would actually say — scRNA-seq, spatial, flow cytometry, biological ontologies, data lakehouses, lineage — with good coverage of variations across the 'Use when...' clause.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (LaminDB / biological data management) with distinct domain-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: f627ab5

Reviewed: about 7 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.