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 ./backend/cli/skills/biology/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 body is well-structured with executable examples and a clean progressive-disclosure split into six reference files, but it is verbose (repeated reference listings) and its batch/destructive workflows lack explicit validation feedback loops. Tightening the duplicated reference lists and adding validate→retry checkpoints would lift the weaker dimensions.

Suggestions

Consolidate the reference-file pointers into a single Reference Files section and remove the duplicated 'Reference:' lines and the Getting Started Checklist reference list to reduce verbosity.

Add explicit validation feedback loops to batch/destructive workflows, e.g. after .cat.standardize() or bulk artifact registration, run curator.validate() and only proceed on success with a fix→re-validate retry path.

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

Dimension	Reasoning	Score
Conciseness	Mostly capability lists and concrete API names rather than re-explained concepts, but the six reference files are listed ~4 separate times (per-section Reference: lines, Getting Started Checklist, Reference Files) and sections overlap, so it could be tightened noticeably.	3 / 5
Actionability	Four complete executable Python examples with real imports and API calls, plus concrete method names and install commands, but a few examples reference undefined variables (schema, data_files, tissues, conditions).	4 / 5
Workflow Clarity	Sequences are present (curation 1-2-3, Getting Started 1-6, ordered code), but batch/destructive operations (bulk artifact registration, in-place .cat.standardize()) lack explicit validate→fix→retry feedback loops, capping this at 3 per the rubric.	3 / 5
Progressive Disclosure	Six real, clearly signaled one-level-deep reference files map cleanly to the six capability sections, with SKILL.md acting as an overview pointing to the bulk detail; navigation is easy.	5 / 5
	Total	15 / 20 Passed

Description

92%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 across all dimensions: it concretely states what LaminDB does, when to use it with natural trigger terms, and occupies a clear biology-data-framework niche. Minor improvement would come from adding common file-format synonyms like .h5ad/AnnData to lift trigger_term_quality to 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (managing biological datasets, tracking workflows, curating/validating with ontologies, building lakehouses, ensuring lineage) plus specific capabilities (schema validation, Nextflow/Snakemake/W&B/MLflow integrations), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (open-source data framework for biology making data queryable/traceable/reproducible/FAIR; covers data management, annotation, ontologies, schema validation, integrations, deployment) and 'when' (Use when managing biological datasets... or ensuring data lineage and reproducibility).	5 / 5
Trigger Term Quality	Strong natural terms a biology researcher would say (scRNA-seq, spatial, flow cytometry, data lakehouses, Nextflow, Snakemake, W&B, MLflow), but missing some file-format synonyms (h5ad, AnnData) and a few common variations.	4 / 5
Distinctiveness Conflict Risk	Clearly niched to LaminDB as a biology data framework with specific ontology and tooling triggers, giving a distinct niche with minimal conflict risk against other skills.	5 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/lamindb/SKILL.md
Commit: 3a6c3a9

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.