CtrlK
BlogDocsLog inGet started
Tessl Logo

lamindb

This skill is applicable when using LaminDB. LaminDB is an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR-compliant. It is suitable for managing biological datasets (scRNA-seq, spatial transcriptomics, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakes, or ensuring data lineage and reproducibility in biological research. It covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integration with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/lamindb/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 delivers concrete, actionable LaminDB guidance with a well-organized reference structure, but it is padded with duplicated description text, generic boilerplate, and a promotional section, and its workflows lack explicit validation checkpoints.

Suggestions

Remove the verbatim description duplicates from 'When to Use' and 'Key Features' and replace them with distinct, concise guidance.

Delete the generic 'Implementation Details' and 'Example Usage' boilerplate (e.g., 'No packaged executable script was detected') and the promotional 'K-Dense Web' section, which add no LaminDB-specific value.

Add explicit validation/checkpoint steps (e.g., verify curator.validate() passes and handle failures) into the use-case workflows to strengthen feedback loops.

DimensionReasoningScore

Conciseness

The description text is duplicated verbatim three times (the lowercased 'When to Use' bullet, the 'Key Features' bullet, and the Overview), alongside generic boilerplate ('Implementation Details', 'Example Usage' template) and a promotional K-Dense section — noticeably padded.

2 / 5

Actionability

Provides executable Python with real API calls (ln.track, bt.CellType.import_source, AnnDataCurator) and concrete commands (uv pip install, lamin init); only minor placeholders like train_model() and data_files keep it from a 5.

4 / 5

Workflow Clarity

The Getting Started Checklist gives a clear sequenced path, but validation checkpoints and error-recovery feedback loops are implicit or absent across the workflows.

3 / 5

Progressive Disclosure

Six real reference files are well-signaled one level deep ('Reference: references/X.md - Read this document…') with a dedicated Reference Files section; the body is somewhat long with inline detail, keeping it just below a 5.

4 / 5

Total

13

/

20

Passed

Description

83%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 comprehensive, concrete, and well-targeted to a distinct biological-data niche with strong trigger terms. Its main weakness is a slightly circular 'when' trigger and minor missing keyword synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (managing biological datasets, tracking workflows, curating/validating with ontologies, building data lakes, ensuring lineage) plus specific ontologies and integrations, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (open-source data framework for biology, queryable/traceable/reproducible/FAIR) and 'when' ('applicable when using LaminDB', 'suitable for…'), but the 'when' is somewhat circular and could be more specific.

4 / 5

Trigger Term Quality

Strong natural domain terms (LaminDB, scRNA-seq, spatial transcriptomics, flow cytometry, Nextflow, Snakemake, W&B, MLflow) that users would say, but a few synonyms or file extensions are missing, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (biology data framework / LaminDB) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
aipoch/medical-research-skills
Reviewed

Table of Contents

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.