lamindb

Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. Covers setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation with Bionty, collections, branches, storage, and workflow integrations.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

61%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.

A well-structured, actionable skill body that leverages real one-level-deep reference files and concrete code examples. Its main weaknesses are redundancy (references listed three times, principles restating capabilities) and missing validation checkpoints in batch registration workflows.

Suggestions

Remove the duplicate reference listings: keep one canonical 'Reference Files' section and drop the repeated per-section 'Reference:' lines or vice versa.

Add an explicit validation/verification step inside batch workflows (e.g., Use Case 2) — validate each artifact or confirm count before proceeding — to lift workflow_clarity above the batch cap.

Trim or merge 'Key Principles' into 'Core Capabilities' to eliminate restated material and reduce token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific content, but padded with redundancy: the six reference files are listed three times (inline per capability, again in 'Reference Files', and again in 'Getting Started Checklist'), and 'Key Principles' largely restates 'Core Capabilities'.	3 / 5
Actionability	Provides concrete, mostly executable code across four use cases plus specific API calls (ln.track(), curator.validate(), bt.CellType.import_source()), though some examples use undefined placeholders (schema, data_files, train_model).	4 / 5
Workflow Clarity	Sequences are present and Use Case 1 includes a validate()-then-save checkpoint, but batch workflows like Use Case 2 loop over files registering artifacts without validation/verification steps, capping this dimension per the batch-operations rule.	3 / 5
Progressive Disclosure	Six real reference files are clearly signaled one level deep with per-section 'Reference: references/X.md' pointers and a consolidated listing, though the triple-repetition of the reference list and inline 'Key Principles' show minor organization gaps.	4 / 5
	Total	14 / 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.

A strong, specific description that clearly states both what the skill covers and when to invoke it, with a distinct biological-data niche. It could improve trigger coverage by adding the natural synonyms and file formats (AnnData, .h5ad, scRNA-seq) that practitioners actually say.

Suggestions

Add common synonyms and file extensions users say, e.g. 'AnnData', '.h5ad', 'scRNA-seq', or 'single-cell data', to broaden natural trigger matching.

Consider leading with the concrete actions before the product tagline so the most queryable capabilities appear first in the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation with Bionty, collections, branches, storage, and workflow integrations' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both: what it does ('Covers setup, artifact registration, query/search...') and when to use it ('Use when working with LaminDB...'), with concrete trigger phrasing in third person.	5 / 5
Trigger Term Quality	Includes natural terms like 'working with LaminDB', 'biological datasets and models', 'lineage tracking', and 'Bionty', but misses common synonyms and file extensions users might say (e.g., AnnData, .h5ad, scRNA-seq, single-cell).	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — a lineage-native lakehouse for biological data — with distinct, product-specific triggers (LaminDB, Bionty) that minimize overlap with generic data or documentation 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: K-Dense-AI/scientific-agent-skills
Path: skills/lamindb/SKILL.md
Commit: 1e5eeff

Reviewed: 5 days 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.