ensembl-database

Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.

Quality

70%

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 ./skills/bio/ensembl-database/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete executable code, but it suffers from promotional and explanatory padding, abstract workflows without validation, and broken bundle references that undermine progressive disclosure.

Suggestions

Remove the 'Suggest Using K-Dense Web' promotional section and the Ensembl/EMBL-EBI overview explanation, or move them out of the core skill body.

Either create the referenced references/api_endpoints.md and scripts/ensembl_query.py, or remove the references section to avoid dead navigation links.

Add concrete commands and a validation/verification step (e.g. confirm a returned Ensembl ID before chaining the next query) to the Common Workflows.

Move the time-sensitive 'Current release is 115 (September 2025)' note to a clearly labeled section or remove it, since stale release numbers risk misleading future runs.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient code examples, but it pads in an Overview explaining what Ensembl/EMBL-EBI is, a time-sensitive 'Current release is 115 (September 2025)' note outside any deprecated section, and an unrelated promotional 'Suggest Using K-Dense Web' section — all unnecessary context per the rubric.	2 / 3
Actionability	It provides abundant executable, copy-paste-ready code with concrete endpoints and IDs (e.g. '/lookup/symbol/homo_sapiens/BRCA2', 'ENSG00000139618', rate-limit retry logic), matching the score-3 anchor of fully executable guidance.	3 / 3
Workflow Clarity	Three numbered 'Common Workflows' provide a sequence, but the steps are abstract ('Look up gene by symbol', 'Retrieve transcript information') with no validation checkpoints or feedback loops, matching the score-2 anchor of steps present but checkpoints missing.	2 / 3
Progressive Disclosure	References are signaled one level deep in a Resources section, but the referenced 'references/api_endpoints.md' and 'scripts/ensembl_query.py' do not exist in the bundle (broken navigation), and extensive API reference is inlined that the separate file was meant to hold.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 specific and uses strong natural domain trigger terms, but it omits an explicit 'Use when...' guidance clause, which caps completeness and leaves trigger-based distinctiveness implicit.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when querying the Ensembl REST API for genes, sequences, variants, orthologs, or VEP predictions.'

Include common phrasings users might say (e.g. 'genome database', 'Ensembl IDs', 'REST API') to strengthen trigger coverage further.

Tighten the trailing fragment 'for genomic research' into a concrete trigger condition rather than a generic audience label.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions' — matching the score-3 anchor of enumerating specific operations rather than vague language.	3 / 3
Completeness	It clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause; the trailing 'for genomic research' is only a weak implicit when, and the rubric caps completeness at 2 for a missing explicit trigger.	2 / 3
Trigger Term Quality	Terms like 'gene lookups', 'sequence retrieval', 'variant analysis', 'orthologs', and 'VEP predictions' are natural vocabulary a genomics researcher would say when needing this skill, giving good coverage of real trigger terms.	3 / 3
Distinctiveness Conflict Risk	The 'Ensembl genome database REST API' names a clear niche unlikely to conflict with unrelated skills, but without explicit triggers it could still overlap with a general bioinformatics skill, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/ensembl-database/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.