ensembl-database

Access Ensembl REST API for vertebrate genomic data; use when you need gene/ID lookups, sequence retrieval, variant effect prediction (VEP), or homology/assembly coordinate mapping.

Quality

76%

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 ./scientific-skills/Evidence Insight/ensembl-database/SKILL.md

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 content contains solid executable CLI examples and a properly structured reference file, but is weighed down by a duplicated set of generic template sections that pad the body without adding skill-specific value. Removing the boilerplate duplicate of the five core sections would substantially improve conciseness.

Suggestions

Delete the unnumbered 'When to Use / Key Features / Dependencies / Example Usage / Implementation Details' block; it duplicates the numbered sections with generic boilerplate like 'a evidence insight task needs a packaged method instead of ad-hoc freeform output'.

Resolve the capability gap: the features list advertises homology retrieval and assembly/coordinate mapping, but --action only supports lookup/sequence/vep — either add the actions or trim the advertised features and add examples.

Make workflow validation explicit and concrete, e.g. a checkpoint to verify HTTP 200 / handle rate-limit (429) responses from rest.ensembl.org rather than the generic 'Review the generated output' step.

Dimension	Reasoning	Score
Conciseness	The body duplicates 'When to Use', 'Key Features', 'Dependencies', 'Example Usage', and 'Implementation Details' as both unnumbered generic boilerplate (e.g. 'a evidence insight task needs a packaged method instead of ad-hoc freeform output') and as numbered specific sections, adding substantial padding.	2 / 5
Actionability	Provides copy-paste-ready CLI commands for common cases ('--action lookup --species human --symbol BRCA2', sequence, vep) with concrete parameters, though the advertised homology and assembly-mapping features lack examples and are absent from the script's supported --action values.	4 / 5
Workflow Clarity	A 4-step run plan is present (confirm inputs, edit CONFIG, run, review) but validation checkpoints are generic and implicit rather than concrete (e.g. no HTTP/rate-limit verification step), leaving sequence gaps.	3 / 5
Progressive Disclosure	Endpoint detail is properly offloaded to a real one-level-deep reference (references/api_endpoints.md) and the script path is clearly signaled, though the duplicated generic sections slightly muddy the overall organization.	4 / 5
	Total	13 / 20 Passed

Description

100%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, concise description that clearly states the skill's purpose and trigger conditions with concrete, domain-specific actions. It assumes third-person voice and avoids fluff.

Dimension	Reasoning	Score
Specificity	Names the domain (Ensembl REST API, vertebrate genomic data) and lists multiple concrete actions — 'gene/ID lookups, sequence retrieval, variant effect prediction (VEP), homology/assembly coordinate mapping' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Access Ensembl REST API for vertebrate genomic data...') and when ('use when you need...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Covers natural domain terms including synonyms and the acronym pair 'variant effect prediction (VEP)', plus 'gene/ID lookups', 'sequence retrieval', and 'homology/assembly coordinate mapping' that users in this niche would naturally say.	5 / 5
Distinctiveness Conflict Risk	Scoped to Ensembl REST API and vertebrate genomics with distinct, specialized triggers, giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	20 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/ensembl-database/SKILL.md
Commit: 63c61d3

Reviewed: 5 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.