CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ensembl-database

Query the Ensembl database to resolve gene, transcript, and protein IDs, fetch genomic or protein sequences, retrieve gene structures (exons), and get variant consequence and effect predictions (VEP). Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool.

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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, highly actionable skill body with copy-paste commands and good progressive disclosure via a single clearly signaled reference file; only minor conciseness trimming and a missing failure-recovery loop hold it back.

Suggestions

Trim the Overview paragraph and the ENSG/ENST/ENSP entries in Key Concepts, which restate facts Claude already knows.

Add a brief failure-handling note (e.g., empty/ambiguous resolve-gene results, 429 responses) to close the validation gap without bloating context.

DimensionReasoningScore

Conciseness

The body is largely efficient — command examples and rules carry most of the weight — but the Overview paragraph restates the description and Key Concepts over-explains basics (ENSG/ENST/ENSP) Claude already knows, leaving minor trimmable padding.

4 / 5

Actionability

Every command ships copy-paste-ready bash with real IDs, real flags, and real output paths, plus a worked VEP stdout example — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Numbered prerequisites, explicit Core Rules acting as checkpoints (flag default species, flag MANE defaulting, flag non-default assembly), and a clear Parsing Outputs sequence give a clear flow; minor gap is the absence of an explicit validate/retry path for failed or empty queries.

4 / 5

Progressive Disclosure

The body is a concise overview that delegates the bulk API surface to a real, clearly signaled one-level-deep reference (references/ensembl_rest_api_reference.md) and drives all execution through the bundled script — content is appropriately split and easy to navigate.

5 / 5

Total

18

/

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.

A strong, specific, third-person description that names concrete actions and a distinct niche, with only minor gaps in trigger-term exhaustiveness and the explicitness of the "when to use" clause.

Suggestions

Add concrete user-utterance triggers, e.g. "Use when the user asks to look up a gene ID, fetch a protein sequence, or predict a variant's effect."

Include common synonyms/file-format users mention (HGNC, RefSeq, UniProt, FASTA) to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "resolve gene, transcript, and protein IDs", "fetch genomic or protein sequences", "retrieve gene structures (exons)", "get variant consequence and effect predictions (VEP)" — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Both "what" and "when" are present — "Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool" — but the "when" is role-based rather than concrete user-utterance trigger phrases, so it could be more explicit.

4 / 5

Trigger Term Quality

Good keyword coverage with natural domain terms (gene/transcript/protein IDs, sequences, exons, VEP, variant consequence), but a few natural synonyms users might say (e.g., "look up a gene", HGNC, RefSeq) are absent, so it is not quite exhaustive.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear Ensembl-specific niche (ID translation, genomic sequence retrieval, VEP) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

google-deepmind/science-skills

Path

skills/ensembl_database/SKILL.md

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.