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

93%

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

Quality

Content

87%Weight 40%Scale 1-3

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

A high-quality, executable reference: lean and concrete command examples with proper offloading of the full API reference to a bundle file. The only weakness is workflow clarity, where the read-only catalog lacks explicit validation checkpoints or an end-to-end sequenced checklist.

Suggestions

Add an explicit verification checkpoint after running commands — e.g., confirm the output JSON/summary contains the expected ENSG/ENST ID or VEP consequence before presenting results, with guidance on retrying or re-resolving when results are empty.

Include a short end-to-end workflow checklist for common multi-step tasks (e.g., resolve symbol -> list canonical transcript -> run VEP) so Claude sequences commands with explicit checkpoints rather than treating each command as standalone.

Expand the error-recovery feedback loop beyond rate limits — note what to do on HTTP 400/404 for an unresolved symbol or unsupported assembly so Claude can recover rather than abort.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it defines only Ensembl-specific nomenclature (ENSG/ENST/ENSP/MANE/Canonical) rather than general concepts, and each section earns its place, with only minor redundancy in the re-listed VEP plugins.	3 / 3
Actionability	Every one of the nine commands ships with fully executable, copy-paste-ready `uv run scripts/ensembl_api.py ...` examples using real arguments and flags, matching the score-3 anchor for executable, specific guidance.	3 / 3
Workflow Clarity	Commands are clearly organized in a numbered catalog and there is one feedback loop (429 -> exponential backoff), but there are no explicit validation checkpoints or checklists for multi-step flows, so it sits at 'steps listed but checkpoints missing or implicit' rather than a 3.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview that cleanly splits the full endpoint reference into the verified, one-level-deep `references/ensembl_rest_api_reference.md`, explicitly signaled by path, with the wrapper script invoked inline — matching the score-3 anchor for clear, well-signaled navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, well-scoped description: it enumerates concrete capabilities, provides an explicit 'Use this skill as...' trigger clause, and occupies a distinct niche. Voice is third-person throughout, so no specificity penalty applies.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'resolve gene, transcript, and protein IDs', 'fetch genomic or protein sequences', 'retrieve gene structures (exons)', and 'get variant consequence and effect predictions (VEP)' — matching the score-3 anchor of listing several specific concrete actions rather than vague language.	3 / 3
Completeness	It answers both 'what' (resolve IDs, fetch sequences, retrieve structures, VEP) and 'when' via the explicit 'Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool' clause, which is equivalent explicit trigger guidance and clears the cap-at-2 bar.	3 / 3
Trigger Term Quality	For the genomics audience it targets, terms like 'gene, transcript, and protein IDs', 'genomic or protein sequences', 'exons', and 'VEP' are the natural phrases a user would say when they need this skill, giving good coverage of domain-natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Ensembl ID translation, genomic sequence retrieval, and VEP prediction form a clear, specialized niche with distinct triggers that are unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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: google-deepmind/science-skills
Path: skills/ensembl_database/SKILL.md
Commit: 0b42509

Reviewed: 8 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.