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

68%

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 ./backend/cli/skills/databases/ensembl-database/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, code-heavy reference with strong executable REST examples and a genuine, clearly signaled bundle. Weaker spots are the generic workflow steps without validation checkpoints, scattered over-explanation (including uncaveated version claims), and a bundled script that is never actually used in the documented workflows.

Suggestions

Add explicit validation and error-recovery checkpoints to the three workflows (e.g., check HTTP status / handle 429 as each step runs, and reference the retry pattern already shown), moving them from bare step lists to guided sequences.

Trim padding: remove the 'Current release is 115 (September 2025)' claim or move it into a versioned/deprecated section, and cut filler sentences like 'The ensembl_rest package provides a Pythonic interface to all Ensembl REST API endpoints.'

Integrate scripts/ensembl_query.py into the workflows and quick examples (e.g., 'python ensembl_query.py --gene BRCA2 --species human') so the bundled script is actually discoverable and used, rather than only listed under Resources.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, code-first content, but includes unnecessary padding that could be trimmed: time-sensitive version info outside any versioning section ('Current release is 115 (September 2025)'), filler sentences ('The ensembl_rest package provides a Pythonic interface to all Ensembl REST API endpoints'), and three generic workflow lists that add prose without detail. The over-explanation is more than minor, so it sits below the anchor 4.	3 / 5
Actionability	Mostly executable guidance: real REST endpoints with headers ('/lookup/symbol/homo_sapiens/BRCA2') and a complete error-handling function with 429 retry logic. Not fully copy-paste-ready across the board — workflow steps are abstract ('Export results', 'Generate report') with no code, and the ensembl_rest client API is used without verification.	4 / 5
Workflow Clarity	Three numbered workflows give a clear sequence, but they contain no validation checkpoints, no per-step commands, and no error-recovery guidance — checkpoints are missing rather than explicit. Queries are read-only, so the destructive/batch cap is not triggered.	3 / 5
Progressive Disclosure	Good structure with a well-signaled, one-level-deep bundle: references/api_endpoints.md (17 endpoint categories, verified present) and scripts/ensembl_query.py (verified, matches its description). Minor gap: the script is listed under Resources but never invoked in any example or workflow, leaving it unintegrated with the body's guidance.	4 / 5
	Total	14 / 20 Passed

Description

75%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 specific, action-rich description with strong distinctiveness in a clear domain niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and slightly limits natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions' — with comprehensive coverage of the skill's capabilities in third-person voice. Coverage has no notable gaps, matching the top anchor rather than the 'minor gaps' anchor below it.	5 / 5
Completeness	The 'what' is clear (query the Ensembl genome database REST API, with a concrete action list), but there is no 'Use when...' clause; 'for genomic research' is only a weak implied trigger. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('gene lookups', 'sequence retrieval', 'orthologs', 'VEP') that a user would plausibly say, but a few natural terms are missing (e.g., 'Ensembl ID', 'rsID', 'homologs/paralogs', 'DNA/protein sequence'). Falls between the 'good coverage' and 'comprehensive with synonyms' anchors.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers — 'Ensembl genome database REST API', 'VEP', 'orthologs' — making it unlikely to fire for the wrong skill; minimal conflict risk with other database or bioinformatics skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/ensembl-database/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.