embl-ebi-ols

Query and search the EMBL-EBI Ontology Lookup Service (OLS) for biomedical ontology terms, definitions, and hierarchies across 250+ ontologies (e.g., GO, DOID, HP). Use when the user asks to search for terms, retrieve details, navigate hierarchies (parents, children, ancestors), look up properties and individuals, get autocomplete suggestions, or access ontology metadata and statistics.

Quality

92%

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

85%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 well-structured, highly actionable skill body with clear sequencing and good externalization of detail. The main weakness is redundancy: the same commands appear in three sections, inflating token usage without adding guidance value.

Suggestions

Consolidate overlapping command examples: 'Quick Recipes', 'Utility Scripts', and 'Workflow' repeat the same scripts and flags — keep one canonical set of examples and cross-reference it from the others to reduce token load (lowest-scoring conciseness dimension).

Move the detailed per-script --option listings into references/api_reference.md (or a dedicated CLI reference file), keeping SKILL.md focused on recipes and workflow so the overview stays lean.

Add a one-line 'Citation' note in the Reference section pointing to references/citation.bib so all bundle files are discoverable from the body.

Dimension	Reasoning	Score
Conciseness	Largely lean and free of explaining known concepts, but the same script commands are repeated across 'Quick Recipes', 'Utility Scripts', and the 'Workflow' section, so not every token earns its place and the body could be tightened.	2 / 3
Actionability	Every section gives fully executable 'uv run scripts/...' commands with concrete flags, output paths, and complete option listings — copy-paste ready with no pseudocode.	3 / 3
Workflow Clarity	The multi-step query block is explicitly sequenced ('exactly 2 steps') with intermediate --output files as checkpoints and an ontology-selection rule, and the 8-step Workflow is ordered; read-only queries do not require destructive-validation feedback loops.	3 / 3
Progressive Disclosure	Clear overview with scripts externalized to scripts/ and a well-signaled one-level reference to references/api_reference.md (verified to exist); content is sensibly split between SKILL.md recipes/options and the API-endpoint reference, though citation.bib is present but unreferenced.	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, third-person description that clearly states capabilities, gives explicit 'Use when' triggers with natural phrasing, and carves out a distinctive niche. No significant weaknesses; the only minor gap is the lack of explicit .obo/.owl file-format trigger terms.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions (search for terms, retrieve details, navigate hierarchies, look up properties and individuals, autocomplete, metadata/statistics), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers both what (query/search OLS for terms, definitions, hierarchies across 250+ ontologies) and when via an explicit 'Use when the user asks to...' trigger clause.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered ('search for terms', 'autocomplete suggestions', 'navigate hierarchies (parents, children, ancestors)', 'ontology metadata and statistics'), giving good coverage of terms a biomedical user would actually say.	3 / 3
Distinctiveness Conflict Risk	The EMBL-EBI OLS / biomedical-ontology niche with concrete examples (GO, DOID, HP) is highly specific with distinct triggers, making conflict with other skills unlikely.	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/embl_ebi_ols/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.