opentargets-database

Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/opentargets_database/SKILL.md

Quality

Content

70%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.

The body is a well-structured, actionable command reference with good validation guidance and a clean one-level-deep reference split, but it is held back by a broken custom-query example and minor repetition of the pagination warning.

Suggestions

Fix the custom-query bash block: add the opening quote (`custom-query 'query drugsForDisease...`) and a `\` continuation before `--output` so the example is copy-paste executable.

De-duplicate the incomplete-results warning: keep the detailed version in the L2G section and shorten the Tips entry to a one-line pointer to avoid repeating the same guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the pagination / 'count vs rows' incomplete-results warning is restated in both the L2G section and the Tips section, and 'Quick Reference' overlaps lightly with 'Core Rules'.	2 / 3
Actionability	The subcommand reference is concrete with real IDs and copy-paste-ready invocations, but the flagship 'Advanced GraphQL Queries' custom-query example is broken — it is missing the opening quote before `query` and the line-continuation backslash before `--output` — so it is not executable as written.	2 / 3
Workflow Clarity	Commands are unambiguous and the body gives an explicit validation checkpoint (compare the API `count` field to rows returned) with a feedback loop (increase `--page-size` or inform the user of partial results), plus a sequenced license-notification prerequisite.	3 / 3
Progressive Disclosure	The overview keeps command usage inline while deferring full schema details to a clearly signaled, one-level-deep reference (references/OpenTargets_GraphQL_Guide.md, which exists), and the wrapper script lives in scripts/ — content is appropriately split.	3 / 3
	Total	10 / 12 Passed

Description

67%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.

The description is specific and clearly occupies a distinct niche, but it is missing an explicit 'Use when...' trigger clause and leans on domain jargon rather than natural user phrasing. Adding trigger guidance would lift the weakest dimensions.

Suggestions

Append a 'Use when ...' clause listing natural triggers (e.g., 'Use when identifying druggable targets for a disease, ranking target-disease associations, or exploring tractability and known drugs').

Soften jargon by adding plain-language variants a user might actually say, such as 'drug targets', 'genetic evidence for a disease', or 'clinical candidates'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'target-disease associations', 'drug target discovery', 'tractability/safety data', 'genetics/omics evidence', 'known drugs' — rather than vague abstractions.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' trigger guidance, so the 'when' is only implied; per the rubric a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Domain terms like 'drug target discovery', 'known drugs', and 'therapeutic target identification' are reasonably natural for a researcher, but the phrasing leans on Open Targets jargon (tractability, omics) and omits plainer variations a user might say.	2 / 3
Distinctiveness Conflict Risk	Naming the specific 'Open Targets Platform' plus therapeutic-target-discovery scope gives it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: google-deepmind/science-skills
Path: skills/opentargets_database/SKILL.md
Commit: 0b42509

Reviewed: 7 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.