CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/opentargets_database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is well-structured, highly actionable, and includes a real validation feedback loop for incomplete/large results, with most content appropriately split into a single one-level-deep reference. The main gaps are a broken custom-query code example and a slightly malformed reference link.

Suggestions

Fix the custom-query example: add the missing opening quote for the GraphQL query string and a `\` line continuation before the `--output` line so the snippet is copy-paste executable.

Correct the reference link to include the `.md` extension ([references/OpenTargets_GraphQL_Guide.md](references/OpenTargets_GraphQL_Guide.md)) so navigation resolves.

Tighten the Overview and L2G sections to remove phrasing that reiterates the description, pushing conciseness toward 5.

DimensionReasoningScore

Conciseness

The body is mostly lean, assumes Claude's competence (no basic PDF/library-style padding), but the Overview mildly reiterates the description and the L2G and Tips sections could be tightened, fitting the 'efficient with minor over-explanation' anchor.

4 / 5

Actionability

Concrete, copy-pasteable `uv run` commands with real IDs (e.g. MONDO_0008383, ENSG00000156515) cover common cases, but the custom-query example is not executable as written (missing opening quote for the query string and a missing `\` line-continuation before `--output`), leaving a minor gap.

4 / 5

Workflow Clarity

Subcommand workflows are clearly sequenced and there is an explicit feedback loop for the main batch risk (compare `count` to returned `rows`, then increase `--page-size` or inform the user), but checkpoints are scattered rather than presented as a clean checklist.

4 / 5

Progressive Disclosure

Good structure with the bulk schema detail split into a one-level-deep reference (OpenTargets_GraphQL_Guide.md) and clearly signaled; the reference link drops the `.md` extension and some inline command reference could arguably live in the reference, leaving a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

70%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.

The description clearly conveys the platform and its concrete data capabilities but omits any explicit 'Use when' trigger guidance, capping completeness. Specificity and trigger-term quality are strong but stop just short of comprehensive.

Suggestions

Add an explicit trigger clause such as 'Use when identifying therapeutic targets, drug target discovery, or ranking target-disease associations.' to lift completeness above 3.

Include natural synonyms or phrasings a user might say (e.g. 'drug repurposing', 'GWAS target prioritization') to push trigger-term quality toward 5.

Consider splitting the single 'Query ... for' verb into distinct action verbs (e.g. 'Rank target-disease associations, discover drug targets, assess tractability/safety') to strengthen specificity.

DimensionReasoningScore

Specificity

Lists several specific concrete data domains ('target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs') but they are all scoped under a single verb ('Query'), so it falls just short of the comprehensive multi-action anchor at 5.

4 / 5

Completeness

It clearly answers 'what' (Query Open Targets Platform for the listed data) but has no explicit 'Use when...' trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Good coverage of natural domain keywords a researcher would say (drug target discovery, tractability/safety, genetics/omics evidence, known drugs), but it lacks synonyms and the 5-anchor requires comprehensive synonyms/extensions which are absent.

4 / 5

Distinctiveness Conflict Risk

It names the specific named platform ('Open Targets Platform') and a distinct domain (therapeutic target identification), giving a clear niche with minimal conflict risk against other skills.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Revision

4de6786

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill