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

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pharma/opentargets-database/SKILL.md

Quality

Content

42%

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 with concrete workflow examples and rich domain detail, but its actionability and progressive disclosure are undermined by code and reference files that are not actually present in the bundle, and workflows lack validation checkpoints.

Suggestions

Provide the missing `scripts/query_opentargets.py` and the three `references/*.md` files, or remove the references and inline the genuinely needed detail, so navigation is not broken.

Add executable, self-contained examples (with import/install context or direct GraphQL calls) instead of relying entirely on helper functions that are not bundled.

Insert explicit validation checkpoints in the workflows — e.g. verify API responses, handle pagination/errors, and confirm identifier resolution before proceeding — to support fragile/batch operations.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific, but the ~374-line body explains somewhat known concepts (clinical trial phase semantics, association-score caveats repeated across sections) and restates evidence types both inline and in the missing references, so it could be tightened.	2 / 3
Actionability	Numerous code examples, but they all call helper functions from a `scripts/query_opentargets.py` that does not exist and are essentially pseudocode with assumed returns; there are no installation steps or runnable snippets, so guidance is concrete but not executable as written.	2 / 3
Workflow Clarity	A clear 7-step core workflow plus four sequenced common workflows is present, but there are no validation/verification checkpoints (e.g. checking API responses, paging/error handling) and operations lack explicit feedback loops.	2 / 3
Progressive Disclosure	The body heavily references `scripts/query_opentargets.py` and `references/api_reference.md`, `references/evidence_types.md`, and `references/target_annotations.md`, but none of these files exist — navigation is broken and large reference-style detail is inlined in the overview rather than split into the referenced files.	1 / 3
	Total	7 / 12 Passed

Description

67%

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 occupies a clear, distinct niche with third-person voice, but it omits an explicit 'when to use' trigger clause, capping completeness. Trigger-term coverage could include more natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers (e.g. 'Use when identifying or prioritizing therapeutic drug targets, finding drug-disease associations, or assessing target tractability and safety').

Incorporate more natural user-facing keywords alongside the technical terms (e.g. 'drug repurposing', 'GWAS', 'gene-disease associations').

Tighten the comma-separated list into a scannable what-then-when structure to make the trigger guidance unambiguous.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Query ... target-disease associations', 'drug target discovery', 'tractability/safety data', 'genetics/omics evidence', 'known drugs' — each a distinct capability rather than vague language.	3 / 3
Completeness	Clearly answers 'what' through enumerated capabilities, but provides no 'when' trigger — there is no 'Use when...' clause, so per the guidelines completeness caps at 2.	2 / 3
Trigger Term Quality	Includes natural domain terms a user might say ('drug target discovery', 'known drugs', 'therapeutic target identification') but relies on technical/jargon phrasing and omits common user variations like 'gene-disease', 'GWAS', or 'drug repurposing'.	2 / 3
Distinctiveness Conflict Risk	The Open Targets Platform niche is specific and well-scoped to therapeutic target identification, with triggers unlikely to fire 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
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/opentargets-database/SKILL.md
Commit: df37802

Reviewed: 4 minutes 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.