open-targets-search

Search Open Targets drug-disease associations with natural language queries. Target validation powered by Valyu semantic search.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pharma/open-targets-search/SKILL.md

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is actionable and has a clear, well-sequenced setup workflow with a feedback loop, but it is let down by a path-resolution inconsistency that breaks copy-paste usability and by references to unbundled scripts. Trimming marketing and integration sections would improve token efficiency.

Suggestions

Make every command example use the resolved `$OPEN_TARGETS_SCRIPT` path so examples are truly copy-paste ready, instead of mixing in relative `scripts/search` forms.

Trim the 'Why This Skill is Powerful' marketing bullets and move the Python/TypeScript integration snippets to a separate reference file.

Ensure the referenced `scripts/search` and `scripts/search.mjs` files actually ship in the bundle, or note their absence explicitly.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete command examples and no basic-concept explanations, but the 'Why This Skill is Powerful' marketing bullets and the inline Python/TypeScript integration sections add padding that could be trimmed.	2 / 3
Actionability	Commands are concrete, but the later examples use the relative form `scripts/search "query"` which the skill's own CRITICAL section warns will not resolve — so examples are not truly copy-paste ready, matching the incomplete-guidance anchor.	2 / 3
Workflow Clarity	The API-key setup flow is a clear sequenced process with a `setup_required` feedback loop and explicit retry step, and error handling (success field, exit codes) is documented, matching the top anchor.	3 / 3
Progressive Disclosure	The skill is a single well-sectioned file, but it references a `scripts/` directory that is not present in the bundle and keeps integration material inline that could be split out, so it is not cleanly one-level-deep.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 clear and domain-specific about what the skill does, but it omits an explicit "when to use" trigger clause and only names a single action. Adding concrete use-case triggers would lift completeness and specificity.

Suggestions

Add an explicit 'Use when...' clause listing natural trigger scenarios (e.g., target validation, drug-disease associations, drug repurposing).

Name additional concrete actions (e.g., retrieve evidence scores, find genetic associations) to raise specificity.

Replace the generic 'natural language queries' phrasing with user-facing terms like 'drug repurposing' or 'genetic evidence'.

Dimension	Reasoning	Score
Specificity	The description names the domain and a concrete action ("Search Open Targets drug-disease associations with natural language queries"), but it lists only a single action rather than multiple specific concrete actions, so it falls short of the top anchor.	2 / 3
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain keywords like "Open Targets", "drug-disease associations", and "target validation" are present, but "natural language queries" is not a term a user would naturally say and common variations are missing, matching the mid anchor.	2 / 3
Distinctiveness Conflict Risk	The Open Targets drug-disease-association niche with Valyu semantic search is clearly distinct and unlikely to trigger for the wrong skill, matching the top anchor.	3 / 3
	Total	9 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 9 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/open-targets-search/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.