tooluniverse-drug-target-validation

Comprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ ToolUniverse tools. Produces a quantitative Target Validation Score (0-100) with GO/NO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or "is X a good drug target for Y?"

Quality

88%

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

Quality

Content

77%

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

The body is highly actionable with a clearly sequenced, validated workflow and valuable API-quirk corrections Claude would not otherwise know. Its weaknesses are conciseness (a large placeholder report template and duplicated parameter tables) and the absence of progressive disclosure for a skill this size.

Suggestions

Move the large report template and the 'Quick Reference: Verified Tool Parameters' table into separate reference files (e.g. references/report-template.md, references/tool-params.md) and link to them from SKILL.md to improve progressive disclosure and cut inline tokens.

Deduplicate the parameter guidance: the 'Known Parameter Corrections' table and the 'Quick Reference' table cover overlapping ground — merge them into one reference.

Trim the report template's '[Researching...]' placeholder skeleton to a compact outline so the body stays lean while still defining report structure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient concrete tool calls and parameter corrections, but the ~175-line report template filled with '[Researching...]' placeholders and the duplicated parameter tables ('Known Parameter Corrections' vs 'Quick Reference: Verified Tool Parameters') could be tightened; not every token earns its place.	2 / 3
Actionability	Provides fully executable python tool calls with exact parameters (e.g. 'tu.tools.ensembl_lookup_gene(gene_id=ensembl_id, species="homo_sapiens")'), explicit scoring logic, and a worked EGFR/NSCLC example — copy-paste ready.	3 / 3
Workflow Clarity	Phases 0-10 are clearly sequenced with 'Phase 0 ... ALWAYS FIRST', a mandatory completeness checklist, fallback chains, and evidence-grading checkpoints providing explicit validation and error-recovery feedback loops.	3 / 3
Progressive Disclosure	The skill is well-organized by section but monolithic at ~1200 lines with no bundle files; large blocks (the report template, parameter reference tables, example execution) that could be split into separate reference files are inlined, matching the level-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 third-person, specific, and complete, with an explicit trigger clause and natural user phrasings. It clearly communicates both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions across '10 dimensions (disambiguation, disease association, druggability, ...)' and 'Produces a quantitative Target Validation Score (0-100) with GO/NO-GO recommendation', listing multiple specific capabilities rather than vague language.	3 / 3
Completeness	It clearly answers both what (validate drug targets across 10 dimensions, produce a 0-100 score with GO/NO-GO) and when (explicit 'Use when...' trigger clause), matching the level-3 anchor.	3 / 3
Trigger Term Quality	The 'Use when users ask about target validation, druggability assessment, target prioritization, or "is X a good drug target for Y?"' clause gives good coverage of natural phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche (computational drug-target validation with a quantitative score) and the distinctive 'is X a good drug target for Y?' trigger make it unlikely to fire for sibling tooluniverse skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1207 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/tooluniverse-drug-target-validation/SKILL.md
Commit: df37802

Reviewed: 2 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.