tooluniverse-drug-repurposing

Identify drug repurposing candidates using ToolUniverse for target-based, compound-based, and disease-driven strategies. Searches existing drugs for new therapeutic indications by analyzing targets, bioactivity, safety profiles, and literature evidence. Use when exploring drug repurposing opportunities, finding new indications for approved drugs, or when users mention drug repositioning, off-label uses, or therapeutic alternatives.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/pharma/tooluniverse-drug-repurposing/SKILL.md

Quality

Content

50%

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 and well-sectioned with real ToolUniverse tool calls, but it suffers from redundancy across overlapping sections, lacks validation checkpoints in its batch workflows, and is a monolithic wall of inline content with no progressive disclosure into reference files.

Suggestions

Consolidate redundant tool usage across Quick Start, Complete Workflow, Common Patterns, and Advanced Techniques into a single canonical example, then reference it — remove the duplicated calls to recover token budget.

Add explicit validation checkpoints between phases (e.g., assert disease_info returned an id before fetching targets; verify drug lists are non-empty before scoring) so batch operations fail fast with clear recovery.

Split the advanced techniques, use-case catalogues, and the full 'Key ToolUniverse Tools' reference into bundled reference files (references/) and link to them one level deep, leaving SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The code itself is lean and avoids explaining concepts Claude already knows, but the body is ~596 lines with substantial redundancy — Quick Start, Complete Workflow, Common Patterns, and Advanced Techniques repeat the same tooluniverse calls, so it could be tightened considerably. Not a 3 because of the duplicated content; not a 1 because the prose is not padded with generic explanation.	2 / 3
Actionability	Many real, specific tool calls make most examples copy-paste ready, but template placeholders like '[disease_name]' and data-structure mismatches (the scoring function reads drug['target_association_score'] / drug['safety_profile'] which the collection code never populates) leave key details incomplete.	2 / 3
Workflow Clarity	The five-phase sequence (target analysis → drug discovery → safety → literature → scoring) is clearly ordered, but there are no explicit validation/verification checkpoints for the batch loops, which caps workflow clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	Headers are well organized, but the skill is monolithic — no own reference files exist (references/scripts/assets absent) and content that should be split out (advanced techniques, use cases, full tool catalogue) is all inline in SKILL.md.	2 / 3
	Total	8 / 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 exemplary: it states concrete capabilities, provides natural trigger terms, answers both what and when, and occupies a distinct niche. It is concise and uses proper third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Identify drug repurposing candidates', 'Searches existing drugs for new therapeutic indications', and 'analyzing targets, bioactivity, safety profiles, and literature evidence' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what ('Identify…candidates…analyzing targets, bioactivity, safety profiles, and literature evidence') and when via a clear 'Use when…' trigger clause, satisfying both halves.	3 / 3
Trigger Term Quality	Strong coverage of natural user terms ('drug repurposing opportunities', 'finding new indications for approved drugs', 'drug repositioning', 'off-label uses', 'therapeutic alternatives') that a user would naturally say.	3 / 3
Distinctiveness Conflict Risk	A clear niche (drug repurposing via ToolUniverse) with distinct triggers unlikely to fire for unrelated skills; written in third person ('Identify', 'Searches') with no voice penalty.	3 / 3
	Total	12 / 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
skill_md_line_count	SKILL.md is long (596 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/tooluniverse-drug-repurposing/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.