tooluniverse-drug-repurposing

Identify drug repurposing candidates via target-based, compound-based, and disease-based strategies. Combines drug-target-disease network reasoning with mechanism rationale, clinical-trial precedent, and patent/regulatory feasibility. Use for hypothesis-generating repurposing for orphan diseases, finding existing drugs for new indications, and prioritizing candidates by evidence and feasibility.

Quality

83%

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

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 dense, actionable, and well-sequenced with strong tool-specific gotchas and a decision framework, but the dose-feasibility code is a non-executable stub and all four referenced bundle files are missing, breaking progressive disclosure navigation.

Suggestions

Provide the referenced bundle files (PROCEDURES.md, REFERENCE.md, EXAMPLES.md, REPORT_TEMPLATE.md) or remove the references and inline the essential content, since none currently exist.

Replace the `pass` stub in check_dose_feasibility with executable parsing logic and use a consistent tool-calling convention matching the Quick Start (tu.tools.<name> vs tu.run_one_function).

Convert the interpret-and-combine questions into explicit validate-then-proceed checkpoints (e.g., 'Stop and mark speculative if target association < 0.5') to harden the batch workflow.

Dimension	Reasoning	Score
Conciseness	Largely lean and information-dense with minimal concept padding, but a few sections restate earlier points (e.g., the 'Key principle' restating the dose-feasibility warning) and could be trimmed.	4 / 5
Actionability	Provides executable Quick Start code with real response-path navigation and concrete parameter gotchas, but the dose-feasibility function is a stub with `pass` and uses an inconsistent calling convention (tu.run_one_function vs tu.tools.<name>).	4 / 5
Workflow Clarity	Clear five-phase sequence with a strategy-selection gate, a scoring/grading synthesis framework, and interpret-and-combine verification questions; minor validation gaps remain because checkpoints are framed as interpretive questions rather than hard stop/proceed gates.	4 / 5
Progressive Disclosure	Well-organized into overview plus clearly signaled one-level-deep references (PROCEDURES.md, REFERENCE.md, EXAMPLES.md, REPORT_TEMPLATE.md), but those referenced bundle files do not actually exist, so navigation fails when followed.	4 / 5
	Total	16 / 20 Passed

Description

92%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 is specific, complete, and distinctive, clearly stating both the capability and concrete use-when triggers. It would benefit only from adding common synonyms (repositioning, off-label) to broaden trigger matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across three named strategies (target-based, compound-based, disease-based) and several evidence dimensions (network reasoning, mechanism rationale, clinical-trial precedent, patent/regulatory feasibility), giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	Explicitly answers both what ('Identify... candidates via... strategies', 'Combines... reasoning with...') and when ('Use for hypothesis-generating repurposing for orphan diseases, finding existing drugs for new indications, and prioritizing candidates...').	5 / 5
Trigger Term Quality	Good natural keyword coverage ('drug repurposing', 'existing drugs for new indications', 'orphan diseases'), but missing common synonyms like 'drug repositioning' or 'off-label'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (drug repurposing, orphan diseases, patent/regulatory feasibility) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-drug-repurposing/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.