CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

The canonical home for this skill is tooluniverse-drug-repurposing in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

A content-rich, well-organized skill body with strong executable examples and tool-specific param guidance. Its main weaknesses are repeated dose-feasibility prose, a pseudocode featured procedure, implicit validation checkpoints, and four dangling references to non-existent bundle files.

Suggestions

Create the referenced bundle files (PROCEDURES.md, REFERENCE.md, EXAMPLES.md, REPORT_TEMPLATE.md) or remove the references, so the progressive-disclosure navigation does not dead-end.

Consolidate the dose-feasibility guidance into one location; it is currently repeated across Best Practices #4, the Computational Procedure, and the closing Key principle.

Complete the check_dose_feasibility code block with actual IC50/Ki parsing logic instead of ending in `pass`, since it is presented as a featured executable procedure.

Make workflow checkpoints explicit (e.g., 'Validate target association >0.5 before proceeding to Phase 2') rather than leaving them as implicit interpretive questions.

DimensionReasoningScore

Conciseness

Mostly efficient and rich in high-value tool-specific knowledge (param gotchas like `query=` not `target_name=`, response nesting paths), but the dose-feasibility principle is restated at least three times (Best Practices #4, the Computational Procedure intro, and the closing 'Key principle') and could be tightened.

3 / 5

Actionability

Quick Start is fully executable with real tool calls and response paths, and the tool catalog gives concrete params, but the featured Computational Procedure ends in `pass # Parse actual values from results`, leaving the central helper as pseudocode — a minor but real gap.

4 / 5

Workflow Clarity

A clear five-phase sequence is present with synthesis guidance, but checkpoints are implicit (interpretive questions) rather than explicit validate-then-proceed gates, and the detailed step-by-step procedures are deferred to PROCEDURES.md which does not exist.

3 / 5

Progressive Disclosure

Section structure is clear and references are explicitly signaled (dedicated Reference Files section, inline 'See: PROCEDURES.md'), but all four referenced files (PROCEDURES.md, REFERENCE.md, EXAMPLES.md, REPORT_TEMPLATE.md) are absent and no bundle directory exists, so navigation dead-ends and bulk content (tool catalog, scoring tables) is inlined that belongs in separate files.

3 / 5

Total

13

/

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.

A strong, well-constructed description that explicitly states both capabilities and use triggers with concrete, domain-specific language. The only minor gap is synonym coverage (e.g., 'drug repositioning', 'rare diseases').

DimensionReasoningScore

Specificity

Lists multiple concrete actions across three explicit strategies ("target-based, compound-based, and disease-based") plus four combined reasoning modes (network reasoning, mechanism rationale, clinical-trial precedent, patent/regulatory feasibility), matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers what ("Identify drug repurposing candidates via...") and when ("Use for hypothesis-generating repurposing for orphan diseases, finding existing drugs for new indications, and prioritizing candidates..."), with concrete trigger phrases in the Use clause.

5 / 5

Trigger Term Quality

Natural phrases users would say are present ("drug repurposing candidates", "existing drugs for new indications", "orphan diseases", "prioritizing candidates"), but common synonyms like "drug repositioning" and "rare diseases" are missing, so it sits just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (drug repurposing via ToolUniverse) with domain-specific triggers unlikely to fire for unrelated skills, matching the clear-niche-minimal-conflict anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.