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.

77

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

A high-signal, actionable body with excellent tool-specific guidance and a clear phased workflow. Its main weaknesses are a non-executable dose-feasibility code skeleton and four referenced bundle files that do not exist on disk, which breaks progressive-disclosure navigation.

Suggestions

Ship the referenced bundle files (PROCEDURES.md, REFERENCE.md, EXAMPLES.md, REPORT_TEMPLATE.md) — the body delegates "detailed step-by-step procedures and code patterns" to PROCEDURES.md, but none of the four files exist, so progressive-disclosure links resolve to nothing.

Make the Drug-Target Dose Feasibility Check executable: replace the `pass` placeholder with real ChEMBL response parsing (extract IC50/Ki, compute the original-vs-new potency ratio), or explicitly state that it is a template to be adapted.

Tighten the repeated dose-feasibility point: the "100x approved dose" idea recurs in the intro, a best-practice item, code comments, and the key-principle line — consolidate to a single statement to recover tokens.

DimensionReasoningScore

Conciseness

Dense with non-obvious, tool-specific signal (param gotchas like "query= (NOT target_name=)" and response paths like "data.search.hits[0].id") and avoids explaining concepts Claude already knows; the only slack is localized repetition of the dose-feasibility point, not structural verbosity.

3 / 3

Actionability

The Quick Start is copy-paste-ready executable Python and the tool reference gives exact params, response paths, and gotchas; the lone gap is the "Drug-Target Dose Feasibility Check" block, which is a skeleton ending in `pass` rather than runnable code.

3 / 3

Workflow Clarity

A clear 5-phase overview, explicit "identify which strategy applies FIRST" sequencing, and validation checkpoints with numeric thresholds (association score >0.5, IC50 >10x ratio) plus the "LOOK UP DON'T GUESS" rule.

3 / 3

Progressive Disclosure

The body is well-organized and signals one-level-deep references clearly ("See: PROCEDURES.md" plus a Reference Files section), but all four referenced files — PROCEDURES.md, REFERENCE.md, EXAMPLES.md, REPORT_TEMPLATE.md — are absent (no references/scripts/assets bundles exist), so navigation dead-ends.

2 / 3

Total

11

/

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.

A strong, well-structured description that states concrete strategies, natural trigger terms, and an explicit use-when clause. The only mild weakness is a slight over-claim: "patent/regulatory feasibility" is broader than the body's IP-only coverage.

DimensionReasoningScore

Specificity

Names three concrete strategies ("target-based, compound-based, and disease-based strategies") and lists the analyses it combines ("drug-target-disease network reasoning with mechanism rationale, clinical-trial precedent, and patent/regulatory feasibility"), matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers what ("Identify drug repurposing candidates via ... strategies") and when with an explicit "Use for ..." trigger clause, satisfying both halves of the top anchor.

3 / 3

Trigger Term Quality

Uses natural terms a user would actually say — "drug repurposing", "orphan diseases", "existing drugs for new indications", "prioritizing candidates" — giving good coverage rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The repurposing framing and "Use for hypothesis-generating repurposing for orphan diseases, finding existing drugs for new indications" triggers carve a clear niche distinct from sibling disease/compound gathering skills.

3 / 3

Total

12

/

12

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.