tooluniverse-drug-drug-interaction

Assess drug-drug interactions — CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management recommendations. Use for polypharmacy review, prescribing decision support, and safety analysis when adding or switching drugs.

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 well-sequenced, validated workflow and a properly signaled bundled script. Its main weakness is conciseness and progressive disclosure: substantial inline pharmacology teaching and a duplicated interaction table inflate the overview that would be better split into reference files.

Suggestions

Move the full covered-interactions table and the detailed UGT/perpetrator-victim paradigm into a references/ file (e.g. INTERACTIONS.md), keeping SKILL.md as a lean overview that points to it one level deep.

Trim general pharmacology exposition (e.g. what glucuronidation is, basic inhibitor/inducer definitions) that Claude already knows; retain only the DDI-specific reasoning algorithms and decision rules.

Consolidate the duplicated interaction list — it appears both inline in the body and inside pharmacology_ref.py — so the body signals the script rather than restating its contents.

Dimension	Reasoning	Score
Conciseness	The body is ~330 lines and includes a full interaction table duplicated from the bundled script plus extensive inline teaching of general pharmacology (UGT paradigm, perpetrator-victim model, cascading effects, ADR attribution) that Claude largely already knows; it is mostly efficient but could be tightened and offloaded to a reference file.	2 / 3
Actionability	It provides copy-paste-ready script invocations with exact flags (e.g. "--type ugt_inhibitor --drug [drug]"), named MCP tools, a numeric risk-scoring formula, an explicit output report structure, and a success-criteria checklist — fully executable guidance.	3 / 3
Workflow Clarity	The Tool Workflow is clearly sequenced (Phases 1–6) with a MANDATORY report-first progressive update and a terminal Success Criteria checklist that acts as an explicit validation gate and feedback loop, matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	The one bundle file (scripts/pharmacology_ref.py) is well-signaled and one level deep, but the SKILL.md itself is monolithic — the interaction table and detailed reasoning paradigms sit inline rather than being split into reference files, fitting the 'content that should be separate is inline' 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.

A strong, third-person description that clearly states concrete capabilities and provides an explicit 'Use for…' trigger clause covering natural clinical phrasing. It is distinguishable and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — "CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management recommendations" — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It answers both 'what' (the Assess… verb chain) and 'when' via an explicit "Use for polypharmacy review, prescribing decision support, and safety analysis when adding or switching drugs" clause, satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Natural phrasing a clinician would actually say appears throughout: "drug-drug interactions", "polypharmacy review", "prescribing decision support", "safety analysis", and "adding or switching drugs", giving good coverage of common variations rather than only technical jargon.	3 / 3
Distinctiveness Conflict Risk	The DDI niche is specific and the triggers are domain-distinct, making it unlikely to fire for unrelated skills; it is well above the 'somewhat specific but could still overlap' level.	3 / 3
	Total	12 / 12 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-drug-interaction/SKILL.md
Commit: 089eb8e

Reviewed: about 6 hours 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.