Name: tooluniverse-drug-research
Rating: 69.6 (1 reviews)
Author: mims-harvard

tooluniverse-drug-research

Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory work.

Quality

85%

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

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

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.

A well-organized, domain-specific routing skill that is dense and actionable with strong fallback/error-recovery guidance. It is held back from top marks by distributed (non-inline) validation gates, pseudo-call rather than complete executable examples, and referenced bundle files that are absent from the bundle.

Suggestions

Inline explicit validation gates in the 12-step workflow (e.g., 'Validate: confirm Section 4 is non-empty before moving on') so checkpoints sit in the step sequence itself rather than only in surrounding CRITICAL notes.

Add at least one fully-parameterized example tool invocation inline (real CID/SMILES values) so the routing examples are copy-paste executable, not just pseudo-calls.

Ship the referenced bundle files (REPORT_TEMPLATE.md, REPORT_GUIDELINES.md, TOOLS_REFERENCE.md, CHECKLIST.md, EXAMPLES.md) alongside SKILL.md so the progressive-disclosure navigation links actually resolve.

Dimension	Reasoning	Score
Conciseness	Dense, token-efficient tables for fallback chains, type normalization, and tool routing assume Claude's knowledge of the data sources, but the 'LOOK UP, DON'T GUESS' motivational section and overlap between the Research Paths tool lists and the Quick Reference table add mild redundancy.	4 / 5
Actionability	Highly actionable routing with exact tool names, an identifier-resolution chain, and concrete type-normalization rules (UPPERCASE FAERS names, full CHEMBL ID format, SMILES as a list), but inline examples are pseudo-calls rather than fully-parameterized executable invocations, deferring params to TOOLS_REFERENCE.md.	4 / 5
Workflow Clarity	A clear 12-step progressive writing sequence plus per-path 'CRITICAL' validation notes, mandatory completeness, and fallback-chain error recovery; however validation is distributed across notes rather than inline-gated within the step sequence, leaving minor checkpoint gaps.	4 / 5
Progressive Disclosure	Well-structured overview with clearly signaled one-level-deep references (REPORT_TEMPLATE.md, REPORT_GUIDELINES.md, TOOLS_REFERENCE.md, CHECKLIST.md, EXAMPLES.md) and an Additional Resources index, but none of these referenced files are present in the bundle, so navigation links currently dangle and cannot be verified.	4 / 5
	Total	16 / 20 Passed

Description

96%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, specific description that clearly states what the skill does and when to use it, with excellent natural trigger terms including a literal user query form. Only minor distinctiveness risk from the drug-interaction facet overlapping a sibling skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete profiling facets — 'mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history' — giving comprehensive coverage of the drug-profiling domain rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (comprehensive drug profiling with enumerated facets) and 'when' via a concrete 'Use for ...' clause with multiple trigger phrases, matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	Includes a literal user phrasing ('tell me about drug X' queries) plus natural use-case triggers ('full drug investigation reports', 'assembling drug profiles for clinicians, researchers, or regulatory work'), covering the terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The specialized terms (FAERS, pharmacogenomics) carve a clear niche, but the 'drug interactions' facet overlaps a sibling drug-drug-interaction skill noted in the body, creating minor conflict risk with a closely related skill.	4 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 8 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-drug-research/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.