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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-drug-research/SKILL.md

Quality

Content

68%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 dense, highly actionable research workflow with concrete tool chains, fallback rules, and type-normalization guidance, weakened mainly by missing referenced bundle files that break progressive disclosure and some cross-section redundancy.

Suggestions

Ship the referenced bundle files (REPORT_TEMPLATE.md, REPORT_GUIDELINES.md, TOOLS_REFERENCE.md, CHECKLIST.md, EXAMPLES.md) so the body's navigation links resolve, or inline the essential parts and drop the dangling references.

Consolidate the tool/fallback listings that currently repeat across the PATH sections, the Fallback Chains table, and the Quick Reference table into a single canonical reference to reduce redundancy.

Add an explicit inline validation checkpoint after key workflow steps (e.g., 'Verify identifiers resolved before advancing to Section 2') instead of relying solely on the external checklist.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's knowledge (no definitions of FAERS/PubChem), but fallback chains and tool listings are restated across the PATH sections, the Fallback Chains table, and the Quick Reference table, leaving minor redundancy to trim.	4 / 5
Actionability	Names specific tools, gives executable input-format rules (int→str, UPPERCASE FAERS names, SMILES as list), concrete thresholds (pChEMBL >= 6.0), explicit tool-avoidance guidance, and a citation template — copy-paste ready for an instruction-style tool skill.	5 / 5
Workflow Clarity	A clear 12-step progressive workflow with report-first ordering and a dedicated verification checklist plus mandatory-completeness principle, though inline validation checkpoints are delegated to CHECKLIST.md rather than embedded at each step.	4 / 5
Progressive Disclosure	The body is well-organized and signals one-level-deep references (REPORT_TEMPLATE.md, REPORT_GUIDELINES.md, TOOLS_REFERENCE.md, CHECKLIST.md, EXAMPLES.md), but none of these referenced bundle files actually exist, so navigation is broken despite the clean in-file structure.	3 / 5
	Total	16 / 20 Passed

Description

88%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-targeted description that concretely lists capabilities and gives explicit, natural trigger phrases for when to use the skill. Voice is appropriately third person and there is no fluff or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history' — covering the profiling domain comprehensively with no real gaps.	5 / 5
Completeness	Explicitly answers 'what' (the profiling capabilities) and 'when' via a concrete 'Use for ... queries, ... reports, ... profiles for clinicians, researchers, or regulatory work' trigger clause.	5 / 5
Trigger Term Quality	Includes natural user phrases like "'tell me about drug X' queries", 'full drug investigation reports', and 'drug profiles', but omits a few everyday synonyms such as 'drug info' or 'look up a drug'.	4 / 5
Distinctiveness Conflict Risk	A clear drug-profiling niche anchored to specific data sources (FAERS, pharmacogenomics) with distinct triggers; minor conceptual overlap with sibling biomedical research skills keeps it just below 5.	4 / 5
	Total	18 / 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: plugin/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.