Name: tooluniverse-drug-regulatory
Rating: 72 (1 reviews)
Author: mims-harvard

tooluniverse-drug-regulatory

Drug regulatory and approval research — FDA substance registry, ATC/EPC classification, EMA decisions, generic-drug status, FDA Orange Book exclusivity, NDA/BLA pathways. Use for jurisdiction-aware approval status (FDA vs EMA), generic vs brand availability, exclusivity expiry tracking, and regulatory pathway selection. Always specifies the market when reporting status.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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

Quality

Content

78%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.

The body is highly actionable with executable code and well-sequenced phases, and is mostly token-efficient. Its main weakness is progressive disclosure: it is a monolithic single-file API reference with no bundled reference files for the detailed per-tool specs, and it spends some tokens explaining regulatory concepts Claude already knows.

Suggestions

Move the per-tool parameter/return reference for each phase into separate files under references/ (e.g. references/tools.md) and keep SKILL.md as an overview with one-level-deep links, improving progressive_disclosure.

Trim the "Interpretation Guidance" section to only the non-obvious domain specifics (e.g. the 505(b)(2)-is-not-a-generic and exclusivity-blocks-generics points already in the intro) and remove generic explanations of NCE/ODE/PED durations and label-section distinctions that Claude already knows.

Add an explicit validation/retry checkpoint in at least the Orange Book and DailyMed phases (e.g. "if generics_available is null or total_count is None, re-query with the alternative identifier") to lift workflow_clarity.

Dimension	Reasoning	Score
Conciseness	Mostly lean with parameter/return specs and tight code snippets, but the "Reasoning Framework / Interpretation Guidance" section explains regulatory concepts (NCE/ODE/PED exclusivity, 505(b)(1) vs 505(b)(2), DailyMed section distinctions) that overlap with content Claude already knows, which could be trimmed.	4 / 5
Actionability	Executable copy-paste code for the common cases (substance lookup, class members, generic availability, adverse-reaction parsing) plus concrete parameter signatures and return shapes, with specific call-out gotchas (UPPERCASE brand_name, ttys="IN").	5 / 5
Workflow Clarity	The 8-phase overview diagram sequences steps clearly with named tools per phase, and "Common Mistakes" plus "Synthesis Questions" provide checkpoints; however there are no explicit validate->fix->retry feedback loops for the data-retrieval operations.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the SKILL.md inlines a large API reference across all 8 phases that would be more discoverable split into separate reference files; structure exists but content that belongs in separate files is inlined.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

The description is concrete, well-scoped, and explicitly pairs capabilities with a "Use for..." trigger clause, covering both what and when with natural keyword synonyms. It is concise and free of vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "FDA substance registry, ATC/EPC classification, EMA decisions, generic-drug status, FDA Orange Book exclusivity, NDA/BLA pathways" — comprehensive and specific rather than vague.	5 / 5
Completeness	Explicitly answers both what (the enumerated regulatory research capabilities) and when ("Use for jurisdiction-aware approval status (FDA vs EMA), generic vs brand availability, exclusivity expiry tracking, and regulatory pathway selection").	5 / 5
Trigger Term Quality	Rich natural-term coverage including synonyms and abbreviations a user would say — FDA, Orange Book, generic drug, ATC, EMA, NDA/BLA, exclusivity, "generic vs brand availability", "patent expiration".	5 / 5
Distinctiveness Conflict Risk	Occupies a clear drug-regulatory niche with distinctive triggers (Orange Book, exclusivity, NDA/BLA) that are unlikely to fire for the sibling drug skills (interactions, pharmacogenomics, mechanism, repurposing).	5 / 5
	Total	20 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

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