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

88%

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

Quality

Content

77%

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

Highly actionable and well-sequenced, but it is a single long file with some duplicated explanatory material. Moving the per-tool API reference into a bundled reference file and trimming the interpretive 'Reasoning Framework' would improve both conciseness and progressive disclosure.

Suggestions

Move the per-tool parameter/return-shape reference (Phases 1–6) into a bundled references file (e.g. references/tool_reference.md) and keep SKILL.md as a phase-by-phase overview that links out, raising progressive_disclosure to one level deep.

Trim the 'Reasoning Framework / Interpretation Guidance' section, which restates the exclusivity codes and TE-code meanings already given in Phase 4 — keep only regulatory nuance Claude would not already infer.

De-duplicate exclusivity code definitions between Phase 4 and the Reasoning Framework so each fact appears once, reducing token cost without losing the workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tool reference, but the 'Reasoning Framework / Interpretation Guidance' section re-explains NCE/ODE/PED exclusivity and TE codes already covered in Phase 4 and defines approval pathways at length, so it could be tightened.	2 / 3
Actionability	Executable Python snippets, exact required/optional parameters, return-shape contracts, and three copy-paste example workflows give concrete, ready-to-run guidance.	3 / 3
Workflow Clarity	A clearly sequenced 8-phase pipeline plus three end-to-end example workflows; read-only research needs no destructive/batch validation loop, and the 'Common Mistakes' section provides guardrails.	3 / 3
Progressive Disclosure	No bundle files exist, so this ~280-line SKILL.md is monolithic with the full per-tool API reference inline; content that could live in a separate reference file is not split out, and the under-50-line exemption does not apply.	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 precise, third-person description that covers concrete capabilities, natural trigger terms, explicit use-conditions, and a distinct niche. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'FDA substance registry, ATC/EPC classification, EMA decisions, generic-drug status, FDA Orange Book exclusivity, NDA/BLA pathways' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (the capability list) and when ('Use for jurisdiction-aware approval status... generic vs brand availability, exclusivity expiry tracking, and regulatory pathway selection'), in third person.	3 / 3
Trigger Term Quality	Strong coverage of natural terms a user would say — 'FDA, Orange Book, generic drug, UNII, ATC code, NDA, ANDA, patent, exclusivity, DailyMed, drug label, adverse reactions, approval'.	3 / 3
Distinctiveness Conflict Risk	A clear drug-regulatory niche reinforced by the body's explicit 'NOT for' routing to sibling skills, making mis-triggering unlikely.	3 / 3
	Total	12 / 12 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: plugin/skills/tooluniverse-drug-regulatory/SKILL.md
Commit: 089eb8e

Reviewed: about 5 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.