Name: tooluniverse-product-safety-surveillance
Rating: 74.4 (1 reviews)
Author: mims-harvard

tooluniverse-product-safety-surveillance

Post-market safety surveillance and recall/adverse-event RETRIEVAL across the full spectrum of FDA-regulated products that are NOT covered by the drug-AE signal skills: medical devices, food / dietary supplements / cosmetics, veterinary drugs, and drug supply (shortages). Orchestrates openFDA endpoints (MAUDE device adverse events + device recalls + 510(k), CAERS food/supplement/ cosmetic adverse events, veterinary adverse events, drug shortages, and cross-product enforcement/recall reports). USE WHEN the user asks: "are there adverse events for [device / pacemaker / infusion pump / insulin pump]", "device recalls for [firm/product]", "supplement / vitamin / cosmetic adverse reactions", "is [drug] in shortage", "what injectables are on shortage", "veterinary / animal adverse events for [drug] in [dog/cat/horse]", "food recall for listeria", "MAUDE report for [device]", "CAERS reactions for [brand]". DO NOT USE for drug adverse-event SIGNAL detection or disproportionality (PRR / ROR /...

Quality

91%

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-product-safety-surveillance in mims-harvard/ToolUniverse

Quality

Content

82%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-structured, highly actionable retrieval skill with exact tooling, query grammar, verified worked examples, and a clear workflow supported by a real reference file. Minor conciseness redundancy and a few missing validation/feedback checkpoints keep it just below top marks.

Suggestions

Deduplicate the Limitations section against the inline caveats already stated in the Interpretation Tables and Worked Examples to recover tokens.

Add an explicit empty-result / query-refinement feedback loop to the Workflow (e.g., 'if total = 0, broaden or simplify the field:value term and re-run') to reach a full validation checkpoint.

Move the bulk of the per-endpoint Interpretation Tables into references/openfda_fields.md, keeping only a condensed severity-key summary inline, so SKILL.md reads as a tighter overview.

Dimension	Reasoning	Score
Conciseness	Dense and assumes competence (no conceptual preamble about openFDA/MAUDE), but the Limitations section restates caveats (spontaneous/voluntary, no causation, duplicate reports) already given inline in tables and examples, a minor trim opportunity. Not a 5 because of that redundancy; not a 3 because the body is overwhelmingly substantive rather than padded.	4 / 5
Actionability	Exact tool names and endpoints in the Tool Map, concrete field:value query grammar, and five copy-paste worked examples with real tool-call syntax and verified output totals ('total = 16619', 'total = 799'), covering the common product classes. Fully executable guidance.	5 / 5
Workflow Clarity	A clear 7-step numbered Workflow with a CRITICAL query-grammar guardrail and an out-of-scope routing guardrail; read-only retrieval so the destructive/batch cap does not apply. Not a 5 because there is no explicit empty-result / query-refinement feedback loop or query-syntax verification checkpoint.	4 / 5
Progressive Disclosure	Real bundle file references/openfda_fields.md exists and is clearly signaled one level deep ('See references/openfda_fields.md for the full per-endpoint field reference'), with well-organized body sections. Not a 5 because the body inlines five interpretation tables and five worked examples that partly overlap the reference file's field content, leaving minor organization slack.	4 / 5
	Total	17 / 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.

A highly specific, trigger-rich description that cleanly states capabilities, enumerates natural use-when phrases, and draws an explicit boundary against sibling pharmacovigilance skills. No vagueness or padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('recall/adverse-event RETRIEVAL', 'Orchestrates openFDA endpoints') with comprehensive coverage of data sources (MAUDE, device recalls, 510(k), CAERS, veterinary, shortages, enforcement), matching the 'multiple specific concrete actions; comprehensive coverage' anchor.	5 / 5
Completeness	Explicitly answers 'what' (retrieval/orchestration across FDA product classes) and 'when' (USE WHEN with concrete trigger phrases plus a DO NOT USE boundary), matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.	5 / 5
Trigger Term Quality	The 'USE WHEN the user asks' clause enumerates many natural phrasings users would actually say ('is [drug] in shortage', 'food recall for listeria', 'MAUDE report for [device]', 'CAERS reactions for [brand]') with synonyms and specific terms, matching comprehensive coverage.	5 / 5
Distinctiveness Conflict Risk	Explicitly carves a niche ('NOT covered by the drug-AE signal skills') and routes conflicts away ('DO NOT USE for drug adverse-event SIGNAL detection or disproportionality (PRR / ROR)'), giving a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 20 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: plugins/tooluniverse/skills/tooluniverse-product-safety-surveillance/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.