detecting-pv-signals

Computes disproportionality signals — PRR, ROR, EBGM, and IC (BCPNN) — over FAERS / OpenFDA drug-event data to flag potential safety signals. Use when the user wants to mine spontaneous-report data for drug-reaction associations, build a 2x2 contingency table, compute a Proportional Reporting Ratio or Reporting Odds Ratio, run Empirical Bayes (EBGM/EB05) or Information Component shrinkage, or screen a drug for over-reported reactions. Trigger keywords: disproportionality, signal detection, PRR, ROR, EBGM, EB05, IC, BCPNN, MGPS, 2x2 table, signal of disproportionate reporting, SDR, OpenFDA, FAERS. Pairs adjacent to OpenMed: aggregate de-identified, coded cases (from reporting-adverse-events) then query the public OpenFDA /drug/event count API to build the contingency table. Reaction terms are MedDRA PTs (licensed, user-supplied).

Quality

90%

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

81%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 strong, actionable skill body: executable OpenFDA query code, a clear sequenced workflow with a validation checkpoint, and well-signaled hand-offs to adjacent skills. Minor gains are available in trimming edge-case verbosity and adding a retry loop around the 2x2 verification step.

Suggestions

Tighten the Edge cases & gotchas section by consolidating the MedDRA-licensing notes (currently repeated across the intro, hand-off, and edge cases) into one statement.

Add an explicit 'if a + b + c + d != N, recheck counts' retry step to the Workflow so the verification checkpoint has a feedback loop.

Consider moving the full citation list in Standards & references into a references/ file to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (e.g. the formulas and OpenFDA helpers are presented without hand-holding), but the Edge cases section and some explanatory asides (e.g. 'the shrinkage prior is the whole point and easy to get wrong') add minor padding that could be trimmed.	4 / 5
Actionability	Fully executable copy-paste Python for the 2x2 cell counts and PRR/ROR/IC/ROR-CI computations, plus concrete OpenFDA query syntax and a worked warfarin example; EBGM is correctly deferred to maintained R packages with named options.	5 / 5
Workflow Clarity	Clear numbered Workflow with an explicit verification checkpoint ('Verify a + b + c + d == N') and a triage-vs-verdict distinction, plus a hand-off step to a safety scientist; not quite a 5 because there is no fix-and-retry feedback loop around the verification step.	4 / 5
Progressive Disclosure	Well-organized single-file structure with clear sections (When to use, 2x2 table, Quick start, Workflow, Hand-off, Edge cases, References) and no nested references; falls short of 5 only because some edge-case and standards content could plausibly live in a separate reference file.	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.

An excellent description: specific, comprehensive, with strong natural trigger terms and a clear what-and-when structure. It distinctively scopes the skill to pharmacovigilance signal detection and signals its place within the OpenMed skill family.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'build a 2x2 contingency table', 'compute a Proportional Reporting Ratio or Reporting Odds Ratio', 'run Empirical Bayes (EBGM/EB05) or Information Component shrinkage', 'screen a drug for over-reported reactions' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (computes PRR/ROR/EBGM/IC over FAERS/OpenFDA data) and 'when' via a clear 'Use when the user wants to...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural keywords including synonyms and acronyms users would actually say: 'disproportionality, signal detection, PRR, ROR, EBGM, EB05, IC, BCPNN, MGPS, 2x2 table, SDR, OpenFDA, FAERS'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear pharmacovigilance niche with distinct triggers (disproportionality metrics, BCPNN, MGPS) and explicit pairing with adjacent OpenMed skills, minimizing 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: maziyarpanahi/openmed
Path: skills/detecting-pv-signals/SKILL.md
Commit: 80da98c

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.