CtrlK
BlogDocsLog inGet started
Tessl Logo

reporting-adverse-events

Structures adverse-event mentions that OpenMed extracts into FAERS / ICH E2B(R3) reportable fields — suspect drug, reaction (MedDRA PT), seriousness criteria, and outcome. Use when the user needs to build an individual case safety report (ICSR), populate a FAERS submission, map a narrative to E2B(R3) data elements, classify seriousness (death, life-threatening, hospitalization, disability, congenital anomaly), or assign reaction outcomes. Trigger keywords: adverse event, ADR, ICSR, FAERS, E2B, E2B(R3), suspect drug, seriousness, MedDRA, reaction outcome, pharmacovigilance case. Pairs after OpenMed NER: consume Pharmaceutical/Chemical and Disease entities from openmed.analyze_text. MedDRA is licensed and user-supplied — never bundled. De-identify the narrative with openmed.deidentify before any external submission.

74

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

The body is a well-structured, actionable guide with executable code, concrete E2B value sets, a clear sequenced workflow, and thoughtful edge-case guidance. It is slightly verbose in its framing and lacks an explicit validation feedback loop before human hand-off.

Suggestions

Tighten the intro and 'When to use' sections — the pharmacovigilance/E2B framing partly restates the description and could be trimmed to respect token budget.

Add an explicit verification checkpoint in the workflow (e.g. 'Confirm every reaction has a MedDRA PT or a flagged uncoded verbatim term before handing the draft to the reviewer') to close the validate→fix→retry loop.

Consider moving the E2B value-set tables and the Standards & references URL list into a single references/ file so SKILL.md stays a lean overview pointing one level deep.

DimensionReasoningScore

Conciseness

Mostly lean — the value-set tables, workflow, and edge cases are dense and earn their tokens — but the intro paragraph and 'When to use' re-explain pharmacovigilance/E2B context that could be trimmed slightly. Not a 5 because of minor over-explanation.

4 / 5

Actionability

The Quick start gives copy-paste-ready, executable Python that assembles the ICSR skeleton, and the value-set tables provide concrete E2B codes (outcome 1–6, drugcharacterization 1–3) covering the common cases.

5 / 5

Workflow Clarity

A clear 7-step sequence with a de-identify-first safety checkpoint and explicit hand-off to a human reviewer; not a 5 because there is no explicit validate→fix→retry feedback loop before hand-off. The destructive/batch cap does not apply since this produces a draft for human review rather than mutating state.

4 / 5

Progressive Disclosure

Well-organized into clearly signaled sections (Quick start, value sets, Workflow, Hand-off, Edge cases, Standards) with no bundle files to navigate. Not a 5 because everything lives in one file with no one-level-deep references, though the length is modest enough that the split is optional.

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.

The description is exemplary: third-person voice, explicit 'what' and 'when', a comprehensive trigger-keyword list, and a clearly distinct pharmacovigilance niche. It also surfaces important constraints (MedDRA licensing, de-identification) without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'build an individual case safety report (ICSR), populate a FAERS submission, map a narrative to E2B(R3) data elements, classify seriousness (death, life-threatening, hospitalization, disability, congenital anomaly), or assign reaction outcomes' — with comprehensive coverage of what the skill does.

5 / 5

Completeness

Clearly answers 'what' ('Structures adverse-event mentions... into FAERS / ICH E2B(R3) reportable fields') and 'when' ('Use when the user needs to build an ICSR, populate a FAERS submission, map a narrative... or assign reaction outcomes') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Explicit 'Trigger keywords' list covers natural terms and synonyms a pharmacovigilance user would say — 'adverse event, ADR, ICSR, FAERS, E2B, E2B(R3), suspect drug, seriousness, MedDRA, reaction outcome, pharmacovigilance case' — including acronyms and abbreviations.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (FAERS / ICH E2B(R3) pharmacovigilance reporting) with domain-specific triggers (MedDRA, ICSR, E2B(R3)) that are unlikely to fire for unrelated skills; minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
maziyarpanahi/openmed
Reviewed

Table of Contents

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.