From openevidence-pack
Searches medical evidence, manages citations, and generates structured evidence reports with graded recommendations via OpenEvidence API.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openevidence-pack:openevidence-core-workflow-bThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Search medical evidence, manage citations, and generate formatted evidence reports
Search medical evidence, manage citations, and generate formatted evidence reports
through OpenEvidence. Use this workflow to find clinical studies for a specific
question, build citation collections for literature reviews, or produce structured
evidence summaries with graded recommendations. This is the secondary workflow —
for DeepConsult research synthesis, see openevidence-core-workflow-a.
const results = await client.evidence.search({
query: 'SGLT2 inhibitors cardiovascular outcomes type 2 diabetes',
filters: {
study_type: ['rct', 'meta_analysis', 'systematic_review'],
year_range: { min: 2020, max: 2026 },
evidence_level: ['1a', '1b', '2a'],
},
limit: 25,
sort: 'relevance',
});
console.log(`Found ${results.total} studies`);
results.items.forEach(s =>
console.log(` [${s.evidence_level}] ${s.title} (${s.journal}, ${s.year}) — ${s.citations} citations`)
);
const collection = await client.citations.create({
name: 'SGLT2i CV Outcomes Review — April 2026',
study_ids: results.items.slice(0, 15).map(s => s.id),
tags: ['cardiology', 'diabetes', 'sglt2i'],
});
console.log(`Collection ${collection.id}: ${collection.study_count} studies`);
await client.citations.addByDoi(collection.id, { doi: '10.1056/NEJMoa2034577' });
const graded = await client.evidence.grade(collection.id, {
framework: 'GRADE', // GRADE | Oxford | USPSTF
outcome: 'major_adverse_cardiovascular_events',
});
graded.findings.forEach(f =>
console.log(`${f.outcome}: ${f.grade} (${f.certainty}) — ${f.summary}`)
);
console.log(`Overall recommendation: ${graded.recommendation}`);
const report = await client.reports.generate({
collection_id: collection.id,
format: 'structured',
sections: ['clinical_question', 'search_strategy', 'evidence_table', 'grade_summary', 'references'],
citation_style: 'AMA',
});
console.log(`Report generated: ${report.page_count} pages`);
console.log(`Download: ${report.download_url}`);
| Issue | Cause | Fix |
|---|---|---|
401 Unauthorized | Invalid API key or expired session | Regenerate key in OpenEvidence dashboard |
404 Study not found | DOI not indexed or incorrect ID | Search by title or check DOI format |
422 Invalid filter | Unsupported evidence_level or study_type | Use allowed values from client.schema.filters() |
429 Rate limited | Exceeded 60 queries/minute | Add backoff; batch searches where possible |
503 Grading unavailable | GRADE engine under maintenance | Retry after 5 minutes or use Oxford framework |
A successful workflow returns ranked evidence results with evidence levels, a curated citation collection, GRADE assessments with certainty ratings, and a downloadable structured report in AMA citation format.
See openevidence-sdk-patterns for authentication and HIPAA-compliant configuration.
npx claudepluginhub fleet-to-force/claude-code-plugins-plus --plugin openevidence-pack5plugins reuse this skill
First indexed Jul 10, 2026
Searches medical evidence, manages citations, and generates structured evidence reports with graded recommendations via OpenEvidence API.
Guides clinical and health science research through PICOT question formulation, evidence hierarchy assessment, bias evaluation (Cochrane RoB 2, ROBINS-I), outcome prioritization, and GRADE certainty rating.
Generates The Lancet's mandatory Research in context panel with three headed parts, grounded in a systematic literature search with stated databases, terms, and dates.