openevidence-core-workflow-a
Integrates OpenEvidence search functionality for clinical literature retrieval and decision support.
Install
mkdir -p .claude/skills/openevidence-core-workflow-a && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4116" && unzip -o skill.zip -d .claude/skills/openevidence-core-workflow-a && rm skill.zipInstalls to .claude/skills/openevidence-core-workflow-a
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute OpenEvidence primary workflow: Clinical Query & Decision Support.Key capabilities
- →Search clinical literature with evidence-level filters
- →Retrieve structured citations with journal and year metadata
- →Check drug interactions against patient context
- →Lookup specialty guidelines from major bodies
- →Provide confidence scores and evidence grading
How it works
The workflow queries clinical literature databases using specified filters and returns structured evidence with confidence metrics. It also checks drug interactions and retrieves guidelines from sources like ACC/AHA, ESC, and NICE.
Inputs & outputs
When to use openevidence-core-workflow-a
- →Implement clinical evidence lookups
- →Build decision support features
- →Filter literature by specialty
- →Retrieve structured citations
About this skill
OpenEvidence Clinical Consult Workflow
Overview
Convert a clinical uncertainty into a focused Ask workflow, then validate the evidence before using it in care. Keep inputs minimal, separate observed facts from assumptions, and leave consequential decisions with the named accountable owner.
Prerequisites
- A clearly bounded workflow, accountable clinical owner, and organizational policy
- Current first-party OpenEvidence documentation and applicable institution agreements
- Synthetic or properly authorized minimum-necessary data
Tool Discipline
Use Read, Glob, and Grep to inspect supplied policies, plans, and evidence. Use WebFetch only for current first-party OpenEvidence documentation. Use Write or Edit only when the user requests a named deliverable with an approved destination. Never expose credentials, PHI, recordings, or unrestricted environment output.
Current Contract
- The platform is informational and educational and does not replace diagnosis or professional clinical judgment.
- The public guide describes Ask for evidence-based clinical questions with cited sources.
- Only enter patient context permitted by applicable policy, agreement, authorization, and consent.
Authentication
Use only the official OpenEvidence web/mobile sign-in or an institution-approved access path. Do not invent API keys, OAuth clients, SDK credentials, service accounts, or private endpoints. Never ask a user to reveal a password, session token, cookie, or recovery code.
Instructions
- Define the decision to support and the minimum context needed; remove direct identifiers unless approved and necessary.
- Frame the question with population, intervention or exposure, comparator, outcomes, and relevant constraints.
- Choose the documented Ask model or workflow appropriate to complexity; use Snow for a literature investigation when warranted.
- Review EvidenceGrade when present, then open citations and inspect recency, study design, population, and guideline provenance.
- Reconcile the response with patient-specific facts, contraindications, local policy, and the clinician’s independent judgment.
- Record the question, evidence reviewed, uncertainty, decision owner, and any follow-up without copying unnecessary PHI.
Approval Boundaries
Do not create or share accounts; change access, roles, agreements, consent, retention, or security settings; enter PHI; record a conversation; copy content into another system; contact a patient; make a diagnosis or treatment decision; submit billing; transmit a support packet; run a production pilot; or represent vendor capabilities without explicit approval from the accountable owner. A qualified professional remains responsible for clinical decisions.
Output
Return scope, current first-party evidence and date, data classification, workflow or findings, citations reviewed, assumptions rejected, clinical and governance owners, approval state, unresolved risk, and the exact next action. Redact patient and credential data.
Error Handling
| Condition | Response |
|---|---|
| Evidence conflicts | Surface both positions and have the clinical owner resolve applicability. |
| Patient context exceeds policy | De-identify further or stop until authorization is confirmed. |
| Answer sounds definitive | Restate uncertainty and verify source support before use. |
Examples
This compact example shows the minimum reviewable handoff; adapt fields to the approved workflow without adding sensitive data.
Input:
decision=therapy options; population=de-identified adult; constraints=renal impairment
Expected handoff:
question=structured; sources=opened; uncertainty=recorded; decision=clinician-owned
Resources
When not to use it
- →Queries requiring patient case analysis
- →Reporting tasks
Limitations
- →Empty citations array if question is too narrow
- →Rate limit of 30 queries per minute
How it compares
Unlike manual literature searches, this workflow provides structured, graded evidence and automated drug interaction checks specifically for clinical decision support.
Compared to similar skills
openevidence-core-workflow-a side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| openevidence-core-workflow-a (this skill) | 1 | 2mo | Review | Intermediate |
| identify-vault-protocol | 1 | 8mo | No flags | Intermediate |
| biopython | 1 | 9mo | Review | Intermediate |
| reference-sdk | 1 | 8mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
identify-vault-protocol
tradingstrategy-ai
Identify an unknown vault protocol based on its smart contract address
biopython
davila7
Primary Python toolkit for molecular biology. Preferred for Python-based PubMed/NCBI queries (Bio.Entrez), sequence manipulation, file parsing (FASTA, GenBank, FASTQ, PDB), advanced BLAST workflows, structures, phylogenetics. For quick BLAST, use gget. For direct REST API, use pubmed-database.
reference-sdk
parcadei
Check reference SDK implementations using btca ask
apollo-hello-world
jeremylongshore
Create a minimal working Apollo.io example. Use when starting a new Apollo integration, testing your setup, or learning basic Apollo API patterns. Trigger with phrases like "apollo hello world", "apollo example", "apollo quick start", "simple apollo code", "test apollo api".
evernote-core-workflow-b
jeremylongshore
Execute Evernote secondary workflow: Search and Retrieval. Use when implementing search features, finding notes, filtering content, or building search interfaces. Trigger with phrases like "search evernote", "find evernote notes", "evernote search", "query evernote".
juicebox-migration-deep-dive
jeremylongshore
Advanced Juicebox data migration strategies. Use when migrating from other recruiting platforms, performing bulk data imports, or implementing complex data transformation pipelines. Trigger with phrases like "juicebox data migration", "migrate to juicebox", "juicebox import", "juicebox bulk migration".