Skip to main content Startseite Ersteller jeremylongshore tons-of-skills-marketplace abridge-core-workflow-b
abridge-core-workflow-b Implement Abridge patient-facing documentation and after-visit summary generation.
Use when building patient portal integration, generating plain-language summaries,
multi-language translations, or after-visit instructions from clinical encounters.
Trigger: "abridge patient summary", "after-visit summary", "patient portal abridge",
"abridge patient-facing", "abridge multilingual".
Zur Installation springen Skills Marktplatz Entdecken und erkunden Sie KI-Skills, die von der Community erstellt wurden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Prompt kopierenPrompt-Details anzeigen Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill abridge-core-workflow-bDer Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.
Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.
ZIP herunterladen Herunterladen... Mehr aus diesem Repository langchain-deploy-integration Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
langchain-langgraph-agents Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
langchain-langgraph-human-in-loop Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before /
interrupt_after and Command(resume=...) — JSON-serializable state, clean
resume semantics, and UI wiring for approval decisions. Use when adding an
approval gate before an expensive tool call, wiring a Slack/web UI for agent
approvals, or debugging a graph that crashes on interrupt.
Trigger with "langgraph human in loop", "langgraph interrupt_before",
"langgraph approval flow", "Command resume", "langgraph HITL".
name abridge-core-workflow-b description Implement Abridge patient-facing documentation and after-visit summary generation.
Use when building patient portal integration, generating plain-language summaries,
multi-language translations, or after-visit instructions from clinical encounters.
Trigger: "abridge patient summary", "after-visit summary", "patient portal abridge",
"abridge patient-facing", "abridge multilingual".
allowed-tools Read, Write, Edit, Bash(npm:*), Grep version 1.4.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","healthcare","ai","abridge","patient-engagement"] compatibility Designed for Claude Code
Abridge Core Workflow B — Patient-Facing Documentation
Overview
Secondary workflow: generating plain-language patient summaries from the same clinical encounter captured in Workflow A. Abridge produces both clinician notes and patient-friendly after-visit summaries (AVS), supporting 28+ languages and multiple reading levels.
Prerequisites
Completed abridge-core-workflow-a (encounter-to-note pipeline)
Patient portal integration configured (Epic MyChart, Athena Patient Portal)
Understanding of health literacy requirements
Instructions
Step 1: Request Patient Summary from Completed Session
import axios, { AxiosInstance } from 'axios' ;
interface PatientSummary {
summary_id : string ;
session_id : string ;
language : string ;
reading_level : 'basic' | 'intermediate' | 'advanced' ;
sections : {
visit_reason : string ;
what_we_discussed : string ;
your_diagnosis : string ;
next_steps : string ;
medications : Array <{
name : string ;
instructions : ;
: ;
}>;
: {
: ;
: ;
: ;
};
: [];
};
: {
: ;
: ;
: ;
};
}
( ): < > {
{ data } = api. ( , {
language,
: readingLevel,
: ,
: ,
: ,
});
data;
}
string
warnings
string
follow_up
when
string
why
string
scheduling_instructions
string
questions_to_ask
string
source_encounter
date
string
provider_name
string
department
string
async
function
generatePatientSummary
api : AxiosInstance ,
sessionId : string ,
language : string = 'en' ,
readingLevel : PatientSummary ['reading_level' ] = 'basic'
Promise
PatientSummary
const
await
post
`/encounters/sessions/${sessionId} /patient-summary`
reading_level
include_medications
true
include_follow_up
true
include_suggested_questions
true
return
Step 2: Push to Patient Portal via FHIR
interface FhirCommunication {
resourceType : 'Communication' ;
status : 'completed' ;
category : Array <{ coding : Array <{ system : string ; code : string }> }>;
subject : { reference : string };
encounter : { reference : string };
payload : Array <{ contentString : string }>;
sent : string ;
}
async function pushToMyChart (
fhirBaseUrl : string ,
accessToken : string ,
summary : {
patient_id: string ;
encounter_id: string ;
content: string ;
language: string ;
}
): Promise <string > {
const communication : FhirCommunication = {
resourceType : 'Communication' ,
status : 'completed' ,
category : [{
coding : [{
system : 'http://terminology.hl7.org/CodeSystem/communication-category' ,
code : 'notification' ,
}],
}],
subject : { reference : `Patient/${summary.patient_id} ` },
encounter : { reference : `Encounter/${summary.encounter_id} ` },
payload : [{ contentString : summary.content }],
sent : new Date ().toISOString (),
};
const response = await axios.post (
`${fhirBaseUrl} /Communication` ,
communication,
{ headers : { Authorization : `Bearer ${accessToken} ` } }
);
return response.data .id ;
}
Step 3: Multi-Language Translation
const SUPPORTED_LANGUAGES = [
'en' , 'es' , 'zh' , 'ar' , 'vi' , 'ko' , 'tl' , 'ru' , 'fr' , 'pt' ,
'hi' , 'de' , 'ja' , 'it' , 'pl' , 'ur' , 'fa' , 'bn' , 'pa' , 'gu' ,
'ha' , 'yo' , 'am' , 'so' , 'sw' , 'ne' , 'my' , 'th' ,
] as const ;
async function generateMultiLanguageSummaries (
api : AxiosInstance ,
sessionId : string ,
languages : string []
): Promise <Map <string , PatientSummary >> {
const summaries = new Map <string , PatientSummary >();
const results = await Promise .allSettled (
languages.map (lang =>
generatePatientSummary (api, sessionId, lang, 'basic' )
)
);
results.forEach ((result, index ) => {
if (result.status === 'fulfilled' ) {
summaries.set (languages[index], result.value );
} else {
console .error (`Translation failed for ${languages[index]} :` , result.reason );
}
});
return summaries;
}
Step 4: Format After-Visit Summary (AVS)
function formatAfterVisitSummary (summary : PatientSummary ): string {
const lines : string [] = [
`AFTER-VISIT SUMMARY` ,
`Date: ${summary.source_encounter.date} ` ,
`Provider: ${summary.source_encounter.provider_name} ` ,
`Department: ${summary.source_encounter.department} ` ,
'' ,
`WHY YOU CAME IN` ,
summary.sections .visit_reason ,
'' ,
`WHAT WE DISCUSSED` ,
summary.sections .what_we_discussed ,
'' ,
`YOUR DIAGNOSIS` ,
summary.sections .your_diagnosis ,
'' ,
`WHAT TO DO NEXT` ,
summary.sections .next_steps ,
];
if (summary.sections .medications .length > 0 ) {
lines.push ('' , 'YOUR MEDICATIONS' );
for (const med of summary.sections .medications ) {
lines.push (` ${med.name} : ${med.instructions} ` );
if (med.warnings ) lines.push (` Important: ${med.warnings} ` );
}
}
lines.push (
'' ,
'FOLLOW-UP' ,
`When: ${summary.sections.follow_up.when} ` ,
`Why: ${summary.sections.follow_up.why} ` ,
summary.sections .follow_up .scheduling_instructions ,
);
return lines.join ('\n' );
}
Output
Patient-friendly after-visit summary at target reading level
Multi-language translations (28+ languages supported)
FHIR Communication resource pushed to patient portal
Formatted AVS document with medications, follow-up, and next steps
Error Handling Error Cause Solution Unsupported language Language not in Abridge's 28+ set Check SUPPORTED_LANGUAGES list Summary too vague Encounter transcript was short Ensure encounter has enough clinical detail MyChart push 403 Patient portal not linked Verify patient has active MyChart account Missing medications Provider didn't discuss meds Medications only included if mentioned in encounter
Resources
Next Steps For common integration errors, see abridge-common-errors.