Agent skill · software engineering · jeremylongshore

abridge-hello-world

Create a minimal Abridge ambient AI clinical documentation example.

Why this skill is useful

Provides a specific implementation for Abridge's API that includes domain-specific patterns for clinical documentation.

What it needs

Requires node installed locally. Requires abridge account access. About 4k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.

What this skill does

Abridge Hello World Overview Minimal working example demonstrating Abridge's ambient clinical documentation. This creates a simulated encounter session, sends audio/transcript data, and receives a structured clinical note. Prerequisites Completed abridge-install-auth setup Abridge sandbox credentials configured Node.js 18+ with TypeScript Instructions Step 1: Create Project Structure Step 2: Build the Encounter Session Client Step 3: Run the Hello World Example Output Encounter session created in Abridge sandbox Transcript processed through Abridge's ambient AI engine Structured SOAP note with ICD-10/CPT codes Source citations mapping AI output to conversation segments Examples Create a new sandbox session with the included fictional identifiers and only a synthetic transcript, then run main.ts with credentials supplied through the local environment rather than the source file. A successful run prints a session ID, selected note sections, and a nonzero source-citation count. Check the generated note for obviously missing sections before using it as an integration fixture. If polling times out, keep the synthetic session ID and redacted status response for diagnosis, then retry only after confirming the sandbox service is healthy; never send a real patient conversation as a test. Error Handling Error Cause Solution ------- ------- ---------- 401 Unauthorized Invalid sandbox credentials Re-check .env.local credentials 422 Invalid specialty Unsupported specialty code Use supported values from API docs Note generation timeout Large/complex transcript Increase polling timeout beyond 60s Empty note sections Transcript too short Provide at least 30 seconds of conversation Missing ICD codes Ambiguous clinical content Ensure transcript includes clear diagnoses Resources Abridge Product Overview Abridge AI Technology HL7 FHIR Clinical Notes Next Steps Proceed to abridge-local-dev-loop for development workflow with live audio capture.

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills jeremylongshore/abridge-hello-world

View the source on GitHub

Browse the @skills marketplace