Agent Native

abridge-ci-integration

This skill helps engineers build CI tests for Abridge integration code using synthetic data and contract-based validation.

by jeremylongshoreCommunityNot reviewed

Community author

Agents
Claude Code
License
MIT (permissive)
Pin
80f86dfpinned Oct 9, 2026
Context cost
about 1,000 tokenswhen the skill loads
GitHub stars
2,823on jeremylongshore/tons-of-skills-marketplace
Scripts
None found

What it does

“Build a synthetic-data CI gate for customer-controlled Abridge integration code without calling undocumented vendor interfaces. Use when adding regression checks to an Abridge deployment repository. Trigger with "test the Abridge integration".”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill helps engineers build CI tests for Abridge integration code using synthetic data and contract-based validation. It creates deterministic checks for configuration, consent handling, note workflows, and redaction without calling live vendor APIs. The skill enforces tool discipline, authentication boundaries, and approval gates to ensure tests remain isolated from production clinical systems.

When to use it

  • Adding regression checks to an Abridge deployment repository
  • Validating customer-owned adapter behavior against signed contracts
  • Testing consent state, redaction, and note-review handoffs
  • Verifying integration changes before production rollout

When not to

  • When live Abridge or EHR tenant access is required for testing
  • Replacing clinical validation or vendor certification workflows
  • Testing undocumented Abridge interfaces without approved schemas

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add jeremylongshore/tons-of-skills-marketplace --skill abridge-ci-integration

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install jeremylongshore/tons-of-skills-marketplace abridge-ci-integration@80f86dfbdb02e5d74c625f411ba6834c66ca0705

Installs the commit we checked (80f86df).

Copy by hand

Download the folder at 80f86df and put it in .claude/skills/abridge-ci-integration for Claude Code and in .agents/skills/abridge-ci-integration for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 80f86df

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "abridge-ci-integration" by jeremylongshore.

Source, pinned to commit 80f86dfbdb02e5d74c625f411ba6834c66ca0705:
https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/80f86dfbdb02e5d74c625f411ba6834c66ca0705/plugins/saas-packs/abridge-pack/skills/abridge-ci-integration

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/abridge-ci-integration/ for Claude Code and .agents/skills/abridge-ci-integration/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/jeremylongshore/abridge-ci-integration

SKILL.md at the pin

---
name: abridge-ci-integration
description: "Build a synthetic-data CI gate for customer-controlled Abridge integration code without calling undocumented vendor interfaces. Use when adding regression checks to an Abridge deployment repository. Trigger with \"test the Abridge integration\"."
argument-hint: "[repository] [workflow-scope]"
allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit
version: 1.5.0
author: Jeremy Longshore <jeremy@intentsolutions.io>
license: MIT
tags:
- saas
- abridge
- ci
- synthetic-data
- contract-testing
model: inherit
effort: high
compatibility: Designed for Claude Code; live work requires an authorized Abridge tenant, approved test data, and health-system change authority
---
# Abridge Synthetic Workflow CI Gate

## Overview

Turn the approved deployment contract into deterministic checks for configuration, consent-state handling, note-review handoffs, redaction, and rollback. The gate proves customer-owned behavior; it does not certify Abridge or an EHR tenant.

## Prerequisites

- The authorized Abridge environment, clinical owner, and health-system policy set
- Current tenant-specific implementation evidence for every private interface in scope
- Synthetic data or the organization's formally approved test-record procedure

## Tool Discipline

Use `Read`, `Glob`, and `Grep` to inspect repository configuration, adapters, tests, policies, and existing evidence. Use `WebFetch` only for current official Abridge, HHS, or named EHR documentation. Use `Write` or `Edit` only after confirming scope, environment, owners, patient-data boundary, and approval state. These tools do not confer access to Abridge, an EHR, or a clinical record; return exact operator steps or an approval-gated handoff for live actions.

## Current Contract

- Abridge documents clinician recording, note review, Linked Evidence, and Epic handoff as user workflows.
- The cited public materials do not define a general Abridge REST sandbox, webhook schema, or public SDK contract.
- Use synthetic encounters and identifiers in CI; never upload patient audio, transcripts, notes, or production tokens.

## Authentication

Use only the health system's provisioned Abridge application access, SSO, administrative role, or tenant-specific partner authentication documented for the approved environment. Do not infer public API credentials, reuse production secrets in tests, or expose tokens and session material. Verify identity owner, least privilege, environment binding, storage, rotation, and revocation before any authenticated action.

## Instructions

1. Inventory the customer-owned adapters, configuration schema, feature flags, and rollback controls with `Read`, `Glob`, and `Grep`.
2. Translate the signed implementation workbook and tenant-specific interface control document into versioned fixtures and schemas.
3. Add negative tests for missing consent state, cross-tenant identifiers, unreviewed note release, and unsafe logs.
4. Mock every vendor and EHR boundary; reject tests that depend on an assumed public Abridge hostname or event name.
5. Use `Write` or `Edit` to add the smallest focused tests and a redacted machine-readable test receipt.
6. Require an integration-owner review when the private contract, EHR template, or rollout cohort changes.

## Approval Boundaries

Do not connect CI to a live Abridge or EHR tenant. A contract-test update cannot authorize a production interface, disclose PHI, or replace clinical validation.

## Output

Return fixture scope, contract revision, tests added, negative paths exercised, redaction result, and an explicit statement of every live boundary not tested. Separate verified facts, tenant-specific evidence, assumptions, and actions still awaiting approval.

## Error Handling

| Condition | Response |
|---|---|
| Fixture contains realistic patient data | Stop, quarantine the fixture, and replace it with synthetic content. |
| Private contract is unavailable | Mark the interface unverified and test only customer-owned invariants. |
| Mock diverges from approved schema | Fail CI and require contract-owner reconciliation. |

## Example

The example is a redacted operational receipt, not patient data or proof of vendor certification.

```text
scope=note-review-handoff; fixtures=synthetic; negative-paths=4; live-calls=0; result=pass; contract=ICD-2026-04
```

## Resources

- [Official documentation map](references/official-docs.md) — dated public evidence and the limits of what those sources establish.

Read the source map before changing a workflow. Recheck tenant-specific implementation evidence for every interface or capability that public documentation does not define.

## Next Steps

Revalidate the evidence date and tenant-specific authority before repeating this workflow in another environment, cohort, care setting, or integration mode.

From jeremylongshore/tons-of-skills-marketplace at 80f86df, shown as plain text under its license: MIT (permissive). The license text is in plugins/saas-packs/abridge-pack/skills/abridge-ci-integration/SKILL.md.

View SKILL.md on GitHub at 80f86df

Files

2 files, 6.7 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 80f86df
All Testing and QA skills
  • next-partial-prefetching-optimizer

    This skill optimizes Next.js client-side navigation under Partial Prefetching by defining what UI loads before and after a click.

    by VercelOfficial publisher

    Claude Code, Codex, Cursor +4 · about 2.8K tokens · pinned 6 days ago

  • Invalid--Name

    This skill cannot be described because its name format is invalid and no functional description or instructions are provided in the skill metadata.

    by CrewAIOfficial publisher

    Claude Code, Codex, Cursor +4 · about 0 tokens · pinned 6 days ago

  • chrome-devtools-cli

    This skill enables agents to automate browser interactions and inspect web pages using Chrome DevTools via command-line interface.

    by GoogleOfficial publisher

    Claude Code, Codex, Cursor +4 · about 2.9K tokens · pinned 6 days ago

  • triaging-visual-review-runs

    Inspects PostHog Visual Review screenshot regression runs that gate pull requests, helping engineers triage diff results, identify flaky stories, and decide…

    by PostHogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 8.9K tokens · pinned 6 days ago

  • code-change-verification

    Runs formatting, linting, type checking, and test verification for SDK code changes after review.

    by OpenAIOfficial publisher

    Contains scripts

    Codex · about 1.3K tokens · pinned 6 days ago

  • runtime-behavior-probe

    This skill guides agents to plan and execute controlled runtime investigations with explicit user approval before each probe runs.

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.8K tokens · pinned 6 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use