SkillAgentSearch skills...

abridge-hello-world

Run a bounded Abridge smoke test through the documented user workflow using an approved test encounter and no invented API

Install / Use

npx skills add jeremylongshore/tons-of-skills-marketplace --skill abridge-hello-world

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Category

Automation

Supported Platforms

Claude Code

Our assessment of abridge-hello-world

abridge-hello-world scores 87/100 on our quality scale, 1231st of 2,250 Automation skills we index.

Its SKILL.md is 4.6 KB long, well organised into 13 sections with 1 code example: a solid amount of guidance for an agent.

With 2,785 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
17/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 5 days ago, so abridge-hello-world is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

abridge-hello-world compared with similar skills

All 4 of these similar skills score higher than abridge-hello-world; compare them before choosing.

SkillScoreStarsUpdatedFormat
abridge-hello-world (this skill)by jeremylongshore872.8k5d agoSKILL.md
Agent-Reachby Panniantong10086.1k14d agoCLAUDE.md
headroomby headroomlabs-ai10074.1ktodayCLAUDE.md
rufloby ruvnet10073.5ktodayCLAUDE.md
crawl4aiby unclecode10084.5k4d agoMCP Server

Frequently asked questions

How do I install abridge-hello-world?
Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill abridge-hello-world. The install tabs above show the steps for each supported agent.
Which AI agents does abridge-hello-world work with?
It is written for Claude Code, as a SKILL.md file. Other agents that read the same format can often use it too.
Is abridge-hello-world safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is abridge-hello-world still maintained?
The repository was last updated 5 days ago, so abridge-hello-world is actively maintained.

name: abridge-hello-world description: "Run a bounded Abridge smoke test through the documented user workflow using an approved test encounter and no invented API. Use when validating a new tenant or pilot cohort. Trigger with "smoke test Abridge"." argument-hint: "[environment] [test-encounter-id]" allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit version: 1.5.0 author: Jeremy Longshore jeremy@intentsolutions.io license: MIT tags:

  • saas
  • abridge
  • smoke-test
  • consent
  • note-review model: inherit effort: medium compatibility: Designed for Claude Code; live work requires an authorized Abridge tenant, approved test data, and health-system change authority

Abridge Consent-to-Note Pilot Smoke Test

Overview

Prove the smallest useful path: authorized user, designated test patient or synthetic scenario, consent handling, recording, note creation, Web Editor review, Linked Evidence check, and approved final disposition.

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's documented entry path uses its clinician application and Web Editor rather than a public create-session REST tutorial.
  • Recording guidance requires following the organization's consent policy.
  • The clinician reviews and edits the generated draft before sending or otherwise finalizing it.

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. Confirm the environment, authorized user, approved test-record procedure, consent script, and expected note destination.
  2. Use Read, Glob, and Grep to inspect the local test plan, tenant labels, and expected configuration without opening credentials.
  3. Run the documented application workflow with synthetic dialogue or the health system's designated non-production encounter.
  4. Verify note creation, visible sections, editability, and a sample of Linked Evidence; record outcomes without clinical text.
  5. Exercise one safe failure path such as interrupted capture or withheld send, then confirm no unintended chart update.
  6. Use Write or Edit to record the receipt; use WebFetch only for current official Abridge instructions.

Approval Boundaries

Do not use a real patient or send content to a production chart unless the health system's controlled test protocol explicitly authorizes it.

Output

Return environment, test identity class, consent path, workflow stages, evidence sample result, chart-write count, failure-path result, and go/no-go. Separate verified facts, tenant-specific evidence, assumptions, and actions still awaiting approval.

Error Handling

| Condition | Response | |---|---| | No designated test encounter exists | Stop and obtain one through the EHR test-data process. | | Patient identity does not match | Stop before recording. | | Draft cannot be reviewed | Do not send or finalize it. |

Example

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

environment=nonprod; encounter=designated-test; consent=scripted; draft=reviewable; evidence=sample-pass; chart-writes=0; result=pass

Resources

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.

Related Skills

View on GitHub
GitHub Stars2.8k
CategoryAutomation
Updated5d ago
Forks404

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions