Index of every page on this site: llms.txt
All skills
jeremylongshore avatar

/abridge-performance-tuning

@820dfc8
Run it yourself

Measure and improve Abridge workflow latency and friction using privacy-safe health-system evidence. Use when clinicians report slow capture, note readiness, review, or EHR handoff. Trigger with "measure Abridge performance".

Use this Skill: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/abridge-performance-tuning

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈63 tokens for metadata: the name and description. ≈1k when used: this file. ≈425 more on demand in 1 file.

Description uses 3.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈254 characters, or 3.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Abridge Clinical Workflow Performance Study

Overview

Measure the stages users experience instead of imposing invented API latency targets. Separate device and network conditions, capture duration, processing wait, review effort, and EHR handoff while protecting patient and clinician identity.

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

  • Official recording guidance identifies connectivity, microphone contention, device placement, and Bluetooth use as factors in capture quality and processing experience.
  • Abridge's Redraft support page documents a user-visible regeneration workflow, but one published timing is not a universal service-level objective.
  • Local baselines and signed service commitments control operational thresholds.

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. Define the cohort, stage boundaries, clock source, sampling policy, privacy threshold, and approved service objectives.
  2. Use Read, Glob, and Grep to inspect instrumentation and dashboards for identifiers or note content that must be removed.
  3. Measure stage distributions and failure rates, not only averages; stratify by device, location, care setting, and workflow version when safe.
  4. Correlate slow paths with network and device conditions, review edits, downstream EHR behavior, and support events.
  5. Use WebFetch only for current official workflow guidance; never convert marketing or support examples into an SLA.
  6. Use Write or Edit to add bounded instrumentation or publish an experiment with rollback and success criteria.

Approval Boundaries

Do not capture audio, transcript, note text, patient identifiers, or individual productivity rankings in performance telemetry.

Output

Return stage definitions, percentile distributions, failure rates, cohort caveats, suspected boundary, experiment, rollback, and owner. Separate verified facts, tenant-specific evidence, assumptions, and actions still awaiting approval.

Error Handling

Condition Response
Stage clocks are incomparable Repair instrumentation before drawing conclusions.
Small cohort risks identification Aggregate or extend the window.
Optimization reduces review quality Roll back immediately and notify the clinical owner.

Example

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

stage=note-ready-to-reviewed; cohort=outpatient-aggregate; p50=local-baseline; p95=regressed; phi=none; experiment=network-path-check

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.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill is a performance tuning tool for Abridge clinical workflows that prioritizes data privacy and security. It includes extensive safeguards against credential exposure, patient data leaks, and unauthorized network access, referencing only official vendor documentation.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: MEDIUM · 1 issue

Signed by skilld at 820dfc8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
What it can do
Reads files Network Edits files
Modelinherit
argument-hint
[cohort] [time-window] [workflow-stage]
version
1.5.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
All 6 allowed tools
ReadGlobGrepWebFetchWriteEdit
Other metadata
tags
[
  "saas",
  "abridge",
  "performance",
  "workflow-metrics",
  "clinical-operations"
]
model
inherit
effort
high
compatibility
Designed for Claude Code; live work requires an authorized Abridge tenant, approved test data, and health-system change authority

README badge

README badge for jeremylongshore/tons-of-skills-marketplace/abridge-performance-tuning