agentsclimarketplace
Sign in

Prior auth coworker

Skill FridrichMethod/awesome-skills/skills/prior-auth-coworker

Prior Auth ReviewFrom its SKILL.md

Install
npx -y skills add FridrichMethod/awesome-skills --skill prior-auth-coworker

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 462 tokens by cl100k_base, as published. Nobody here has run it

<!-- # COPYRIGHT NOTICE # This file is part of the "Universal Biomedical Skills" project. # Copyright (c) 2026 MD BABU MIA, PhD <[email protected]> # All Rights Reserved. # # This code is proprietary and confidential. # Unauthorized copying of this file, via any medium is strictly prohibited. # # Provenance: Authenticated by MD BABU MIA -->

Prior Authorization Coworker

This skill acts as an automated utilization management reviewer. It takes unstructured clinical notes and a procedure code, compares them against internal policy criteria (e.g., conservative therapy failure), and renders a decision.

When to Use This Skill

  • When a user asks to "review a prior auth request".
  • When checking if a patient qualifies for a specific procedure (e.g., MRI).
  • When you need to generate a structured approval/denial letter justification.

Core Capabilities

  1. Policy Matching: Checks against specific criteria (e.g., "Pain > 6 weeks").
  2. Trace Generation: Produces an "Anthropic-style" <thinking> trace for auditability.
  3. Structured Output: Returns a JSON object with decision, reasoning, and timestamps.

Workflow

  1. Extract Data: Parse the clinical note and procedure code from the user's input.
  2. Execute Review: Run the coworker script.
  3. Present Decision: Output the JSON decision and the reasoning trace.

Example Usage

User: "Check if this patient qualifies for an MRI of the Lumbar Spine: Patient has had back pain for 2 months, tried PT but it didn't work."

Agent Action:

python3 Skills/Clinical/Prior_Authorization/anthropic_coworker.py --code "MRI-L-SPINE" --note "Patient has back pain > 2 months. Failed PT."

Supported Policies

  • MRI-L-SPINE (Lumbar Spine MRI)
<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

What ships with it: 5 files

16.2 KB alongside SKILL.md, 3 of them executable

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.