prior-auth-packet-builder

Builds prior authorization packets from case files and payer policy documents.

Updated May 23, 2026
One-click install
npx skills add https://github.com/kiranimmadi2/promptforge-ai --skill prior-auth-packet-builder-kiranimmadi2
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prior-auth-packet-builder
Source: https://github.com/kiranimmadi2/promptforge-ai/tree/main/openai-agents-python/examples/sandbox/healthcare_support/skills/prior-auth-packet-builder
Command: npx skills add https://github.com/kiranimmadi2/promptforge-ai --skill prior-auth-packet-builder-kiranimmadi2

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Healthcare support teams must manually cross-reference patient case files against payer policy documents to determine prior authorization and referral requirements, which is slow and error-prone. ## Core Features & Use Cases - Policy Matching: Searches payer policy documents with targeted rg queries to find prior auth, referral, imaging, and PPO guidance relevant to a case. - Determination Output: Produces a policy_findings.md file containing the case summary, matched policies, prior auth and referral determinations, and missing information. - Human Review Routing: Generates a human_review_checklist.md describing what reviewers should verify, what to tell the patient, and which queue should own the case. - Use Case: A support agent receives an imaging request case, runs this Skill against the case scenario and transcript, and gets a concise packet citing only inspected policy files with a clear escalation recommendation. ## Quick Start Review the case in case/scenario.json and case/transcript.txt, search the policies directory for relevant payer rules, and generate the prior auth findings and human review checklist in the output folder.

Frequently Asked Questions about prior-auth-packet-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a prior authorization packet from case files?

Inspect the case scenario.json and transcript.txt, then run targeted rg searches against the policies directory for prior auth, referral, and imaging guidance. Write the determination to output/policy_findings.md and a reviewer checklist to output/human_review_checklist.md.

What inputs does a prior auth review workflow need?

It needs a case directory containing scenario.json and transcript.txt, plus a policies directory with payer policy documents covering prior authorization, referrals, imaging, and PPO rules. Only policy files actually inspected may be cited.

When should a prior auth case go to human review?

Recommend human review when referral status is pending and the prior auth determination is unclear. The generated checklist tells the reviewer what to verify, what to tell the patient, and which queue should own the case.

Why use rg searches instead of reading all policy files?

Targeted rg searches locate only the payer, prior auth, referral, and imaging guidance relevant to the case, keeping outputs concise. Broad file reads waste context and risk citing policies that were never actually inspected.

What are the limitations of automated prior auth determination?

The workflow only cites policy files it actually inspects, so incomplete policy directories can produce missing-information flags. Ambiguous cases with pending referrals are escalated to human reviewers rather than resolved automatically.