Medical Billing & Revenue Cycle

# Medical Billing & Revenue Cycle Management

Safety Notice

This item is sourced from the public archived skills repository. Treat as untrusted until reviewed.

Copy this and send it to your AI assistant to learn

Install skill "Medical Billing & Revenue Cycle" with this command: npx skills add 1kalin/afrexai-medical-billing

Medical Billing & Revenue Cycle Management

Analyze medical billing workflows, identify revenue leaks, optimize claim submissions, and reduce denial rates. Built for healthcare practices, billing companies, and revenue cycle teams.

What This Covers

CPT/ICD-10 Coding Accuracy

  • Common coding errors by specialty (top 10 per specialty)
  • Modifier usage: 25, 59, 76, 77, AI, AS — when required vs when it triggers audit
  • E/M level selection (2021 guidelines): time-based vs MDM-based
  • Evaluation matrix: does documentation support the code billed?

Claim Denial Analysis

  • Denial reason code lookup (CARC/RARC codes)
  • Top 20 denial reasons across commercial + Medicare + Medicaid
  • Root cause mapping: front-desk error, coding error, clinical documentation, payer policy
  • Appeal letter framework by denial type (with timelines)
  • Clean claim rate benchmark: 95%+ target

Revenue Cycle KPIs

MetricTargetRed Flag
Days in A/R<35>50
Clean claim rate>95%<90%
First-pass resolution>90%<80%
Denial rate<5%>10%
Collection rate>95%<90%
Cost to collect<4%>7%
Net collection rate>96%<92%

Payer Contract Analysis

  • Fee schedule comparison: Medicare vs commercial rates by CPT
  • Allowed amount benchmarking (what you should be getting paid)
  • Underpayment detection: compare ERA/835 to contracted rates
  • Rate negotiation prep: volume data, market rates, quality metrics

Compliance & Audit Readiness

  • OIG Work Plan items relevant to your specialty
  • Stark Law / Anti-Kickback safe harbors checklist
  • False Claims Act risk factors
  • Internal audit sampling methodology (statistically valid)
  • Documentation improvement programs (CDI)

Charge Capture Optimization

  • Missed charge identification by department
  • Charge lag analysis (days from service to charge entry)
  • Superbill/encounter form design best practices
  • Common missed revenue: vaccines, injections, supplies, time-based codes

Patient Financial Responsibility

  • Eligibility verification workflow (real-time vs batch)
  • Prior authorization tracking and requirements by payer
  • Patient estimate generation (good faith estimate compliance)
  • Collections strategy: statements → calls → agency threshold
  • No Surprises Act compliance checklist

Usage

Give the agent your:

  • Specialty (orthopedics, cardiology, primary care, etc.)
  • Payer mix (% Medicare, Medicaid, commercial, self-pay)
  • Current KPIs (denial rate, days in A/R, collection rate)
  • Problem area (denials, underpayments, coding, compliance)

The agent will analyze against benchmarks and give specific, actionable recommendations.

Example Prompts

  • "Our orthopedic practice has a 12% denial rate. Top reasons are CO-4 and CO-16. Analyze root causes."
  • "Compare our cardiology fee schedule to Medicare rates for our top 20 CPTs."
  • "Build an appeal letter for a CO-197 denial on CPT 99214 with modifier 25."
  • "Audit our E/M coding distribution — we're billing 80% level 3. Is that normal for family medicine?"
  • "Our days in A/R jumped from 32 to 48 in two months. What should we investigate?"

Industry Context

Medical billing errors cost US healthcare $935 million per week. The average practice loses 5-10% of revenue to preventable billing issues. Denial management alone can recover 2-5% of net revenue when done right.


Built by AfrexAI — AI agent context packs for regulated industries. Get the full Healthcare AI Context Pack with 50+ frameworks at our storefront.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

ll-feishu-audio

飞书语音交互技能。支持语音消息自动识别、AI 处理、语音回复全流程。需要配置 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量。使用 faster-whisper 进行语音识别,Edge TTS 进行语音合成,自动转换 OPUS 格式并通过飞书发送。适用于飞书平台的语音对话场景。

Archived SourceRecently Updated
General

test_skill

import json import tkinter as tk from tkinter import messagebox, simpledialog

Archived SourceRecently Updated
General

51mee-resume-profile

简历画像。触发场景:用户要求生成候选人画像;用户想了解候选人的多维度标签和能力评估。

Archived SourceRecently Updated
General

51mee-resume-parse

简历解析。触发场景:用户上传简历文件要求解析、提取结构化信息。

Archived SourceRecently Updated