Back to Details

prior-auth-review-skill

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Prior Authorization Review Skill

预先授权审核Skill

Overview

概述

This skill automates the payer review process for prior authorization (PA) requests. It processes clinical documentation, validates medical necessity against coverage policies, and generates authorization decisions with supporting rationale.
Target Users: Health insurance payer organizations (Medicare Advantage, Commercial, Medicaid MCOs)
Value Proposition: Reduce PA review time from 30-60 minutes to under 5 minutes. Enable auto-approval for 40-60% of clear-cut cases.
本Skill可实现预先授权（PA）请求的付款方审核流程自动化。它会处理临床文档，对照承保政策验证医疗必要性，并生成带有支持性理由的授权决策。
目标用户： 健康保险付款方机构（联邦医疗保险优势计划、商业保险、医疗补助管理式医疗组织）
价值主张： 将PA审核时间从30-60分钟缩短至5分钟以内。为40-60%的明确案例实现自动批准。

Architecture

架构

This skill uses a simplified 2-subskill workflow:
Subskill 1: Intake & Assessment
  ↓ (validates data, extracts clinical info, assesses medical necessity)
Subskill 2: Decision & Notification
  ↓ (generates auth decision with provider notification)

ONLY REVIEW THE SUBSKILL FILES WHEN THEY ARE NEEDED, DONT PRE-READ THE WHOLE SKILL ON BOOTUP

Output: Authorization Decision Package
本Skill采用简化的双子Skill工作流：
Subskill 1: 信息采集与评估
  ↓ (验证数据、提取临床信息、评估医疗必要性)
Subskill 2: 决策与通知
  ↓ (生成授权决策并通知提供者)

ONLY REVIEW THE SUBSKILL FILES WHEN THEY ARE NEEDED, DONT PRE-READ THE WHOLE SKILL ON BOOTUP

输出：授权决策包

Waypoint Files

路径点文件

waypoints/
├── assessment.json          # Subskill 1 output (consolidated)
└── decision.json           # Subskill 2 output (final decision)
waypoints/
├── assessment.json          # 子Skill 1的输出（整合结果）
└── decision.json           # 子Skill 2的输出（最终决策）

Prerequisites

前置条件

Required MCP Servers

所需MCP服务器

This skill requires 3 healthcare MCP connectors:
  1. CMS Coverage MCP Connector - Medicare coverage policies (NCDs, LCDs)
  2. ICD-10 MCP Connector - Diagnosis code validation and lookup
  3. NPI MCP Connector - Healthcare provider verification via NPPES
For detailed tool usage, parameters, and CMS web resources, see references/01-intake-assessment.md.
本Skill需要3个医疗MCP连接器：
  1. CMS Coverage MCP Connector - 联邦医疗保险承保政策（NCDs、LCDs）
  2. ICD-10 MCP Connector - 诊断代码验证与查询
  3. NPI MCP Connector - 通过NPPES验证医疗服务提供者资质
如需详细的工具使用方法、参数及CMS网络资源，请查看references/01-intake-assessment.md。

MCP Invocation Notifications

MCP调用通知

During execution, the skill displays notifications before and after each MCP connector call:
  • Before: "Verifying provider credentials via NPI MCP Connector..."
  • After: "NPI MCP Connector completed successfully - Provider verified: Dr. [Name]"
  • Before: "Validating diagnosis codes via ICD-10 MCP Connector..."
  • After: "ICD-10 MCP Connector completed successfully - [N] codes validated"
  • Before: "Searching coverage policies via CMS Coverage MCP Connector..."
  • After: "CMS Coverage MCP Connector completed successfully - Found policy: [Policy ID]"
  • Before: "Validating procedure codes via CMS Fee Schedule..."
  • After: "CPT/HCPCS codes validated via CMS Fee Schedule - [N] codes checked"
在执行过程中，Skill会在每次调用MCP连接器前后显示通知：
  • 调用前：“正在通过NPI MCP Connector验证提供者资质...”
  • 调用后：“NPI MCP Connector执行成功 - 提供者已验证：[姓名]医生”
  • 调用前：“正在通过ICD-10 MCP Connector验证诊断代码...”
  • 调用后：“ICD-10 MCP Connector执行成功 - 已验证[N]个代码”
  • 调用前：“正在通过CMS Coverage MCP Connector搜索承保政策...”
  • 调用后：“CMS Coverage MCP Connector执行成功 - 找到政策：[政策ID]”
  • 调用前：“正在通过CMS费用表验证诊疗代码...”
  • 调用后：“已通过CMS费用表验证CPT/HCPCS代码 - 已检查[N]个代码”

File Structure

文件结构

See README.md File Organization section for complete directory structure and file descriptions.
完整的目录结构及文件说明请查看README.md的文件组织部分。

Decision Policy

决策政策

This skill enforces a decision policy rubric that determines the outcome when validation checks fail. The policy balances regulatory compliance, patient safety, and operational efficiency.
See references/rubric.md for:
  • Complete decision policy matrix (STRICT vs LENIENT enforcement)
  • Detailed decision logic flow and pseudocode
  • Override authority rules
  • Customization examples (lenient mode, strict compliance mode, auto-approval mode)
Quick Summary:
  • STRICT policies → Automatic DENY (provider verification, invalid codes, criteria NOT_MET)
  • LENIENT policies → Automatic PEND (insufficient evidence, missing policy)
  • Default fallback → PEND (when unclear)
To customize decision logic for your organization, edit references/rubric.md.
本Skill执行决策政策准则，用于在验证检查失败时确定结果。该政策平衡了法规合规性、患者安全性与运营效率。
查看references/rubric.md了解：
  • 完整的决策政策矩阵（严格模式 vs 宽松模式）
  • 详细的决策逻辑流程与伪代码
  • 权限覆盖规则
  • 自定义示例（宽松模式、严格合规模式、自动批准模式）
快速摘要：
  • 严格政策 → 自动拒绝（提供者验证失败、代码无效、未满足标准）
  • 宽松政策 → 自动挂起（证据不足、政策缺失）
  • 默认回退 → 挂起（情况不明确时）
如需为您的机构自定义决策逻辑，请编辑references/rubric.md。

How to Use

使用方法

Process PA Request

处理PA请求

Simply invoke the skill:
Use the prior-auth-review-skill
The skill will:
  1. Check for incomplete requests (auto-resume if found)
  2. Collect PA request details
  3. Execute Subskill 1: Intake & Assessment
  4. Execute Subskill 2: Decision & Notification
  5. Output authorization decision package
只需调用本Skill：
Use the prior-auth-review-skill
Skill将执行以下操作：
  1. 检查是否存在未完成的请求（如发现则自动恢复）
  2. 收集PA请求详情
  3. 执行子Skill 1：信息采集与评估
  4. 执行子Skill 2：决策与通知
  5. 输出授权决策包

Execution Flow

执行流程

When this skill is invoked:
当本Skill被调用时：

Startup: Check MCP Configuration

启动：检查MCP配置

Before proceeding, verify required MCP connectors are available.
Check for the following MCP connectors:
  1. CMS Coverage MCP - Required for coverage policy lookup
  2. ICD-10 MCP - Required for diagnosis code validation
  3. NPI MCP - Required for provider verification
If any MCP connectors are not configured:
Display error and exit:
"Missing required MCP connectors: [list missing connectors]. This skill requires all three healthcare MCP connectors to function. Please configure the missing connectors and try again. See README Prerequisites for setup instructions."
Exit skill.
If all MCP connectors are available: Proceed silently to next step.
在继续之前，请验证所需的MCP连接器是否可用。
检查以下MCP连接器：
  1. CMS Coverage MCP - 用于承保政策查询
  2. ICD-10 MCP - 用于诊断代码验证
  3. NPI MCP - 用于提供者资质验证
若任何MCP连接器未配置：
显示错误并退出：
"缺少所需的MCP连接器：[列出缺失的连接器]。本Skill需要全部三个医疗MCP连接器才能运行。请配置缺失的连接器后重试。设置说明请查看README的前置条件部分。"
退出Skill。
若所有MCP连接器均可用： 静默进入下一步。

Startup: Request Input Files

启动：请求输入文件

Prompt the user to provide input files or use sample data.
Display the following prompt:
Prior Authorization Review requires the following input files:

REQUIRED FILES:
1. Prior Authorization Request Form (PDF) - Contains member info, requested service, provider details
2. Clinical Notes / H&P (PDF) - History and physical examination documentation
3. Diagnostic Imaging Reports (PDF) - CT, MRI, X-ray, or other imaging results
4. Laboratory Results (PDF) - Relevant lab work supporting medical necessity
5. Additional Supporting Documentation (PDF, optional) - PFTs, specialist consults, etc.

OPTIONS:
(A) Upload your own files - Provide paths to each required document
(B) Use sample files - Load pre-configured sample case (CT-guided lung biopsy)

Enter your choice (A/B): ___
If user selects (A) - Upload own files:
  • Prompt for path to each required file
  • Validate files exist and are readable
  • Store file paths for use in Subskill 1
  • Set 
    using_sample_files = False
If user selects (B) - Use sample files:
  • Load sample files from 
    assets/sample/
    : 
    • 01_Prior_Auth_Request_Form.pdf
    • 02_Clinical_Notes_H_and_P.pdf
    • 03_CT_Chest_Report.pdf
    • 04_Laboratory_Results.pdf
    • 05_Pulmonary_Function_Tests.pdf
  • Display: "Loading sample case: CT-guided transbronchial lung biopsy for 1.2cm RUL nodule"
  • Set 
    using_sample_files = True
  • Demo mode note: When sample files are used, the sample data contains demo NPI (
    1234567890
    ) and sample member ID (
    1EG4-TE5-MK72
    ). This combination triggers demo mode, which skips the NPI MCP lookup for this specific provider only. All other MCP calls (ICD-10 validation, CMS Coverage policy search) execute normally.
提示用户提供输入文件或使用示例数据。
显示以下提示：
预先授权审核需要以下输入文件：

必填文件：
1. 预先授权请求表（PDF） - 包含会员信息、申请服务、提供者详情
2. 临床记录/病史与体检报告（PDF） - 病史及体格检查文档
3. 诊断影像报告（PDF） - CT、MRI、X光或其他影像结果
4. 实验室结果（PDF） - 支持医疗必要性的相关实验室检查结果
5. 额外支持文档（PDF，可选） - 肺功能测试、专科会诊报告等

选项：
(A) 上传您自己的文件 - 提供每个必填文档的路径
(B) 使用示例文件 - 加载预配置的示例案例（CT引导下肺活检）

请输入您的选择（A/B）：___
若用户选择(A) - 上传自有文件：
  • 提示输入每个必填文件的路径
  • 验证文件是否存在且可读
  • 存储文件路径以供子Skill 1使用
  • 设置
    using_sample_files = False
若用户选择(B) - 使用示例文件：
  • 从
    assets/sample/
    加载示例文件： 
    • 01_Prior_Auth_Request_Form.pdf
    • 02_Clinical_Notes_H_and_P.pdf
    • 03_CT_Chest_Report.pdf
    • 04_Laboratory_Results.pdf
    • 05_Pulmonary_Function_Tests.pdf
  • 显示：“正在加载示例案例：针对1.2cm右肺上叶结节的CT引导下经支气管肺活检”
  • 设置
    using_sample_files = True
  • 演示模式说明： 使用示例文件时，示例数据包含演示用NPI（
    1234567890
    ）和示例会员ID（
    1EG4-TE5-MK72
    ）。该组合会触发演示模式，仅针对此特定提供者跳过NPI MCP查询。所有其他MCP调用（ICD-10验证、CMS承保政策搜索）将正常执行。

Startup: Check for Existing Request

启动：检查现有请求

Check if 
waypoints/assessment.json
exists:
  • If exists and incomplete:
    Found incomplete PA request: [Request ID]
Resume this request? (Y/N): ___
    • If Y: Load assessment and continue to Subskill 2
    • If N: Archive and start new
  • If does not exist:
    • Start from Subskill 1
检查
waypoints/assessment.json
是否存在：
  • 若存在且未完成：
    发现未完成的PA请求：[请求ID]
是否恢复此请求？（Y/N）：___
    • 若选择Y：加载评估结果并进入子Skill 2
    • 若选择N：归档并开始新请求
  • 若不存在：
    • 从子Skill 1开始

Subskill 1: Intake & Assessment

子Skill 1：信息采集与评估

Execute: Read and follow 
references/01-intake-assessment.md
What it does:
  1. Collect PA request information
  2. Validate provider credentials and codes (parallel MCP calls)
  3. Search coverage policies
  4. Extract clinical data
  5. Assess medical necessity against policy criteria
  6. Generate recommendation (APPROVE/DENY/PEND)
Output: 
waypoints/assessment.json
(consolidated)
Duration: 3-4 minutes
Ask user:
Ready to proceed to Subskill 2? (Y/N): ___
  • If Y: Continue to Subskill 2
  • If N: Save and exit
执行： 阅读并遵循
references/01-intake-assessment.md
的说明
功能：
  1. 收集PA请求信息
  2. 验证提供者资质与代码（并行MCP调用）
  3. 搜索承保政策
  4. 提取临床数据
  5. 对照政策标准评估医疗必要性
  6. 生成建议（批准/拒绝/挂起）
输出： 
waypoints/assessment.json
（整合结果）
耗时： 3-4分钟
询问用户：
是否准备进入子Skill 2？（Y/N）：___
  • 若选择Y：进入子Skill 2
  • 若选择N：保存并退出

Subskill 2: Decision & Notification

子Skill 2：决策与通知

Execute: Read and follow 
references/02-decision-notification.md
What it does:
  1. Load assessment from Subskill 1
  2. Confirm or override recommendation
  3. Generate decision-specific content:
    • Approval: Auth number, validity dates, limitations
    • Denial: Specific reasons, policy references, appeal rights
    • Pend: Documentation requests, submission deadline
  4. Create provider notification letter
  5. Document audit trail
Output:
  • waypoints/decision.json
    (final decision)
  • outputs/notification_letter.txt
    (provider notification)
Duration: 1-2 minutes
执行： 阅读并遵循
references/02-decision-notification.md
的说明
功能：
  1. 加载子Skill 1的评估结果
  2. 确认或覆盖建议
  3. 生成特定决策内容：
    • 批准： 授权编号、有效期、限制条件
    • 拒绝： 具体理由、政策参考、申诉权利
    • 挂起： 补充文档要求、提交截止日期
  4. 创建提供者通知函
  5. 记录审计跟踪
输出：
  • waypoints/decision.json
    （最终决策）
  • outputs/notification_letter.txt
    （提供者通知）
耗时： 1-2分钟

Final Summary

最终摘要

Display a concise completion message with:
  • Request details (ID, member, service, decision outcome)
  • Authorization number and validity dates (if approved)
  • Files generated (waypoints and notification)
  • Next steps based on decision type
Offer user options to:
  1. View decision letter
  2. Start new PA review
  3. Exit
显示简洁的完成消息，包含：
  • 请求详情（ID、会员、服务、决策结果）
  • 授权编号及有效期（若批准）
  • 生成的文件（路径点文件与通知函）
  • 根据决策类型的后续步骤
为用户提供以下选项：
  1. 查看决策函
  2. 开始新的PA审核
  3. 退出

Error Handling

错误处理

Missing MCP Servers: If required MCP connectors not available, display error listing missing connectors and Removefully.
Missing Subskill Prerequisites: If Subskill 2 invoked without 
waypoints/assessment.json
, notify user to complete Subskill 1 first.
File Write Errors: If unable to write waypoint files, display error with file path, check permissions/disk space, and offer retry.
Data Quality Issues: If clinical data extraction confidence <60%, warn user with confidence score and low-confidence areas. Offer options to: continue, request additional documentation, or abort.
For all errors, provide clear, actionable messages and user options for resolution.
缺少MCP服务器： 若所需MCP连接器不可用，显示列出缺失连接器的错误信息并完全退出。
缺少子Skill前置条件： 若未生成
waypoints/assessment.json
即调用子Skill 2，通知用户需先完成子Skill 1。
文件写入错误： 若无法写入路径点文件，显示包含文件路径的错误信息，检查权限/磁盘空间，并提供重试选项。
数据质量问题： 若临床数据提取置信度<60%，向用户发出警告并告知置信度得分及低置信度区域。提供以下选项：继续、请求补充文档、或中止。
所有错误均需提供清晰、可操作的消息及用户解决选项。

Quality Checks

质量检查

Before completing workflow, verify:
  • All required waypoint files created
  • Decision has clear rationale documented
  • All required fields populated
  • Output files generated successfully
完成工作流前，验证：
  • 已创建所有所需的路径点文件
  • 决策已记录明确的理由
  • 所有必填字段已填充
  • 输出文件已成功生成

Implementation Requirements

实现要求

  1. Always read subskill files: Don't execute from memory. Read the actual subskill markdown file and follow instructions.
  2. Auto-detect resume: Check for existing 
    waypoints/assessment.json
    on startup. If found and status is not "assessment_complete", offer to resume.
  3. Parallel MCP execution: In Subskill 1, execute NPI, ICD-10, and Coverage MCP calls in parallel for optimal performance.
  4. Preserve user data: Never overwrite waypoint files without asking confirmation or backing up.
  5. Clear progress indicators: Show users what's happening during operations (MCP queries, data analysis).
  6. Graceful degradation: If optional data missing, continue with available data and note limitations.
  7. Validate outputs: Check that waypoint files have expected structure before proceeding.
  1. 始终阅读子Skill文件： 不要凭记忆执行。请阅读实际的子Skill markdown文件并遵循说明。
  2. 自动检测恢复： 启动时检查是否存在
    waypoints/assessment.json
    。若存在且状态为“未完成评估”，提供恢复选项。
  3. 并行MCP执行： 在子Skill 1中，并行执行NPI、ICD-10与承保MCP调用以优化性能。
  4. 保留用户数据： 未经确认或备份，切勿覆盖路径点文件。
  5. 清晰的进度指示： 在操作过程中向用户显示当前进展（MCP查询、数据分析等）。
  6. 优雅降级： 若可选数据缺失，使用现有数据继续并注明限制条件。
  7. 验证输出： 进入下一步前，检查路径点文件是否符合预期结构。

MCP Tool Call Transparency (REQUIRED)

MCP工具调用透明度（必填）

CRITICAL: Every time you invoke an MCP tool or WebFetch for code validation:
BEFORE the call:
  • Display a simple notification explaining which connector is being used and what data is being queried
  • Example: "Verifying provider credentials via NPI MCP Connector..."
AFTER receiving results:
  • Display a brief summary of findings
  • Example: "NPI MCP Connector completed successfully - Provider verified: Dr. [Name] ([Specialty])"
If there's an issue:
  • Explain what went wrong and what happens next
  • Example: "NPI verification failed - Provider NPI not found in database. This will result in automatic DENY per policy."
Benefits:
  • Provides audit trail of all data sources consulted
  • Demonstrates thoroughness of review process
  • Highlights MCP connector capabilities
  • Makes AI decision-making transparent and explainable
  • Helps users understand what information drives recommendations
Requirements:
  • Display notification BEFORE and AFTER each MCP/WebFetch call
  • Keep notifications concise and informative
  • Always include brief summary of findings
  • Apply to ALL data lookups: NPI, ICD-10, CMS Coverage, and CPT/HCPCS validation
关键要求： 每次调用MCP工具或WebFetch进行代码验证时：
调用前：
  • 显示简单通知，说明正在使用的连接器及查询的数据
  • 示例：“正在通过NPI MCP Connector验证提供者资质...”
收到结果后：
  • 显示简要的结果摘要
  • 示例：“NPI MCP Connector执行成功 - 提供者已验证：[姓名]医生（[专科]）”
若出现问题：
  • 说明问题及后续处理
  • 示例：“NPI验证失败 - 提供者NPI未在数据库中找到。根据政策，此情况将自动拒绝。”
优势：
  • 提供所有咨询数据源的审计跟踪
  • 展示审核流程的全面性
  • 突出MCP连接器的能力
  • 使AI决策过程透明且可解释
  • 帮助用户了解驱动建议的信息
要求：
  • 每次MCP/WebFetch调用前后均显示通知
  • 通知需简洁且信息丰富
  • 始终包含简短的结果摘要
  • 适用于所有数据查询：NPI、ICD-10、CMS承保、CPT/HCPCS验证

Common Mistakes to Avoid

需避免的常见错误

  • ❌ Don't generate fake data when MCP queries fail
  • ❌ Don't skip prerequisite checks
  • ❌ Don't overwrite existing files without checking
  • ❌ Don't proceed if current subskill had errors
  • ❌ Don't call ICD-10 MCP multiple times for same codes
  • ✅ DO provide clear, actionable error messages
  • ✅ DO give users options when things go wrong
  • ✅ DO validate data quality at each step
  • ✅ DO execute MCP calls in parallel where possible
  • ❌ 不要在MCP查询失败时生成虚假数据
  • ❌ 不要跳过前置条件检查
  • ❌ 不要未经检查覆盖现有文件
  • ❌ 当前子Skill出现错误时不要继续
  • ❌ 不要对相同代码多次调用ICD-10 MCP
  • ✅ 务必提供清晰、可操作的错误消息
  • ✅ 出现问题时务必为用户提供选项
  • ✅ 务必在每个步骤验证数据质量
  • ✅ 尽可能并行执行MCP调用

Subskill Descriptions

子Skill说明

Subskill 1: Intake & Assessment (3-4 minutes)

子Skill 1：信息采集与评估（3-4分钟）

  • Collects PA request details (member, service, provider, clinical docs)
  • Validates provider credentials via NPI MCP
  • Validates and retrieves ICD-10 code details via ICD-10 MCP (single batch call)
  • Validates CPT/HCPCS codes via WebFetch to CMS Fee Schedule
  • Searches coverage policies via CMS Coverage MCP
  • Extracts structured clinical data from documentation
  • Maps clinical evidence to policy criteria
  • Performs medical necessity assessment
  • Generates recommendation (APPROVE/DENY/PEND)
  • Output: 
    waypoints/assessment.json
    (consolidated)
  • Data Sources: NPI MCP, ICD-10 MCP, CMS Coverage MCP (parallel), CMS Fee Schedule (web)
  • 收集PA请求详情（会员、服务、提供者、临床文档）
  • 通过NPI MCP验证提供者资质
  • 通过ICD-10 MCP验证并获取ICD-10代码详情（单次批量调用）
  • 通过WebFetch访问CMS费用表验证CPT/HCPCS代码
  • 通过CMS Coverage MCP搜索承保政策
  • 从文档中提取结构化临床数据
  • 将临床证据映射到政策标准
  • 执行医疗必要性评估
  • 生成建议（批准/拒绝/挂起）
  • 输出： 
    waypoints/assessment.json
    （整合结果）
  • 数据源： NPI MCP、ICD-10 MCP、CMS Coverage MCP（并行）、CMS费用表（网络）

Subskill 2: Decision & Notification (1-2 minutes)

子Skill 2：决策与通知（1-2分钟）

  • Loads assessment from Subskill 1
  • Confirms or allows override of recommendation
  • Generates authorization number (if approved) or denial rationale (if denied)
  • Creates provider notification letter
  • Documents complete audit trail
  • Output: 
    waypoints/decision.json
    and notification letter
  • 加载子Skill 1的评估结果
  • 确认或允许覆盖建议
  • 生成授权编号（若批准）或拒绝理由（若拒绝）
  • 创建提供者通知函
  • 记录完整的审计跟踪
  • 输出： 
    waypoints/decision.json
    与通知函