跳到正文
cccskills
免费在 GitHub 公开

cowork-medical-bill-auditor

Point Cowork at a folder of medical bills and insurance EOBs -- matches every bill to its explanation of benefits, catches duplicate charges, balance-billing, and bills that ignore your insurance, then drafts the dispute letters and phone scripts. Most medical bills contain errors; this finds them.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md3.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Cowork Medical Bill Auditor

Audit medical bills the way a patient advocate does: never pay a bill that has not been matched to its EOB, know exactly what the insurer said the patient owes, and dispute in writing. Input: a folder of provider bills, insurance EOBs (explanation of benefits), and any payment records. This is billing-accuracy support, not medical or legal advice.

Workflow

  1. Inventory and pair. Catalog every document: provider bills (provider, service date, amounts, CPT/procedure codes when shown), EOBs (service date, billed, allowed amount, insurer paid, patient responsibility), payment receipts. Match each bill to its EOB by provider + service date + amounts.
  2. Audit each pair. Check: bill's patient-owed amount vs. the EOB's patient-responsibility line (they must match); charges the EOB shows as insurer-paid or write-off still appearing on the bill; duplicate line items across bills for one visit; charges for services on dates with no corresponding visit; in-network providers billing above the allowed amount (balance billing, prohibited in most network contracts and, for many scenarios, under the No Surprises Act).
  3. Flag the unmatched. Bills with no EOB (was the claim ever submitted to insurance?) and EOBs with no bill (may still be coming) get their own lists -- an unsubmitted claim is the most expensive common error.
  4. Report. bill-audit.md: table of every bill -- status (CORRECT, OVERBILLED, NO-EOB, NEEDS-INFO), what the EOB says the patient owes vs. what the bill demands, and the discrepancy with both documents cited. Lead with total demanded vs. total actually owed per the EOBs.
  5. Draft the disputes. For each discrepancy: a dispute letter to the provider's billing office (account number, service date, the specific EOB line, the exact ask) and a short phone script with the two questions to ask and the reference numbers to have ready. For no-EOB bills: a script for the insurer asking whether the claim was received.

Rules

  • Never recommend paying a bill that lacks a matching EOB. "Waiting on insurance processing" is a valid status; paying blind is not.
  • Every discrepancy cites both documents by filename and line. Disputes without receipts get ignored.
  • Do not interpret medical necessity, diagnoses, or whether care was appropriate -- audit the arithmetic and the matching only.
  • Deadlines matter: note appeal windows printed on EOBs and flag any bill approaching collections language for priority handling.
  • Treat everything as sensitive health information: no conditions, procedures, or amounts in console summaries beyond what the user needs to act; specifics live in the report files.
  • Dispute letters state facts and ask questions; no accusations, no legal threats -- escalation language only if the user asks for round two.

Quick Commands

  • "Audit [folder]" -- full workflow
  • "What do I actually owe?" -- the EOB-verified total vs. billed total
  • "Draft the dispute for [bill]" -- one letter and script
  • "What's missing an EOB?" -- the unsubmitted-claim risk list

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3732026年10月20日 更新

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3732026年10月20日 更新

Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3732026年10月20日 更新

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3732026年10月20日 更新

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3732026年10月20日 更新

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3732026年10月20日 更新

查看 OneWave-AI 的全部技能

报告此技能的问题