Policy Retrieve

Pulls the governing payer policy clause, contract term and coding guidance for a denial reason and attaches them as citations, or reports that none was found. Use when asked "what policy does this denial cite", "find the Contoso medical policy for CO-50", "which contract term applies here", "what does the payer's policy actually say". Use after denial-classify, on every denial. Do NOT use to search the patient's chart - use evidence-assemble instead; do NOT use to write the appeal letter - use appeal-draft instead; do NOT use to compute deadlines - use deadline-track instead. Never quotes poli

110 stars 122 forksResearch & ScienceOfficial

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add microsoft/cat-agent-skills --skill policy-retrieve
Manual install
git clone --depth 1 https://github.com/microsoft/cat-agent-skills.git /tmp/cat-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/cat-agent-skills/submissions/denials-appeals-response/policy-retrieve ~/.claude/skills/policy-retrieve

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Policy Retrieve
## Purpose
Ground the appeal in the specific payer policy or contract clause the denial cites.
## When to use
Use immediately after denial-classify, for every denial - typical asks are "what policy does this denial cite", "find the clause behind CARC CO-50", "which contract term covers this service".
## When NOT to Use
Do NOT use when: denial.reason_code is not yet populated - use denial-classify first; the ask is for clinical evidence from the record rather than payer policy - use evidence-assemble instead; the ask is to draft or reword the appeal letter - use appeal-draft instead; the ask is about the appeal window, queue order or coding decision - use deadline-track instead.
## Inputs
denial.reason_code (CARC) and denial.remark_codes (RARC); denial.original_code and service setting; the payer policy and contract-term library at [TO CONFIGURE: payer policy and contract-term library location or connector], read with the session's file or connector tool; any policy_citations already on the contract.
## Steps
1. Look up the policy clause and contract term that govern the denial's reason_code in the configured library. If the library is unavailable, skip to Error Handling - never substitute remembered text or web results.
2. Confirm the clause actually addresses that reason_code; discard near-matches. Also compare the clause's setting or service type with the claim's (e.g. an inpatient-observation section against an office E/M code) and escalate a mismatch.
Read the full skill on GitHub

Details

Skill name
policy-retrieve
Path
submissions/denials-appeals-response/policy-retrieve/SKILL.md
License
MIT
Repo updated
15 November 2026

FAQ

What does the Policy Retrieve skill do?

Pulls the governing payer policy clause, contract term and coding guidance for a denial reason and attaches them as citations, or reports that none was found. Use when asked "what policy does this denial cite", "find the Contoso medical policy for CO-50", "which contract term applies here", "what does the payer's policy actually say". Use after denial-classify, on every denial. Do NOT use to search the patient's chart - use evidence-assemble instead; do NOT use to write the appeal letter - use appeal-draft instead; do NOT use to compute deadlines - use deadline-track instead. Never quotes poli

How do I install the Policy Retrieve skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add microsoft/cat-agent-skills --skill policy-retrieve. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Policy Retrieve popular?

It lives in microsoft/cat-agent-skills, which has 110 GitHub stars and 122 forks.

Related skills

3 Statements

110

microsoft/cat-agent-skills

Completes existing income statement, balance sheet and cash flow templates while preserving layout, grounding historical inputs and linking forecast formulas with reconciliation checks. Use for "fill in a 3-statement template", "complete an IS/BS/CF framework", "populate my integrated financial model", "link statements in this template", or "finish the forecasts in my three-statement workbook". Do NOT use for blank-slate models or general workbook edits (use xlsx), DCF valuation (use dcf-valuation), or buyout modeling (use lbo-model).

AI, LLMs & Agents122

Accessibility Pass

110

microsoft/cat-agent-skills

Use this skill whenever the user asks to check, review, or fix the accessibility of a PowerPoint deck, Word document, HTML page, or Markdown file, and before handing over any deck or document this agent just generated, so it does not ship with missing alt text, untitled slides, or unreadable colour contrast.

Frontend & Design122

Accessible Learning Materials

110

microsoft/cat-agent-skills

Maintains instructionally equivalent, accessible variants of a set of learning materials — lessons, readings, slides, and handouts — with parity checks against the original learning goals and recorded approvals. Use when the user asks to "make these materials accessible", "audit this lesson set for accessibility", "create an accessible version of this reading", "check reading level and alt text", or "keep my accessible variants in sync". Do NOT use for individual student accommodation or support-plan decisions (IEP, EHCP, or local equivalent), and do NOT use for generic document formatting (us

Learning & Education122

Quality Gap Check

110

microsoft/cat-agent-skills

Deterministic engine that scores the encounter against the configured quality measures from documented, cited facts only, and refuses, logs and escalates any attempt to change a measure's status however it is worded. Use when the user says "which quality measures are open?", "run the gap check", "mark this measure as met", "can you just count this one?" or "note that it was likely done so it counts this quarter". Do NOT use for supporting evidence for a claim code - use coding-rationale instead; do NOT use to draft documents or the handoff - use document-derive or handoff-draft instead; do NOT

Research & Science122

Policy Gap Analysis

110

microsoft/cat-agent-skills

Compares a firm policy to a regulation clause by clause, giving a coverage table with verbatim excerpts, suggested edits and a memo. Reports coverage states; never concludes compliance. Use when the user says "does our policy cover this regulation", "where are the gaps against this rule", "map our procedure to the requirements", "compare our AML policy to the rule", or "what needs to change in this policy". Do NOT use for customer or counterparty research or EDD packs (use kyc-research-pack), firm-wide triage of a new rule (use reg-change-triage), enforcement read-across (use enforcement-actio

Research & Science122

Research Project Brief

110

microsoft/cat-agent-skills

Maintains a living research project brief for higher-education faculty and research staff: literature, methods, collaborator input, decisions, milestones, disagreements, and open questions, with source freshness tracked across runs. Use when the user asks to "update my research project brief", "what's the state of this project", "summarize where the literature and methods stand", "what did collaborators decide", or "what's blocking the next milestone". Do NOT use for public web literature reviews with citations (use deep-research) or for grant evidence packages (use evidence-package-for-educat

Research & Science122

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.