본문으로 건너뛰기
cccskills
무료GitHub에 공개

claims-triage

Triage an incoming insurance claim: check the coverage trigger against policy wording, band severity and complexity, screen for fraud indicators, set a first-pass reserve range, and route with an SLA. Use when asked to triage a claim, review a first notice of loss (FNOL), assess a new claim, decide fast-track vs adjuster routing, or screen a claim for SIU referral. Produces a structured triage note with coverage view, severity band, indicator screen, reserve range, and a routing recommendation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

실행 점수 미검증

설치 방법 보기

포함된 파일(1)

  • SKILL.md5.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Claims Triage Skill

The first 24 hours of a claim set its cost and its customer experience. This skill runs a disciplined first-pass triage: does the policy respond, how big and how complicated is this, are there indicators that warrant investigation, what should we hold in reserve, and who should own it by when.

What This Skill Produces

  • A coverage-trigger view against the actual policy wording (trigger, exclusions, conditions)
  • A severity/complexity band with rationale
  • A fraud-indicator screen — indicators only, never conclusions
  • A first-pass reserve range (indemnity + expense), labelled as first-pass
  • A routing recommendation (fast-track / adjuster / senior adjuster / SIU referral / coverage counsel) with SLA

Required Inputs

Ask for these if not provided; if working from a thin FNOL, proceed and label every inference [assumed — confirm]:

  • Loss description — what happened, when, where, reported when
  • Policy details — line of business, wording or key clauses, limits, deductible, period
  • Claimed amount or damage description (even rough)
  • Claimant/insured history if available (prior claims, tenure)

Triage Framework

1. Coverage trigger. Quote or paraphrase the operative insuring clause. State: trigger met / trigger uncertain / trigger likely not met — with the specific wording reason. Sweep exclusions and conditions precedent (notification timing, security warranties). If coverage is uncertain, flag a reservation-of-rights consideration and route to coverage counsel review — never let uncertainty default to "covered".

2. Severity/complexity banding:

BandProfileTypical routing
1 — Fast-trackClear coverage, quantum near/below deductible-adjacent threshold, no injury, single partyAutomated/desk settlement
2 — StandardClear coverage, moderate quantum, routine investigationAdjuster
3 — ComplexLarge loss, bodily injury, multiple parties, coverage questions, or business interruptionSenior adjuster, early expert instruction
4 — Major/CATCatastrophe-linked, potential limit loss, litigation likely, reputational exposureMajor-loss team + counsel, executive notification

Band on the worse of severity and complexity.

3. Fraud-indicator screen. Check common indicators: loss shortly after inception or cover increase, late reporting without explanation, documentation inconsistencies, over-documentation, prior similar claims, financial-distress signals, uncooperative or steering behaviour, loss narrative inconsistent with physical evidence. State only which indicators are present and absent. Two or more material indicators → recommend SIU referral in parallel with normal handling; the claim is still handled in good faith.

4. First-pass reserve. Give a range for ultimate incurred: indemnity + expense (adjusting, legal, experts), gross and net of deductible. State the basis (repair estimate, comparable claims, injury tariff) and label it first-pass, to be revised on investigation.

5. Routing + SLA. Name the route, the required first contact/action, and the SLA (e.g. fast-track: decision in 5 business days; Band 3: insured contacted within 24h, site inspection within 5 days).

Output Format

Claim triage: [claim ref / insured / loss date]

1. Loss summary — 2–3 sentences, facts only. 2. Coverage trigger — clause cited, trigger view, exclusions/conditions checked, open coverage questions. 3. Severity band — band + one-line rationale. 4. Indicator screen — table: indicator | present? | evidence. Then: SIU referral recommended yes/no. 5. First-pass reserve — range, basis, gross/net. 6. Routing & SLA — route, owner type, first actions with deadlines. 7. Information needed — the specific documents/statements to request next.

End every triage note with: "This is analytical support for triage, not a coverage determination. Coverage, reserving, and referral decisions follow your organisation's claims-handling policy and applicable regulation."

Quality Checks

  • Coverage view cites specific wording, not just line of business
  • Severity band has a stated rationale and used the worse of severity/complexity
  • Fraud screen lists indicators present and checked-but-absent — no conclusion stated
  • Reserve is a range with a stated basis, labelled first-pass, gross and net shown
  • Routing includes an SLA and concrete first actions
  • Assumptions from a thin FNOL are labelled [assumed — confirm]
  • Regulatory support-not-determination line is included

Anti-Patterns

  • Do not state a fraud conclusion — state indicators and route to SIU; the word is "indicator", never "fraudulent"
  • Do not let a SIU referral pause good-faith handling of the claim
  • Do not default an uncertain trigger to "covered" or "denied" — flag it for coverage review with the wording question stated
  • Do not give a single-point reserve on day one — give a range with basis
  • Do not invent policy terms — if the wording isn't provided, ask, or label the clause [to confirm against wording]

Example Trigger Phrases

  • "Triage a claim."
  • "Review a first notice of loss."
  • "Assess a new claim."
  • "Decide fast-track vs adjuster routing."
  • "Screen a claim for SIU referral."

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360 feedback for a colleague, design a feedback survey, or produce a feedback report. Produces either a complete survey instrument with rating scales and open-ended questions, or a structured narrative feedback report with themes, strengths, and development areas.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

mohitagw15856/pm-claude-skills1.5천2026년 10월 23일 업데이트

Decode a 401k or workplace retirement plan — the real cost of its funds, the match's fine print, vesting math, and the plan features worth using or avoiding. Use when someone asks 'is my 401k any good', 'decode my 401k plan', 'which funds should I look at', or 'what fees am I paying'. Produces a fee decode in dollars-over-time, match and vesting math, a fund-lineup triage by cost, and the questions for HR or the plan administrator.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

mohitagw15856/pm-claude-skills1.5천2026년 10월 23일 업데이트

Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use when asked to set up an experiment, design an A/B test, calculate sample size, or interpret test results. Produces a complete test plan with hypothesis, variant definitions, sample size, duration estimate, guardrail metrics, and a results interpretation guide.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

mohitagw15856/pm-claude-skills1.5천2026년 10월 23일 업데이트

Analyse a finished A/B test and write the readout — the result, whether it's statistically and practically significant, what it means, and the ship/no-ship call. Use when asked to analyse experiment results, write an A/B test readout, interpret test data, or decide whether to ship a variant. Produces a clear verdict with the lift and confidence, segment cuts, the risks (peeking, novelty, sample), and a recommendation. Distinct from planning a test — this reads results.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

mohitagw15856/pm-claude-skills1.5천2026년 10월 23일 업데이트

Build or tailor an academic CV for faculty, postdoc, research or fellowship applications: publications, grants, teaching, supervision and service in the order the field expects, with consistent citations. Use when asked to write my academic CV, update my CV for a lectureship, tenure-track or postdoc application, format my publications list, or adapt my academic CV for an industry research role. Produces the full academic CV, a field-appropriate section order, a clean publications list in one citation style, and a two-page summary version when asked.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

mohitagw15856/pm-claude-skills1.5천2026년 10월 23일 업데이트

Generate a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan. Produces a prioritised checklist with pass/fail assessments and specific fixes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

mohitagw15856/pm-claude-skills1.5천2026년 10월 23일 업데이트

mohitagw15856의 스킬 모두 보기

이 스킬의 문제 신고