Insurance Operations Automation
npx skills add https://github.com/FDU-INS/Insurance-Skills --skill afrexai-insurance-automationCopy and paste this command into Claude Code to install the skill
Insurance Claims Processor
Policy Writer
Manage Allstate insurance with Drivewise and Milewise programs.
Analyze latest policy analysis sweep runs (*_policy_analysis_*) by comparing episodes/summary metrics, diagnostics, and video artifacts; generate a concise markdown report and optional frame snapshots.
既存の自動車保険契約を解約し、contracts.csv を更新する。
新規の自動車保険契約を contracts.csv に登録する。
| name | afrexai-insurance-automation |
| description | Insurance Operations Automation |
Comprehensive insurance operations framework for AI agents. Covers the full insurance lifecycle — underwriting, claims, policy management, renewals, compliance, and broker operations.
Guides your AI agent through insurance-specific workflows with industry benchmarks, regulatory requirements, and automation priorities.
| Metric | Personal Lines Target | Commercial Target |
|---|---|---|
| Combined Ratio | 95-98% | 88-95% |
| Loss Ratio | 60-70% | 55-65% |
| Expense Ratio | 25-32% | 28-35% |
| Claims Settlement Time | <48h (auto) | <14 days |
| Policy Issuance Time | <15 min | <24h |
| Renewal Rate | >85% | >80% |
| Quote-to-Bind Ratio | >25% | >15% |
| NPS | >40 | >35 |
| Process | Hours/Month (50-person broker) | Agent-Ready? | Expected Savings |
|---|---|---|---|
| Quote comparison | 160h | Yes — now | $140K-$280K/yr |
| FNOL intake | 120h | Yes — now | $105K-$210K/yr |
| Policy document generation | 80h | Yes — now | $70K-$140K/yr |
| Renewal processing | 100h | Yes — now | $87K-$175K/yr |
| Compliance checks | 60h | Yes — now | $52K-$105K/yr |
| Subrogation identification | 40h | Partial | $35K-$70K/yr |
| Complex claims adjustment | 200h | Human-in-loop | $50K-$100K/yr |
Underwriting Agent:
You are an underwriting assessment agent. For each submission:
1. Extract all risk factors from the application
2. Score each factor against the risk matrix (1-10 scale)
3. Calculate composite risk score (weighted by line of business)
4. Flag any referral triggers (prior losses >3 in 5yr, credit <600, high-hazard occupation)
5. Recommend: Auto-approve / Refer to senior / Decline with reason
6. Generate underwriting memo with supporting data
Claims Triage Agent:
You are a claims triage agent. For each FNOL:
1. Extract: date of loss, type, description, estimated amount, policyholder details
2. Verify active coverage and applicable endorsements
3. Assign severity: Green (<$2K auto-process) / Yellow ($2K-$25K adjuster) / Red (>$25K or fraud flags)
4. Check fraud indicators against the 15-point SIU trigger list
5. Set initial reserve based on claim type benchmarks
6. Route to appropriate handler with priority score
Month 1: Deploy intake + quote comparison agents. Target: 70% of personal lines quotes handled autonomously.
Month 2: Add claims triage + policy document generation. Target: FNOL processing <5 minutes, auto-approval for Green claims.
Month 3: Compliance monitoring + renewal automation. Target: 85%+ renewal rate, zero compliance gaps.