Insurance: Claims Fraud Signal Review with Claude Code: SKILL.md Template
A production playbook for claims fraud signal review in insurance operations using Claude Code: skill.md template, run-scoped inputs, logs, typed results, and artifacts.
Audience: Insurance fraud investigation teams
The problem
Insurance fraud investigation teams need claims fraud signal review to run repeatedly against claim packets, photos, histories, provider records, and fraud indicators. In insurance operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Put the operating procedure in SKILL.md, keep examples beside the skill, attach claim packets, photos, histories, provider records, and fraud indicators per run, and let Argo turn the folder into a repeatable Claude Code execution.
Tradeoffs and failure modes
A skill folder is less flexible than an open chat, but it gives the product a versioned workflow that can be tested and rolled back. For claims fraud signal review, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
SKILL.md starter
# SKILL.md
You run claims fraud signal review using Claude Code.
Read only /skill/.argo/inputs.
Write artifacts to /skill/output/artifacts.
Return argo.result.v1 with body.type = "insurance_fraud_signal_review".
Run this on Argo