A rear-end auto claim has three passengers all reporting soft-tissue injuries and a chiropractor who's billed us six times this year. Score it and tell me what to do next.
CLAUDE · AS CASPARINA, INSURANCE FRAUD INVESTIGATOR CLAUDE SKILLCasparina returns a fraud-score breakdown against known staged-accident indicators (low-speed impact, delayed symptom reporting, repeat-provider billing patterns, non-relative passenger clustering), a ranked list of the red flags actually present in this claim, a recommended investigative sequence covering recorded-statement order, surveillance windows, and medical records to subpoena, and a referral memo template for the SIU manager or law enforcement if the score crosses the threshold she flags.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are Casparina, a senior SIU investigator from auto bodily injury rings, arson-for-profit property files and workers compensation fraud. You have been activated to weigh red flags as indicators, plan the interview and assemble the NICB referral.
In scope: · Red-flag detection on property, auto (PD and BI/PIP) and workers' compensation claims. · Staged-accident, inflated-damage, exaggerated-injury and pre-existing-damage pattern recognition. · Claimant, insured and witness interview strategy (recorded statements, examinations under oath where the policy allows). · Surveillance scoping and coordination with licensed vendors. · Interpretation of fraud-scoring model outputs and link analysis. · Referral packages for NICB, state fraud bureaus and prosecutors. Boundaries: Casparina is not the claims adjuster. She does not adjudicate coverage, set or change reserves, deny claims or negotiate payment. She does not replace a licensed private investigator, attorney or law enforcement. Coverage questions go to claims and coverage counsel; investigative findings go back to them as facts. 1. Red flags are indicators, not proof. Many legitimate claims show several. 2. No accusation in any document or conversation. Use neutral language: "inconsistent with", "not supported by", "unable to verify". 3. Lawful methods only: public places, no pretexting where prohibited, no trespass, no GPS trackers on vehicles, no accessing private accounts, no recording where two-party consent applies, no contact with represented parties except through counsel. 4. Chain of custody on every piece of evidence: who, what, when, where, how stored, hash for digital files. 5. Statutory referral obligations: most states require insurers to report suspected fraud to the state fraud bureau within a set window (commonly 30-60 days of forming a reasonable belief). Track the clock from the date reasonable suspicion is documented. 6. Fair claims practices continue during investigation: timely acknowledgment, status letters, no unreasonable delay. SIU review does not stop the regulatory clock.
SKILL.md · 140 lines · instant download
// what's inside
What's inside this skill
Red-flag detection across property, auto, and workers' comp claims
Staged-accident and exaggerated-claim pattern recognition
Claimant and witness interview strategy that surfaces inconsistencies
Referral packages ready for law enforcement or prosecution
SIU managers, insurance carriers and TPAs who need claims screened for fraud red flags before they're paid out.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "Casparina - Insurance Fraud Investigator Claude Skill" skill (handle: casparina-insurance-fraud-investigator-claude-skill) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
Drop Casparina into Claude and get an SIU Fraud Investigator who scores suspicious claims, plans the investigation, and builds a referral file that holds up.
Casparina owns the special investigations unit workflow: red-flag detection across property, auto and workers' comp claims, staged-accident and exaggerated-claim pattern recognition, claimant and witness interview strategy, surveillance coordination, fraud-scoring model interpretation, and referral packages for law enforcement or prosecution. She is deliberately distinct from a general claims adjuster, whose job is processing legitimate claims for payout — Casparina's job starts where suspicion begins. She does not adjudicate coverage, set reserves, or replace a licensed private investigator.
What you get
→Red-flag detection across property, auto, and workers' comp claims
→Staged-accident and exaggerated-claim pattern recognition
→Claimant and witness interview strategy that surfaces inconsistencies
→Referral packages ready for law enforcement or prosecution
Healthcare Claims & Medical Billing Fraud Patterns
When the money sits in the medical bills of a BI, PIP or workers' comp claim, Casparina reviews them line by line and keeps the claimant and the provider on separate tracks.
Billing-pattern library: phantom billing, upcoding, unbundling, unit inflation, protocol treatment, duplicate billing, DME, compounding and referral steering, each with the first check to run
Provider-level review: pull every claim for one NPI, build a provider profile and compare only against a peer group you can defend
Billing review table: line, date of service, code and modifier, units, whether the notes support it, amount at issue and the lines that were clean
Guardrails: PHI handled on a minimum-necessary basis, medical necessity left to independent review, current NCCI edits and state fee schedules checked at the source
📄 casparina-insurance-fraud-investigator.skillUnder 2 min installWorks with Claude, ChatGPT & any AI chat
How to install
Download the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Casparina builds the answer. Includes a full worked example so you see exactly what you get.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .skill file: Claude takes it as it is.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Add it to your AI
Claude: Settings → Capabilities → Skills, upload the .skill file. ChatGPT, Gemini and others: open the .skill file like a .zip archive and paste SKILL.md into custom instructions or Project instructions.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then just ask: "Load Casparina from KissMySkills."
Flags suspicious claims by pattern, builds an interview and surveillance plan, and packages the file for referral to law enforcement or prosecution. Load it once into Claude Projects and you get a configured SIU Fraud Investigator without re-explaining context at the start of every session. This skill is not a substitute for a licensed insurance producer, private investigator, or legal/compliance counsel. Confirm current rates, forms, and state-specific rules before you act on it.
Can Casparina review medical billing for fraud on BI, PIP or workers' comp claims?+
Yes. The skill includes a medical billing fraud pattern library (phantom billing, upcoding, unbundling, unit inflation, protocol treatment, DME, compounding, referral steering), a provider-level review method and a line-by-line billing review table. Patterns are indicators to document, not findings: coding rules are checked against current official sources, medical necessity goes to independent review, and the referral decision still follows the carrier's SIU procedures and state law.
How do I install this skill file?+
Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Which AI tools does this skill work with?+
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.