Skip to main content
skill CX Codex

fraud-detection · gtmagents — Claude Code skill for referral abuse

The fraud-detection skill lays out a process for spotting and investigating suspicious activity in referral programs. Use it when referrals spike or payouts look unusual.

Apache-2.0 154 installs ★ 450 updated 2026-04-03

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add gtmagents/gtm-agents --skill fraud-detection -a claude-code
Open on GitHub

What fraud-detection does

The skill outlines how to gather warning signals, including IP or device matches, activity rates, blacklist checks, and manual reviews. It then groups cases by risk factors such as new accounts, high-volume referrers, or mismatched locations. Suggested responses include flagging a case, sending it for review, or holding rewards until verification.

It includes outlines for a monitoring dashboard, an investigation log, and a policy-change checklist. The process also covers evidence gathering, communication templates, and ways to resolve a case. Agree on clawback procedures with legal and finance before launch; that decision shapes how disputed payouts are handled.

This is guidance for designing safeguards and investigating incidents, not a connector to a referral system. The skill also points to incentive-design for sharing findings that could inform changes to incentives.

What it helps with

  • spot suspicious referral spikes
  • score risk across new accounts and high-volume referrers
  • route questionable cases for manual review
  • record signals and actions in an investigation log
  • coordinate referral policy changes with legal and finance

Example prompts for the agent

  • Review a spike in referral registrations and suggest signals to investigate.
  • Draft an investigation log for suspicious payouts, with fields for actions and notes.
  • Create a referral policy update checklist for legal and finance.

How to install fraud-detection

1Skills CLI (Vercel)

npx skills add gtmagents/gtm-agents --skill fraud-detection -a claude-code

2Manually: put the files in place

~/.claude/skills/fraud-detection/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/fraud-detection/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about fraud-detection

How do I install fraud-detection in Claude Code?

Run npx skills add gtmagents/gtm-agents --skill fraud-detection -a claude-code. The skill file is at ~/.claude/skills/fraud-detection/SKILL.md.

What does fraud-detection do?

It provides a workflow for finding possible abuse in referral programs, assessing risk, and handling investigations. It also includes templates for monitoring and case records.

How does the skill suggest handling a suspicious referral?

You can flag it, send it for review, or hold rewards until verification. The skill advises agreeing on clawback procedures with legal and finance before launch.

Source text

SKILL.md · Apache-2.0
---
name: fraud-detection
description: Use to monitor, investigate, and prevent abuse within referral programs.
---

# Referral Fraud Detection Skill

## When to Use
- Designing safeguards for new referral initiatives.
- Investigating suspicious referral spikes, duplicate accounts, or payout anomalies.
- Reporting on program integrity for finance, legal, or compliance teams.

## Framework
1. **Signal Collection** – IP/device matching, velocity checks, blacklist databases, manual reviews.
2. **Scoring Model** – assign risk scores by cohort (new accounts, high-volume referrers, geo mismatch).
3. **Workflow Automation** – auto-flag, queue for review, or pause rewards until verified.
4. **Investigation Runbook** – define evidence gathering, communication templates, and resolution paths.
5. **Feedback Loop** – update heuristics, adjust incentives, and communicate policy changes.

## Templates
- Fraud monitoring dashboard outline (metrics, thresholds, owners).
- Investigation log (case ID, referrer, signals, action taken, notes).
- Policy update checklist (legal, comms, ops, partner notifications).

## Tips
- Combine automated checks with random manual audits for accuracy.
- Align with legal/finance on clawback procedures before launch.
- Share learnings with `incentive-design` to discourage risky behavior.

---

© gtmagents · Apache-2.0 · gtmagents/gtm-agents

Similar skills

All skills for Security →

fraud-detection by other authors comes first.

fraud-detection official anthropics The fraud-detection Claude Code skill screens Medicare and Medicaid claims for signs of fraud, waste, and abuse. It runs on requests to scan a claims dataset or spot billing anomalies. CX Codex +1 104installs affiliate-fraud-detection Maya-Beth Finotti affiliate-fraud-detection builds fraud detection rules and validation workflows for affiliate programs in B2B SaaS and ecommerce, covering cookie stuffing, fake leads, and holds. CX Codex +1 17,600installs Bewary: scam, phishing and fraud detection bewary-app Bewary: scam, phishing and fraud detection is a Claude Code MCP server that checks URLs, domains, phone numbers, emails, crypto wallets and IBANs for scam signals. CX Codex +1 referral-abuse-guardrails Maya-Beth Finotti referral-abuse-guardrails is a Claude Code skill that creates a guardrail spec for refer-a-friend programs, covering reward caps, hold windows, eligibility, verification, and enforcement. CX Codex +1 17,100installs ARM Verify — Entity Intelligence API ata-rajput1990 ARM Verify — Entity Intelligence API is an MCP server that checks companies against public registries and sanctions lists, traces ultimate owners and scores jurisdiction risk. CX Codex +1 149installs maxmind-minfraud membrane MaxMind minFraud integration powered by Membrane CLI. Helps AI agents evaluate transaction risk scores using billing, device, and email data. CX Codex +1 183installs referral-program OpenClaudia Guides AI agents in designing referral programs and viral loops. It covers incentive structures, viral coefficient math, and invite copy. CX Codex +1 437installs

From the same set224

The whole set →
cold-outreach cold-outreach is a Claude Code skill for writing cold emails and LinkedIn outreach. It helps shape outbound sequences and follow-up messages. CX Codex +1 544installs scriptwriting scriptwriting is a Claude Code skill for drafting video scripts and storyboards, with pacing structured from the opening hook to the final call to action. CX Codex +1 335installs technical-bid-library technical-bid-library is a Claude Code skill that organizes reusable technical content for manufacturing RFI and RFP responses, including compliance evidence and bid templates. CX Codex +1 176installs storytelling storytelling — a skill for Claude Code, Codex, Cursor, GitHub Copilot, and Gemini CLI that structures narratives around a four-step SCAR arc. Runs when you need campaign copy, a pitch script, or a product launch story. CX Codex +1 121installs mood-board-builder mood-board-builder gathers visual references, color palettes and typography for creative concepts and presents them to stakeholders. CX Codex +1 108installs whitepapers Guides agents through drafting research-driven whitepapers, data appendices, and launch copy for technical or regulated B2B buyers. CX Codex +1 102installs procurement-playbook The procurement-playbook skill organizes procurement reviews, contract negotiations, and RFP/RFI responses. Use it when legal, security, privacy, or finance specialists need to coordinate. CX Codex +1 1installs engagement-analytics engagement-analytics builds a webinar funnel view from sign-up to conversion, sets KPI thresholds, and shows where the audience drops off. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open