mcpField
F
fraud-detection

fraud-detection

github.com/gtmagentsMarketing & growth428153 installsUpdated 30w ago
Repository

About fraud-detection

A skill for designing safeguards and investigating suspicious activity in referral programs. It outlines signal collection, risk scoring, review workflows, investigation procedures, and ongoing policy updates.

Key features

  1. 01Referral fraud signal collection
  2. 02Cohort-based risk scoring
  3. 03Automated flagging and review workflows
  4. 04Investigation runbook templates
  5. 05Heuristic and policy feedback loop

Use cases

  1. 01Design safeguards for a referral launch
  2. 02Investigate suspicious referral spikes
  3. 03Review duplicate accounts or payout anomalies
  4. 04Report program integrity to compliance teams

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/gtmagents/gtm-agents --skill fraud-detection

After installing, type/fraud-detectionin Claude Code to confirm it loaded.

Details

From the project README

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.

Comments

Markdown supported