fraud-detection · anthropics — Claude Code skill for claims screening
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.
no license 104 installs ★ 456 updated 2026-08-27
npx skills add anthropics/healthcare --skill fraud-detection -a claude-codeWhat fraud-detection does
The skill checks claims in corpus.duckdb against public references including NCCI MUE, OIG LEIE, CMS enrollment, and PFS. It produces ranked investigation referrals with citations. The findings describe indicators consistent with a scheme; they do not establish fraud.
It needs a claims database with the canonical six-table schema, a quarter, and a line of business: medicare or medicaid. On a first run for a quarter, reference data must be fetched, which requires network access, unzip, and pdftotext from Poppler on PATH. The workflow combines deterministic screening, agent review of selected findings, and provider-level narratives. Scripts create HTML packets, a dashboard, and an XLSX file in the run directory; npx serve is used to preview the dashboard in Claude Code Desktop.
What it helps with
- spot billing anomalies in a claims corpus
- rank referrals for an SIU review
- prepare cited investigation packets
Example prompts for the agent
- Screen
corpus.duckdbformedicaidclaims in2026q3and create ranked investigation referrals. - Scan the Medicare claims for billing patterns that warrant review, with citations for each finding.
How to install fraud-detection
1Skills CLI (Vercel)
npx skills add anthropics/healthcare --skill fraud-detection -a claude-code2Manually: put the files in place
~/.claude/skills/fraud-detection/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/fraud-detection/
1Skills CLI (Vercel)
npx skills add anthropics/healthcare --skill fraud-detection -a codex2Manually: put the files in place
.agents/skills/fraud-detection/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add anthropics/healthcare --skill fraud-detection -a cursor2Manually: put the files in place
.cursor/skills/fraud-detection/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install anthropics/healthcare plugins/healthcare/skills/fraud-detection2Manually: put the files in place
.github/skills/fraud-detection/SKILL.md1Skills CLI (Vercel)
npx skills add anthropics/healthcare --skill fraud-detection -a gemini-cli2Platform CLI
gemini skills install https://github.com/anthropics/healthcare --path plugins/healthcare/skills/fraud-detectionManually: put the files in place
.devin/skills/fraud-detection/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add anthropics/healthcare --skill fraud-detection -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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 anthropics/healthcare --skill fraud-detection -a claude-code. The skill file is installed at ~/.claude/skills/fraud-detection/SKILL.md.
What does fraud-detection do?
It screens Medicare and Medicaid claims for indicators of fraud, waste, and abuse, then creates ranked, cited investigation referrals.
What does fraud-detection need to run?
It needs corpus.duckdb with the canonical six-table schema, a quarter, and a medicare or medicaid line of business. Fetching reference data also requires network access, unzip, and Poppler's pdftotext on PATH.
Similar skills
SKILL.md skills catalog →fraud-detection by other authors comes first.