skills.rest
lm93129
lm93129COMMUNITY
Explore all skills by this author →
WebsiteGitHub

transaction-analysis

Detect unusual transactions by analyzing time, amount, counterparties, account relations, and circular paths.

2|Updated May 18, 2026
Search Tags:#data analysis#anomaly detection#transaction analysis#fraud detection#financial audit
One-click install
npx skills add https://github.com/lm93129/claude-for-audit --skill transaction-analysis
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transaction-analysis
Source: https://github.com/lm93129/claude-for-audit/tree/main/forensic-audit/skills/transaction-analysis
Command: npx skills add https://github.com/lm93129/claude-for-audit --skill transaction-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires erp_mcp, bank_mcp, pdfplumber, pandas, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps identify anomalies in transactions, providing insights into potential fraudulent activities or irregularities.

Core Features & Use Cases

  • Anomaly Detection: Identify transactions that deviate from normal patterns based on multiple dimensions (time, amount, counterparties, account relations, and circular paths).
  • Use Case: It can be used during fraud investigations for tracing funds, identifying related-party transactions, and verifying fictitious transactions, as well as for filtering unusual transactions in routine audits.

Quick Start

Perform an analysis on transactions using the 'transaction-analysis' skill with the data source 'ERP 序时账' and the period '2023-01-01 to 2023-12-31'.

Frequently Asked Questions about transaction-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect anomalies and potential fraud in financial transaction data?▼

Anomaly detection in financial transaction data identifies unusual activities by analyzing transaction time, amount, counterparties, account relations, and circular paths to flag potential fraud for investigation.

What is the best way to trace funds and identify related-party transactions during an audit?▼

Tracing funds and identifying related-party transactions involves analyzing account relations and circular transaction paths within the dataset to verify fictitious transactions and uncover hidden financial flows.

Do I need ERP and bank MCP integration to analyze transaction anomalies?▼

Yes, ERP and bank MCP integration is required for transaction anomaly analysis to retrieve financial datasets automatically and perform comprehensive audits across connected accounting systems.

Can I use pandas and pdfplumber to filter unusual transactions for routine audits?▼

Yes, pandas and pdfplumber dependencies support filtering unusual transactions during routine audits by extracting and processing financial data to detect deviations from normal patterns.

How does circular path analysis work for identifying fictitious transactions?▼

Circular path analysis for fictitious transactions works by mapping account relationships to detect fund flows that loop back to their origin, exposing fabricated activities within the financial dataset.

What dimensions should I analyze to find unusual transactions in an ERP dataset?▼

To find unusual transactions in an ERP dataset, analyze dimensions including transaction time, amount, counterparties, account relations, and circular paths to detect deviations from normal patterns.

Related Skills

Explore More Finance & Accounting Skills→
PaneriVatsalPaneriVatsal

finance-manager

Extract transactions from bank statement PDFs and analyze spending with pandas.

Community
Advanced
skwuwuskwuwu

gvm_audit

Verify GVM audit log integrity and export compliance reports.

Community
Intermediate
nferrer-devnferrer-dev

hedgefundmonitor

Queries aggregated hedge fund financial time series via OFR's Hedge Fund Monitor API.

Community
Intermediate
rnavarychrnavarych
14

domain-fintech:fraud-detection

Implement fraud detection systems with rule-based and ML-based methods.

Community
Advanced