Compute z-scores of monthly spend to detect category-level financial anomalies.
npx skills add https://github.com/MindOpsTeam/agente-cfo --skill cfo-anomalias
Please help me install this Agent Skill. Skill: cfo-anomalias Source: https://github.com/MindOpsTeam/agente-cfo/tree/main/skills/cfo-anomalias Command: npx skills add https://github.com/MindOpsTeam/agente-cfo --skill cfo-anomalias
Detects financial anomalies automatically using statistical methods (z-score by category, deviations from historical spend, and client concentration) to help Marcos identify what is "out of the ordinary" pro-actively.
Run the anomaly detection workflow for the current month to identify category outliers, spend variation, and client concentration.
High-intent search queries and answers about installing and using this skill.
To detect financial anomalies, the Skill computes a z-score for the current month's spend against historical data, surfacing category-level outliers. It applies this statistical method across categories to flag significant deviations from normal spending patterns.
Monitoring month-over-month spend variation is done by checking deviations from historical spend patterns within the ERP. The Skill flags expenses that diverge from established historical patterns, helping you proactively identify unusual financial activity.
Yes, you can analyze client concentration risk by evaluating over-reliance on key customers using ERP data. The Skill flags concentration risk from top clients to reveal potential vulnerabilities in your revenue streams.
Category-level outlier detection works by computing a z-score by category to surface spend outliers. This statistical approach evaluates the current month's spend against historical data to identify categories with abnormal financial activity.
Yes, historical data is required to identify spend anomalies because the Skill calculates a z-score of the current month's spend against historical data. This historical baseline is essential for accurately flagging category-level outliers and month-over-month variations.
Liangwei-zhangGenerate mean-reversion trading signals from a two-instrument price ratio using Z-scores.
Ronin15Generate performance reports from SDL3 HammerEngine benchmark results.
MindOpsTeamGenerate structured executive CFO reports for weekly and monthly periods.
anton-abyzovDetect anomalies and outliers using statistical methods, Isolation Forest, and autoencoders.
