Agent Skills
› foryourhealth111-pixel/Vibe-Skills
› detecting-data-anomalies
detecting-data-anomalies
GitHub辅助分析数据中的异常值、罕见事件和可疑记录。适用于审查欺诈交易或传感器尖峰，对比隔离森林等检测算法，并生成供人工复核的候选清单及检查表。
Trigger Scenarios
审查异常交易或传感器尖峰
对比不同异常检测算法工作流
筛选可疑记录供人工复核
Install
npx skills add foryourhealth111-pixel/Vibe-Skills --skill detecting-data-anomalies -g -y
SKILL.md
Frontmatter
{
"name": "detecting-data-anomalies",
"author": "Jeremy Longshore <jeremy@intentsolutions.io>",
"license": "MIT",
"version": "1.0.0",
"description": "Investigate outliers, rare events, spikes, and suspicious records in datasets.\nUse as an explicit anomaly-analysis helper when you want concrete anomaly-detection workflow guidance, not generic data validation or end-to-end ML ownership.\n",
"allowed-tools": "Read, Bash(python:*), Grep, Glob"
}
Detecting Data Anomalies
Positioning
Treat this skill as an explicit/manual helper.
In governed ML routing, anomaly-detection ownership normally belongs to scikit-learn.
When to Use
Use this skill when:
- Reviewing outlier transactions, fraud candidates, sensor spikes, or rare failures
- Comparing isolation forest, one-class SVM, LOF, or threshold-based anomaly workflows
- Turning suspicious records into a shortlist for human inspection
Not For / Boundaries
- Null/duplicate/schema/range validation: use
exploratory-data-analysis - Full model training or end-to-end pipeline ownership: use
scikit-learnorml-pipeline-workflow - Publication-grade figure production: use
scientific-visualization
Typical Outputs
- Candidate anomaly-detection methods and thresholds
- A review checklist for false positives and false negatives
- Suggested tables or plots for the suspicious subset
Related Skills
scikit-learnas the governed routed owner for classical anomaly-detection workflowscreating-data-visualizationsafter anomalies are identified
Version History
- f627ab5 Current 2026-07-25 04:40
