commit c87f7cab7b6f0c67ae130f4cc6c60533de4b3944 Author: Zhongwei Li Date: Sat Nov 29 18:50:55 2025 +0800 Initial commit diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json new file mode 100644 index 0000000..f97a41a --- /dev/null +++ b/.claude-plugin/plugin.json @@ -0,0 +1,15 @@ +{ + "name": "anomaly-detection-system", + "description": "Detect anomalies and outliers in data", + "version": "1.0.0", + "author": { + "name": "Claude Code Plugins", + "email": "[email protected]" + }, + "skills": [ + "./skills" + ], + "commands": [ + "./commands" + ] +} \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..c8521ad --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +# anomaly-detection-system + +Detect anomalies and outliers in data diff --git a/commands/detect-anomaly.md b/commands/detect-anomaly.md new file mode 100644 index 0000000..7e9e4fa --- /dev/null +++ b/commands/detect-anomaly.md @@ -0,0 +1,15 @@ +--- +description: Execute AI/ML task with intelligent automation +--- + +# AI/ML Task Executor + +You are an AI/ML specialist. When this command is invoked: + +1. Analyze the current context and requirements +2. Generate appropriate code for the ML task +3. Include data validation and error handling +4. Provide performance metrics and insights +5. Save artifacts and generate documentation + +Support modern ML frameworks and best practices. diff --git a/plugin.lock.json b/plugin.lock.json new file mode 100644 index 0000000..44aa4e3 --- /dev/null +++ b/plugin.lock.json @@ -0,0 +1,61 @@ +{ + "$schema": "internal://schemas/plugin.lock.v1.json", + "pluginId": "gh:jeremylongshore/claude-code-plugins-plus:plugins/ai-ml/anomaly-detection-system", + "normalized": { + "repo": null, + "ref": "refs/tags/v20251128.0", + "commit": "e014c1514c28974685c9fe2a4d0bb8c14410e163", + "treeHash": "4b7f6091d374897d31e748ba1425e24fb4d02e2875ab3417f20a36bf7f1b9ca9", + "generatedAt": "2025-11-28T10:18:04.479865Z", + "toolVersion": "publish_plugins.py@0.2.0" + }, + "origin": { + "remote": "git@github.com:zhongweili/42plugin-data.git", + "branch": "master", + "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390", + "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data" + }, + "manifest": { + "name": "anomaly-detection-system", + "description": "Detect anomalies and outliers in data", + "version": "1.0.0" + }, + "content": { + "files": [ + { + "path": "README.md", + "sha256": "7e522358538e1a46969f29b2fd9cba849367c88687d6a0a0e9dd76028a189394" + }, + { + "path": ".claude-plugin/plugin.json", + "sha256": "5ebc1fc3e0babb0aa09ca6375390ad15c75d53b0981d3ebb93383124c7fd6190" + }, + { + "path": "commands/detect-anomaly.md", + "sha256": "043efb83e2f02fc6d0869c8a3a7388d6e49f6c809292b93dd6a97a1b142e5647" + }, + { + "path": "skills/anomaly-detection-system/SKILL.md", + "sha256": "55b5e24f59081b5369ddc4de2a7654a80dce8a4de09b2aed249f4f57829e6d88" + }, + { + "path": "skills/anomaly-detection-system/references/README.md", + "sha256": "baa99985488429aa5cccbdcd86c1978a0f18c5a0e65a6b689e71a4846fdd0af7" + }, + { + "path": "skills/anomaly-detection-system/scripts/README.md", + "sha256": "6c1b5056799033ecb95538062d1d0ffc6063d44dbdef996729830ef87e3c2a5e" + }, + { + "path": "skills/anomaly-detection-system/assets/README.md", + "sha256": "6793b1db07d62fd3e8e1d489cf4da613dd564f8a6e9836f65b20e09d0ed70393" + } + ], + "dirSha256": "4b7f6091d374897d31e748ba1425e24fb4d02e2875ab3417f20a36bf7f1b9ca9" + }, + "security": { + "scannedAt": null, + "scannerVersion": null, + "flags": [] + } +} \ No newline at end of file diff --git a/skills/anomaly-detection-system/SKILL.md b/skills/anomaly-detection-system/SKILL.md new file mode 100644 index 0000000..d4aee41 --- /dev/null +++ b/skills/anomaly-detection-system/SKILL.md @@ -0,0 +1,52 @@ +--- +name: detecting-data-anomalies +description: | + This skill empowers Claude to identify anomalies and outliers within datasets. It leverages the anomaly-detection-system plugin to analyze data, apply appropriate machine learning algorithms, and highlight unusual data points. Use this skill when the user requests anomaly detection, outlier analysis, or identification of unusual patterns in data. Trigger this skill when the user mentions "anomaly detection," "outlier analysis," "unusual data," or requests insights into data irregularities. +allowed-tools: Read, Bash, Grep, Glob +version: 1.0.0 +--- + +## Overview + +This skill allows Claude to utilize the anomaly-detection-system plugin to pinpoint unusual data points within a given dataset. It automates the process of anomaly detection, providing insights into potential errors, fraud, or other significant deviations from expected patterns. + +## How It Works + +1. **Data Analysis**: Claude analyzes the user's request and the provided data to understand the context and requirements for anomaly detection. +2. **Algorithm Selection**: Based on the data characteristics, Claude selects an appropriate anomaly detection algorithm (e.g., Isolation Forest, One-Class SVM). +3. **Anomaly Identification**: The selected algorithm is applied to the data, and potential anomalies are identified based on their deviation from the norm. + +## When to Use This Skill + +This skill activates when you need to: +- Identify fraudulent transactions in financial data. +- Detect unusual network traffic patterns that may indicate a security breach. +- Find manufacturing defects based on sensor data from production lines. + +## Examples + +### Example 1: Fraud Detection + +User request: "Analyze this transaction data for potential fraud." + +The skill will: +1. Use the anomaly-detection-system plugin to identify transactions that deviate significantly from typical spending patterns. +2. Highlight the potentially fraudulent transactions and provide a summary of their characteristics. + +### Example 2: Network Security + +User request: "Detect anomalies in network traffic to identify potential security threats." + +The skill will: +1. Use the anomaly-detection-system plugin to analyze network traffic data for unusual patterns. +2. Identify potential security breaches based on deviations from normal network behavior. + +## Best Practices + +- **Data Preprocessing**: Ensure the data is clean, properly formatted, and scaled appropriately before applying anomaly detection algorithms. +- **Algorithm Selection**: Choose an anomaly detection algorithm that is suitable for the type of data and the specific characteristics of the anomalies you are trying to detect. +- **Threshold Tuning**: Carefully tune the threshold for anomaly detection to balance the trade-off between detecting true anomalies and minimizing false positives. + +## Integration + +This skill can be used in conjunction with other data analysis and visualization tools to provide a more comprehensive understanding of the data and the identified anomalies. It can also be integrated with alerting systems to automatically notify users when anomalies are detected. \ No newline at end of file diff --git a/skills/anomaly-detection-system/assets/README.md b/skills/anomaly-detection-system/assets/README.md new file mode 100644 index 0000000..31a8d68 --- /dev/null +++ b/skills/anomaly-detection-system/assets/README.md @@ -0,0 +1,7 @@ +# Assets + +Bundled resources for anomaly-detection-system skill + +- [ ] visualization_templates/: Contains pre-designed templates for visualizing anomaly detection results. +- [ ] report_templates/: Provides templates for generating anomaly detection reports in various formats (e.g., PDF, HTML). +- [ ] example_datasets/: Includes sample datasets for testing and demonstrating the anomaly detection system. diff --git a/skills/anomaly-detection-system/references/README.md b/skills/anomaly-detection-system/references/README.md new file mode 100644 index 0000000..f503e98 --- /dev/null +++ b/skills/anomaly-detection-system/references/README.md @@ -0,0 +1,8 @@ +# References + +Bundled resources for anomaly-detection-system skill + +- [ ] anomaly_detection_algorithms.md: Provides a comprehensive overview of different anomaly detection algorithms (e.g., Isolation Forest, One-Class SVM, Local Outlier Factor) and their use cases. +- [ ] data_preprocessing_guide.md: Offers guidance on data cleaning, normalization, and feature engineering techniques to improve anomaly detection accuracy. +- [ ] performance_metrics.md: Explains various performance metrics (e.g., precision, recall, F1-score) for evaluating anomaly detection models. +- [ ] case_studies.md: Presents real-world case studies of anomaly detection applications in different industries. diff --git a/skills/anomaly-detection-system/scripts/README.md b/skills/anomaly-detection-system/scripts/README.md new file mode 100644 index 0000000..d8e58ba --- /dev/null +++ b/skills/anomaly-detection-system/scripts/README.md @@ -0,0 +1,8 @@ +# Scripts + +Bundled resources for anomaly-detection-system skill + +- [ ] data_loader.py: Loads data from various sources (CSV, databases, APIs) into a standardized format for anomaly detection. +- [ ] algorithm_selector.py: Automatically selects the most appropriate anomaly detection algorithm based on the dataset characteristics. +- [ ] anomaly_visualizer.py: Generates visualizations (e.g., scatter plots, histograms) to highlight detected anomalies. +- [ ] report_generator.py: Creates a detailed report summarizing the detected anomalies, their severity, and potential causes.