[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DT4KG0XWFSHT7EVETYNXB":3,"skill-same:01M79DT4KG0XWFSHT7EVETYNXB":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M79DT4KG0XWFSHT7EVETYNXB","model-monitoring-and-drift",null,"Implement automated machine learning model performance monitoring, statistical data drift (KS-test, PSI, Wasserstein distance), concept drift detection, and prediction quality evaluation in production ML systems using Evidently AI, NannyML, SciPy, and Prometheus. Triggers when establishing model observability, real-time feature drift middleware, automated HTML drift reporting, or retraining trigger alerts.","hamzabellouch\u002Fagent-skills","hamzabellouch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F237856042?v=4","01M79BRYW7XAMK3YDWQEMTWGWS","Hamza Bellouch","01M79BRYWXQV3JK2TGVTX8GN2A",8,"MIT","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FProgramming\u002FAI_Engineering_and_Platforms\u002FMLOps_and_Lifecycle\u002Fmodel-monitoring-and-drift\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-monitoring-and-drift\nmetadata:\n  category: Machine Learning Operations (MLOps)\ndescription: >-\n  Implement automated machine learning model performance monitoring, statistical data drift (KS-test, PSI, Wasserstein distance),\n  concept drift detection, and prediction quality evaluation in production ML systems using Evidently AI, NannyML, SciPy, and Prometheus.\n  Triggers when establishing model observability, real-time feature drift middleware, automated HTML drift reporting, or retraining trigger alerts.\ncompatibility: Python (>= 3.9), Evidently AI (>= 0.4.0), SciPy, Prometheus Client, FastAPI \u002F Flask\n---\n\n# Model Monitoring & Drift Detection\n\nProduction patterns for measuring Data Drift, Concept Drift, and Performance Decay in live machine learning applications.\n\n---\n\n## 1. Drift Monitoring Conceptual Framework\n\n| Drift Category | Definition | Statistical Metric | Remediation Strategy |\n| :--- | :--- | :--- | :--- |\n| **Data Drift (Covariate Shift)** | Distribution of input features $P(X)$ changes over time. | Kolmogorov-Smirnov Test, Population Stability Index (PSI), Wasserstein Distance | Feature re-normalization, Retraining on recent data window |\n| **Concept Drift** | Relationship between input features and target $P(Y \\mid X)$ changes. | Cramér's V, Wasserstein Distance, Accuracy\u002FF1 degradation | Architecture update, Label re-annotation, Retraining |\n| **Prior Probability Shift** | Target label distribution $P(Y)$ changes. | Chi-Square Goodness-of-Fit, Jensen-Shannon Divergence | Decision threshold re-calibration |\n\n---\n\n## 2. Statistical Data Drift Engine (`drift_engine.py`)\n\nA pure Python + SciPy statistical drift evaluator for batch production datasets.\n\n```python\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import ks_2samp, chi2_contingency\nimport logging\n\nlogging.basicConfig(level=logging.INFO)\nlogger = logging.getLogger(__name__)\n\nclass StatisticalDriftDetector:\n    def __init__(self, reference_data: pd.DataFrame, alpha: float = 0.05, psi_threshold: float = 0.2):\n        self.reference_data = reference_data\n        self.alpha = alpha\n        self.psi_threshold = psi_threshold\n\n    def calculate_psi(self, reference: np.ndarray, current: np.ndarray, num_buckets: int = 10) -> float:\n        \"\"\"Calculates Population Stability Index (PSI) for continuous variables.\"\"\"\n        # Define bucket boundaries using reference quantiles\n        percentiles = np.linspace(0, 100, num_buckets + 1)\n        buckets = np.percentile(reference, percentiles)\n        buckets[0] = -np.inf\n        buckets[-1] = np.inf\n\n        # Calculate counts per bucket\n        ref_counts, _ = np.histogram(reference, bins=buckets)\n        cur_counts, _ = np.histogram(current, bins=buckets)\n\n        # Convert to proportions with zero-handling smoothing\n        ref_props = np.where(ref_counts == 0, 1e-4, ref_counts) \u002F len(reference)\n        cur_props = np.where(cur_counts == 0, 1e-4, cur_counts) \u002F len(current)\n\n        # Calculate PSI formula\n        psi_value = np.sum((cur_props - ref_props) * np.log(cur_props \u002F ref_props))\n        return float(psi_value)\n\n    def evaluate_numerical_feature(self, feature_name: str, current_data: pd.DataFrame) -> dict:\n        ref_col = self.reference_data[feature_name].dropna().values\n        cur_col = current_data[feature_name].dropna().values\n\n        # Kolmogorov-Smirnov Test\n        ks_stat, p_value = ks_2samp(ref_col, cur_col)\n        drift_detected_ks = p_value \u003C self.alpha\n\n        # Population Stability Index\n        psi_val = self.calculate_psi(ref_col, cur_col)\n        drift_detected_psi = psi_val > self.psi_threshold\n\n        return {\n            \"feature\": feature_name,\n            \"type\": \"numerical\",\n            \"ks_statistic\": float(ks_stat),\n            \"p_value\": float(p_value),\n            \"psi_value\": psi_val,\n            \"drift_detected\": drift_detected_ks or drift_detected_psi\n        }\n\n    def evaluate_categorical_feature(self, feature_name: str, current_data: pd.DataFrame) -> dict:\n        ref_counts = self.reference_data[feature_name].value_counts()\n        cur_counts = current_data[feature_name].value_counts()\n\n        # Combine counts into contingency table\n        df_contingency = pd.DataFrame({'ref': ref_counts, 'cur': cur_counts}).fillna(0)\n        chi2_stat, p_value, _, _ = chi2_contingency(df_contingency.T)\n\n        return {\n            \"feature\": feature_name,\n            \"type\": \"categorical\",\n            \"chi2_statistic\": float(chi2_stat),\n            \"p_value\": float(p_value),\n            \"drift_detected\": p_value \u003C self.alpha\n        }\n\n    def run_drift_analysis(self, current_data: pd.DataFrame) -> dict:\n        results = []\n        drifted_count = 0\n\n        for col in self.reference_data.columns:\n            if np.issubdtype(self.reference_data[col].dtype, np.number):\n                res = self.evaluate_numerical_feature(col, current_data)\n            else:\n                res = self.evaluate_categorical_feature(col, current_data)\n            \n            if res[\"drift_detected\"]:\n                drifted_count += 1\n            results.append(res)\n\n        dataset_drift_ratio = drifted_count \u002F len(self.reference_data.columns)\n\n        return {\n            \"dataset_drift_ratio\": dataset_drift_ratio,\n            \"dataset_drift_detected\": dataset_drift_ratio >= 0.3,\n            \"feature_metrics\": results\n        }\n```\n\n---\n\n## 3. Real-Time Inference Monitoring Middleware (FastAPI + Prometheus Exporter)\n\nExport real-time feature drift statistics directly to Prometheus from your inference endpoints.\n\n```python\nfrom fastapi import FastAPI, Request\nfrom prometheus_client import Gauge, Counter, make_asgi_app\nimport numpy as np\nimport time\n\napp = FastAPI(title=\"ML Model Serving with Drift Exporter\")\n\n# Prometheus Metrics Definition\nPREDICTION_COUNT = Counter(\"model_predictions_total\", \"Total inference requests executed\")\nFEATURE_DRIFT_GAUGE = Gauge(\"model_feature_psi\", \"Population Stability Index per Feature\", [\"feature_name\"])\nDATASET_DRIFT_STATUS = Gauge(\"model_dataset_drift_detected\", \"1 if dataset level drift detected else 0\")\n\n# Reference baseline mean and std for online z-score check\nBASELINE_STATS = {\n    \"income\": {\"mean\": 65000.0, \"std\": 15000.0},\n    \"credit_score\": {\"mean\": 710.0, \"std\": 45.0}\n}\n\n@app.post(\"\u002Fpredict\")\nasync def predict_endpoint(payload: dict):\n    start_time = time.time()\n    PREDICTION_COUNT.inc()\n\n    features = payload.get(\"features\", {})\n    \n    # Online Z-score Outlier & Drift Metric Export\n    for feature_name, val in features.items():\n        if feature_name in BASELINE_STATS:\n            mean = BASELINE_STATS[feature_name][\"mean\"]\n            std = BASELINE_STATS[feature_name][\"std\"]\n            z_score = abs((val - mean) \u002F std)\n            \n            # Export Z-Score as online proxy for drift\n            FEATURE_DRIFT_GAUGE.labels(feature_name=feature_name).set(z_score)\n\n    # Perform prediction logic (mocked)\n    score = np.random.random()\n\n    return {\"credit_decision\": \"approved\" if score > 0.5 else \"rejected\", \"score\": score}\n\n# Expose \u002Fmetrics endpoint for Prometheus scrapers\nmetrics_app = make_asgi_app()\napp.mount(\"\u002Fmetrics\", metrics_app)\n```\n\n---\n\n## 4. Evidently AI Automated HTML Drift Reporting (`generate_report.py`)\n\nGenerate offline interactive HTML drift and data quality reports using Evidently AI.\n\n```python\nimport pandas as pd\nfrom evidently.report import Report\nfrom evidently.metric_preset import DataDriftPreset, TargetDriftPreset, DataQualityPreset\n\ndef generate_evidently_drift_report(reference_df: pd.DataFrame, current_df: pd.DataFrame, output_filepath: str):\n    \"\"\"Generates an HTML Data & Target Drift Report.\"\"\"\n    report = Report(metrics=[\n        DataDriftPreset(),\n        DataQualityPreset(),\n        TargetDriftPreset()\n    ])\n\n    report.run(reference_data=reference_df, current_data=current_df)\n    report.save_html(output_filepath)\n    print(f\"Drift report generated successfully at: {output_filepath}\")\n\nif __name__ == \"__main__\":\n    ref = pd.DataFrame({\"income\": [50000, 60000, 70000, 80000], \"target\": [0, 1, 0, 1]})\n    cur = pd.DataFrame({\"income\": [90000, 120000, 110000, 95000], \"target\": [1, 1, 1, 1]})\n    generate_evidently_drift_report(ref, cur, \"drift_report.html\")\n```\n\n---\n\n## 5. Retraining Trigger & Alerting Integration\n\n```python\nimport requests\nimport json\n\nSLACK_WEBHOOK_URL = \"https:\u002F\u002Fhooks.slack.com\u002Fservices\u002FYOUR_WORKSPACE\u002FYOUR_CHANNEL\u002FYOUR_WEBHOOK_TOKEN\"\n\ndef send_drift_alert(drift_results: dict):\n    if drift_results[\"dataset_drift_detected\"]:\n        payload = {\n            \"text\": \":warning: *ML Model Drift Alert*\",\n            \"attachments\": [\n                {\n                    \"color\": \"#FF0000\",\n                    \"fields\": [\n                        {\"title\": \"Dataset Drift Ratio\", \"value\": f\"{drift_results['dataset_drift_ratio']:.2%}\", \"short\": True},\n                        {\"title\": \"Status\", \"value\": \"CRITICAL - Retraining Triggered\", \"short\": True}\n                    ]\n                }\n            ]\n        }\n        requests.post(SLACK_WEBHOOK_URL, data=json.dumps(payload), headers={'Content-Type': 'application\u002Fjson'})\n\n        # Trigger Retraining Airflow DAG or GitHub Actions Workflow\n        requests.post(\n            \"https:\u002F\u002Fairflow.prod.internal\u002Fapi\u002Fv1\u002Fdags\u002Fretrain_churn_model\u002FdagRuns\",\n            auth=('admin', 'admin_password'),\n            json={\"conf\": {\"reason\": \"data_drift_exceeded_threshold\"}}\n        )\n```\n\n---\n\n## 6. Best Practices\n\n1. **Reference Dataset Hygiene**: Freeze and version reference datasets matching exact training validation splits; update references only when a newly retrained model is deployed to production.\n2. **Sampling Windows**: Select appropriate drift calculation windows (e.g., 7-day rolling window for high-volume endpoints) to prevent false alerts caused by transient weekend noise.\n3. **Alerting Thresholds**: Set PSI warning thresholds at `0.1 \u003C= PSI \u003C 0.2` (slight shift) and critical alert thresholds at `PSI >= 0.2` (significant shift requiring action).\n","# Model Monitoring & Drift Detection\n\nProduction patterns for measuring Data Drift, Concept Drift, and Performance Decay in live machine learning applications.\n\n---\n\n## 1. Drift Monitoring Conceptual Framework\n\n| Drift Category | Definition | Statistical Metric | Remediation Strategy |\n| :--- | :--- | :--- | :--- |\n| **Data Drift (Covariate Shift)** | Distribution of input features $P(X)$ changes over time. | Kolmogorov-Smirnov Test, Population Stability Index (PSI), Wasserstein Distance | Feature re-normalization, Retraining on recent data window |\n| **Concept Drift** | Relationship between input features and target $P(Y \\mid X)$ changes. | Cramér's V, Wasserstein Distance, Accuracy\u002FF1 degradation | Architecture update, Label re-annotation, Retraining |\n| **Prior Probability Shift** | Target label distribution $P(Y)$ changes. | Chi-Square Goodness-of-Fit, Jensen-Shannon Divergence | Decision threshold re-calibration |\n\n---\n\n## 2. Statistical Data Drift Engine (`drift_engine.py`)\n\nA pure Python + SciPy statistical drift evaluator for batch production datasets.\n\n```python\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import ks_2samp, chi2_contingency\nimport logging\n\nlogging.basicConfig(level=logging.INFO)\nlogger = logging.getLogger(__name__)\n\nclass StatisticalDriftDetector:\n    def __init__(self, reference_data: pd.DataFrame, alpha: float = 0.05, psi_threshold: float = 0.2):\n        self.reference_data = reference_data\n        self.alpha = alpha\n        self.psi_threshold = psi_threshold\n\n    def calculate_psi(self, reference: np.ndarray, current: np.ndarray, num_buckets: int = 10) -> float:\n        \"\"\"Calculates Population Stability Index (PSI) for continuous variables.\"\"\"\n        # Define bucket boundaries using reference quantiles\n        percentiles = np.linspace(0, 100, num_buckets + 1)\n        buckets = np.percentile(reference, percentiles)\n        buckets[0] = -np.inf\n        buckets[-1] = np.inf\n\n        # Calculate counts per bucket\n        ref_counts, _ = np.histogram(reference, bins=buckets)\n        cur_counts, _ = np.histogram(current, bins=buckets)\n\n        # Convert to proportions with zero-handling smoothing\n        ref_props = np.where(ref_counts == 0, 1e-4, ref_counts) \u002F len(reference)\n        cur_props = np.where(cur_counts == 0, 1e-4, cur_counts) \u002F len(current)\n\n        # Calculate PSI formula\n        psi_value = np.sum((cur_props - ref_props) * np.log(cur_props \u002F ref_props))\n        return float(psi_value)\n\n    def evaluate_numerical_feature(self, feature_name: str, current_data: pd.DataFrame) -> dict:\n        ref_col = self.reference_data[feature_name].dropna().values\n        cur_col = current_data[feature_name].dropna().values\n\n        # Kolmogorov-Smirnov Test\n        ks_stat, p_value = ks_2samp(ref_col, cur_col)\n        drift_detected_ks = p_value \u003C self.alpha\n\n        # Population Stability Index\n        psi_val = self.calculate_psi(ref_col, cur_col)\n        drift_detected_psi = psi_val > self.psi_threshold\n\n        return {\n            \"feature\": feature_name,\n            \"type\": \"numerical\",\n            \"ks_statistic\": float(ks_stat),\n            \"p_value\": float(p_value),\n            \"psi_value\": psi_val,\n            \"drift_detected\": drift_detected_ks or drift_detected_psi\n        }\n\n    def evaluate_categorical_feature(self, feature_name: str, current_data: pd.DataFrame) -> dict:\n        ref_counts = self.reference_data[feature_name].value_counts()\n        cur_counts = current_data[feature_name].value_counts()\n\n        # Combine counts into contingency table\n        df_contingency = pd.DataFrame({'ref': ref_counts, 'cur': cur_counts}).fillna(0)\n        chi2_stat, p_value, _, _ = chi2_contingency(df_contingency.T)\n\n        return {\n            \"feature\": feature_name,\n            \"type\": \"categorical\",\n            \"chi2_statistic\": float(chi2_stat),\n            \"p_value\": float(p_value),\n            \"drift_detected\": p_value \u003C self.alpha\n        }\n\n    def run_drift_analysis(self, current_data: pd.DataFrame) -> dict:\n        results = []\n        drifted_count = 0\n\n        for col in self.reference_data.columns:\n            if np.issubdtype(self.reference_data[col].dtype, np.number):\n                res = self.evaluate_numerical_feature(col, current_data)\n            else:\n                res = self.evaluate_categorical_feature(col, current_data)\n            \n            if res[\"drift_detected\"]:\n                drifted_count += 1\n            results.append(res)\n\n        dataset_drift_ratio = drifted_count \u002F len(self.reference_data.columns)\n\n        return {\n            \"dataset_drift_ratio\": dataset_drift_ratio,\n            \"dataset_drift_detected\": dataset_drift_ratio >= 0.3,\n            \"feature_metrics\": results\n        }\n```\n\n---\n\n## 3. Real-Time Inference Monitoring Middleware (FastAPI + Prometheus Exporter)\n\nExport real-time feature drift statistics directly to Prometheus from your inference endpoints.\n\n```python\nfrom fastapi import FastAPI, Request\nfrom prometheus_client import Gauge, Counter, make_asgi_app\nimport numpy as np\nimport time\n\napp = FastAPI(title=\"ML Model Serving with Drift Exporter\")\n\n# Prometheus Metrics Definition\nPREDICTION_COUNT = Counter(\"model_predictions_total\", \"Total inference requests executed\")\nFEATURE_DRIFT_GAUGE = Gauge(\"model_feature_psi\", \"Population Stability Index per Feature\", [\"feature_name\"])\nDATASET_DRIFT_STATUS = Gauge(\"model_dataset_drift_detected\", \"1 if dataset level drift detected else 0\")\n\n# Reference baseline mean and std for online z-score check\nBASELINE_STATS = {\n    \"income\": {\"mean\": 65000.0, \"std\": 15000.0},\n    \"credit_score\": {\"mean\": 710.0, \"std\": 45.0}\n}\n\n@app.post(\"\u002Fpredict\")\nasync def predict_endpoint(payload: dict):\n    start_time = time.time()\n    PREDICTION_COUNT.inc()\n\n    features = payload.get(\"features\", {})\n    \n    # Online Z-score Outlier & Drift Metric Export\n    for feature_name, val in features.items():\n        if feature_name in BASELINE_STATS:\n            mean = BASELINE_STATS[feature_name][\"mean\"]\n            std = BASELINE_STATS[feature_name][\"std\"]\n            z_score = abs((val - mean) \u002F std)\n            \n            # Export Z-Score as online proxy for drift\n            FEATURE_DRIFT_GAUGE.labels(feature_name=feature_name).set(z_score)\n\n    # Perform prediction logic (mocked)\n    score = np.random.random()\n\n    return {\"credit_decision\": \"approved\" if score > 0.5 else \"rejected\", \"score\": score}\n\n# Expose \u002Fmetrics endpoint for Prometheus scrapers\nmetrics_app = make_asgi_app()\napp.mount(\"\u002Fmetrics\", metrics_app)\n```\n\n---\n\n## 4. Evidently AI Automated HTML Drift Reporting (`generate_report.py`)\n\nGenerate offline interactive HTML drift and data quality reports using Evidently AI.\n\n```python\nimport pandas as pd\nfrom evidently.report import Report\nfrom evidently.metric_preset import DataDriftPreset, TargetDriftPreset, DataQualityPreset\n\ndef generate_evidently_drift_report(reference_df: pd.DataFrame, current_df: pd.DataFrame, output_filepath: str):\n    \"\"\"Generates an HTML Data & Target Drift Report.\"\"\"\n    report = Report(metrics=[\n        DataDriftPreset(),\n        DataQualityPreset(),\n        TargetDriftPreset()\n    ])\n\n    report.run(reference_data=reference_df, current_data=current_df)\n    report.save_html(output_filepath)\n    print(f\"Drift report generated successfully at: {output_filepath}\")\n\nif __name__ == \"__main__\":\n    ref = pd.DataFrame({\"income\": [50000, 60000, 70000, 80000], \"target\": [0, 1, 0, 1]})\n    cur = pd.DataFrame({\"income\": [90000, 120000, 110000, 95000], \"target\": [1, 1, 1, 1]})\n    generate_evidently_drift_report(ref, cur, \"drift_report.html\")\n```\n\n---\n\n## 5. Retraining Trigger & Alerting Integration\n\n```python\nimport requests\nimport json\n\nSLACK_WEBHOOK_URL = \"https:\u002F\u002Fhooks.slack.com\u002Fservices\u002FYOUR_WORKSPACE\u002FYOUR_CHANNEL\u002FYOUR_WEBHOOK_TOKEN\"\n\ndef send_drift_alert(drift_results: dict):\n    if drift_results[\"dataset_drift_detected\"]:\n        payload = {\n            \"text\": \":warning: *ML Model Drift Alert*\",\n            \"attachments\": [\n                {\n                    \"color\": \"#FF0000\",\n                    \"fields\": [\n                        {\"title\": \"Dataset Drift Ratio\", \"value\": f\"{drift_results['dataset_drift_ratio']:.2%}\", \"short\": True},\n                        {\"title\": \"Status\", \"value\": \"CRITICAL - Retraining Triggered\", \"short\": True}\n                    ]\n                }\n            ]\n        }\n        requests.post(SLACK_WEBHOOK_URL, data=json.dumps(payload), headers={'Content-Type': 'application\u002Fjson'})\n\n        # Trigger Retraining Airflow DAG or GitHub Actions Workflow\n        requests.post(\n            \"https:\u002F\u002Fairflow.prod.internal\u002Fapi\u002Fv1\u002Fdags\u002Fretrain_churn_model\u002FdagRuns\",\n            auth=('admin', 'admin_password'),\n            json={\"conf\": {\"reason\": \"data_drift_exceeded_threshold\"}}\n        )\n```\n\n---\n\n## 6. Best Practices\n\n1. **Reference Dataset Hygiene**: Freeze and version reference datasets matching exact training validation splits; update references only when a newly retrained model is deployed to production.\n2. **Sampling Windows**: Select appropriate drift calculation windows (e.g., 7-day rolling window for high-volume endpoints) to prevent false alerts caused by transient weekend noise.\n3. **Alerting Thresholds**: Set PSI warning thresholds at `0.1 \u003C= PSI \u003C 0.2` (slight shift) and critical alert thresholds at `PSI >= 0.2` (significant shift requiring action).\n",{"name":5,"metadata":24,"description":7,"compatibility":26},{"category":25},"Machine Learning Operations (MLOps)","Python (>= 3.9), Evidently AI (>= 0.4.0), SciPy, Prometheus Client, FastAPI \u002F Flask","main","e905af21e5f1e1c3ca605e9656c3a7930360a84e","Programming\u002FAI_Engineering_and_Platforms\u002FMLOps_and_Lifecycle\u002Fmodel-monitoring-and-drift",1,"https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills","https:\u002F\u002Fhamzabellouch.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fhamzabellouch","hamzabellouch.github.io","CEO & Founder of @tknoglobal | Researcher in Technology & Applied Sciences.","2026-10-17 03:20:19",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add hamzabellouch\u002Fagent-skills --skill model-monitoring-and-drift",{"tool":43,"command":44},"bunx","bunx skills add hamzabellouch\u002Fagent-skills --skill model-monitoring-and-drift",{"tool":46,"command":47},"pnpm","pnpm dlx skills add hamzabellouch\u002Fagent-skills --skill model-monitoring-and-drift","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FProgramming\u002FAI_Engineering_and_Platforms\u002FMLOps_and_Lifecycle\u002Fmodel-monitoring-and-drift\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M79FHH2H815A9TAP6WNKH4Q8","security-audit","Comprehensive security guidance, source code audit, vulnerability assessment, and penetration test review for codebases, APIs, microservices, CLI tools, libraries, and LLM-backed applications. Triggers on requests to audit a codebase, conduct security reviews, find vulnerabilities or flaws, pen-test source code, or when the user asks in Arabic (فحص أمني، تدقيق الكود أمنياً، مراجعة الثغرات، فحص أمان المشروع). Supports Guidance mode (focused review) and Full Audit mode (deterministic 6-phase harness).","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FSecurity_Audit_and_Code_Review\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79FHBGXVBY6VQ1X7ETAZMF1","malware-analysis-reversing","Production malware analysis workflows, reverse engineering methodologies, isolated sandbox triage, static\u002Fdynamic binary analysis, memory forensics, and YARA detection rule authoring.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fmalware-analysis-reversing\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79FH6EACDR801TZCE4R8SAC","application-security-pentesting","Production Application Security (AppSec) standards, OWASP Top 10 vulnerability remediation, SAST\u002FDAST pipeline integration, secure code review, threat modeling, and defensive security posture.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fapplication-security-pentesting\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79FH0VKVT44FK923K520ZQA","oauth2-oidc-security-flows","Implement enterprise OAuth 2.1 and OpenID Connect (OIDC) authorization code flow with Proof Key for Code Exchange (PKCE), state and nonce verification, refresh token rotation, token revocation, and centralized IdP federation (Keycloak, Auth0, Okta). Trigger when building secure authentication, single sign-on (SSO), or third-party delegated authorization.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Foauth2-oidc-security-flows\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79FGVVB3R4T88XXD8FRSV5B","jwt-session-management-hardening","Harden JWT-based authentication and session lifecycles using asymmetric signing (RS256\u002FEdDSA), JWKS rotation, strict claims validation, Redis-backed sliding window sessions, revocation lists, and secure HttpOnly cookie storage. Trigger when implementing token validation, session revocation, or hardening API authentication.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Fjwt-session-management-hardening\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M79FGNCPZ85CVEY0B3NE4H3B","soc2-compliance-automation","Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege, or CI\u002FCD security gates.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FGovernance_Compliance_and_Legal_Tech\u002Fsoc2-compliance-automation\u002FSKILL.md",[],[]]