菜单
Use when incidents occur and you need to triage, categorize, and execute response runbooks automatically. Correlates alerts, identifies root causes, escalates to appropriate teams, and executes remediation procedures for production incidents.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Fully autonomous decision engine with trial-and-error learning capabilities. Executes infrastructure operations without human intervention while leveraging reconciliation engines as safety nets. Learns from outcomes to improve future decisions through pattern recognition and adaptive optimization.
Monitor Kubernetes cluster health and generate alerts for issues. Use when you need automated health monitoring, resource utilization tracking, or proactive issue detection in Kubernetes environments.
Use when you need to create new cloud resources or infrastructure. Handles VM provisioning, Kubernetes clusters, databases, networking, and storage across AWS, Azure, GCP with proper tagging, security, and compliance. Includes cost estimation and resource validation.
AI-powered automated scaling policies skill with intelligent resource optimization, predictive scaling decisions, and adaptive policy management. Use when implementing automated scaling with advanced AI capabilities for proactive resource management and cost optimization.
Enterprise-grade advanced monitoring with AI-powered analytics, real-time anomaly detection, predictive insights, and intelligent alerting. Use when implementing sophisticated monitoring with machine learning, time series analysis, and automated incident response.
Advanced deep learning automation for complex infrastructure pattern recognition, intelligent optimization, and self-healing systems. Use when implementing sophisticated AI capabilities with neural networks, deep learning models, and advanced pattern recognition.
| name | incident-triage-runbook |
| description | Use when incidents occur and you need to triage, categorize, and execute response runbooks automatically. Correlates alerts, identifies root causes, escalates to appropriate teams, and executes remediation procedures for production incidents. |
| license | AGPLv3 |
| metadata | {"author":"agentic-reconciliation-engine","version":"1.0","category":"enterprise","risk_level":"medium","autonomy":"conditional","layer":"temporal"} |
| compatibility | Requires Python 3.8+, cloud provider CLI tools (AWS CLI, Azure CLI, gcloud), and access to multi-cloud monitoring systems |
| allowed-tools | Bash Read Write Grep |
Enterprise-grade automation solution for incident triage runbook operations across AWS, Azure, GCP, and on-premise environments to maximize operational efficiency while maintaining security and compliance standards.
aws|azure|gcp|onprem|all (optional, default: all)production)true)core/scripts/automation/incident-triage-runbook.py: Main automation implementationcore/scripts/automation/incident-triage-runbook_handler.py: Cloud-specific operationscore/scripts/automation/multi_cloud_orchestrator.py: Cross-provider coordinationincident, triage, runbook, automation, enterprise, multi-cloud, aws, azure, gcp, onprem
Load these files when needed:
scripts/incident-triager.py - Alert correlation and categorization enginescripts/runbook-executor.py - Automated runbook execution frameworkreferences/incident-taxonomy.md - Standard incident classification systemassets/escalation-policies.yaml - Team escalation rules and contactsexamples/incident-scenarios/ - Common incident types and response procedures