Pagerduty Incident Responder
GitHubOfficial
Automated incident response workflow that correlates PagerDuty alerts with GitHub activity to suggest remediation.
Cloud and DevOpsGitHub Copilot
MITGitHub stars of the source repository40.9k
Agent Skills
Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
Results
194 skills
AWS Incident Triage
GitHubOfficial
A structured, evidence-based SRE agent for investigating AWS CloudWatch incidents.
Cloud and DevOpsGitHub CopilotMITGitHub stars of the source repository40.9k
Cloud Saas Outage Triage
GitHubOfficial
Triage application failures by distinguishing between upstream cloud or SaaS provider incidents and local code issues.
Cloud and DevOpsGitHub CopilotMITGitHub stars of the source repository40.9k
Qdrant Monitoring Setup
GitHubOfficial
A guide for configuring monitoring, health checks, alerting, and log centralization for Qdrant deployments.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
AWS Cloudwatch Investigation
GitHubOfficial
A structured framework for investigating AWS production incidents using CloudWatch logs, metrics, and alarm correlation patterns.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Vercel Optimize
VercelOfficial
An observability-first audit tool for Vercel projects to identify and resolve cost and performance bottlenecks.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskHas scriptsGitHub stars of the source repository33.7k
Sentry
OpenAIOfficial
Integrates Sentry CLI for read-only inspection of production errors, issue tracking, and observability data.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository28.6k
Gke AI Troubleshooting Tpu Metrics Monitoring
GoogleOfficial
Monitor and troubleshoot GKE TPU workloads using system metrics and PromQL queries.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Low riskHas scriptsGitHub stars of the source repository23.2k
Gke AI Troubleshooting Tpu Performance Degradation
GoogleOfficial
Diagnose and troubleshoot GKE Cloud TPU performance degradation using ML Diagnostics Workload Monitoring and system metrics.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Cloud Monitoring Chart Generation
GoogleOfficial
Generates Google Cloud Monitoring dashboard widget textprotos from PromQL or ListTimeSeries queries.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Low riskHas scriptsGitHub stars of the source repository23.2k
Application Integration Troubleshooting
GoogleOfficial
Diagnose and resolve failed, stalled, or silent Google Cloud Application Integration executions.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Low riskGitHub stars of the source repository23.2k
Workload Manager Basics
GoogleOfficial
Manage Google Cloud Workload Manager evaluations and rules using client libraries and the REST API.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Low riskGitHub stars of the source repository23.2k
Cloud Run Alert Configuration
GoogleOfficial
Generate SRE-aligned Terraform alerting policies for Google Cloud Run services, jobs, and worker pools.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Gke Node Notready
GoogleOfficial
Systematically diagnose GKE nodes in NotReady or Unknown status by analyzing logs, metrics, and node conditions.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Cloud Monitoring Metric Selection
GoogleOfficial
A workflow for discovering and querying Google Cloud Monitoring metric descriptors using MCP tools.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Gke Observability
GoogleOfficial
Configure and troubleshoot GKE observability, including Cloud Logging, Cloud Monitoring, and Managed Service for Prometheus.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Cloud Monitoring Alert Configuration
GoogleOfficial
Configure Google Cloud Monitoring alerting policies using Terraform and PromQL for diverse infrastructure and AI agent workloads.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Low riskHas scriptsGitHub stars of the source repository23.2k
Gke Storage Troubleshooting
GoogleOfficial
Systematically diagnose and resolve persistent storage failures in Google Kubernetes Engine (GKE).
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Cloud Monitoring List Time Series Request
GoogleOfficial
Generates structured Cloud Monitoring ListTimeSeries API requests and aggregation configurations.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Bigquery Troubleshooting
GoogleOfficial
Diagnostic workflows for troubleshooting BigQuery performance, cost spikes, and execution bottlenecks.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Cloud Logging Finops
GoogleOfficial
Audits Google Cloud Logging costs and generates actionable FinOps reports to identify waste and optimize spend.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Low riskHas scriptsGitHub stars of the source repository23.2k
Cloud Logging Cross Project Configuration
GoogleOfficial
Configure and troubleshoot Google Cloud cross-project centralized logging and read-time aggregation.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Cloud Logging Configuration Basics
GoogleOfficial
Configure Google Cloud Logging resources including buckets, sinks, views, metrics, and cost-saving exclusions.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k
Gke AI Troubleshooting Tpu Mxla Hang
GoogleOfficial
Diagnose and categorize multi-slice GKE Cloud TPU training hangs using ML Diagnostics and MXLA Hang Analyzer.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository23.2k