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.
194 skills
Seth Hobson· Community
Manage unified memory and thermal constraints for long-running machine learning jobs on NVIDIA DGX Spark.
Addy Osmani· Community
A systematic approach to instrumenting production code with structured logs, metrics, and traces for effective system observability.
GoogleOfficial
Configure GKE alerting policies in Terraform using PromQL and Google Cloud Managed Service for Prometheus.
Seth Hobson· Community
Expert observability engineer for designing production-grade monitoring, logging, tracing, and reliability systems.
Seth Hobson· Community
An expert DevOps troubleshooter for incident response, system reliability, and complex distributed system debugging.
Seth Hobson· Community
Implement distributed tracing using Jaeger and Tempo to monitor request flows and performance across microservices.
Seth Hobson· Community
A framework for defining and implementing Service Level Indicators, Objectives, and error budgets to manage service reliability.
Seth Hobson· Community
An expert DevOps troubleshooter for rapid incident response, advanced debugging, and system reliability.
Seth Hobson· Community
An expert SRE incident responder persona for managing production outages, coordinating technical teams, and conducting blameless post-mortems.
Seth Hobson· Community
A framework for building structured, reliable, and actionable incident response runbooks.
Seth Hobson· Community
A diagnostic environment doctor for verifying NVIDIA DGX Spark hardware readiness for ML workloads.
Seth Hobson· Community
A guide to designing, structuring, and provisioning production-ready Grafana dashboards for system and application observability.
Seth Hobson· Community
A comprehensive guide to implementing observability patterns, metrics, and distributed tracing for service mesh deployments.
Seth Hobson· Community
A diagnostic workflow for isolating macOS network connectivity failures across local, DNS, path, and service fault domains.
Seth Hobson· Community
An expert DevOps troubleshooter for incident response, system debugging, and observability.
Seth Hobson· Community
A systematic approach to auditing production logs for accurate incident analysis and health monitoring.
Seth Hobson· Community
A comprehensive guide to configuring Prometheus for infrastructure and application metric collection, storage, and monitoring.
Seth Hobson· Community
An expert observability engineer for designing, implementing, and managing production-grade monitoring, logging, and tracing systems.
GitHubOfficial
A two-phase agent-assisted workflow to instrument LLM applications with Arize AX tracing.
GitHubOfficial
A systematic workflow for diagnosing AWS resource health and generating remediation plans using CloudWatch metrics and logs.
GitHubOfficial
A diagnostic guide for troubleshooting Qdrant production performance, memory usage, and optimizer issues using metrics and observability tools.
GitHubOfficial
Instrument web applications to send telemetry data to Azure App Insights for improved observability.
GitHubOfficial
An expert agent for Dynatrace observability and security analysis within GitHub workflows.
GitHubOfficial
A guide for setting up observability and diagnosing performance issues in Qdrant deployments.