worker-protocol
Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.
telemetry-opentelemetry-integrator
Instrument applications with OpenTelemetry for distributed tracing, metrics, and logs; configure exporters for SigNoz, Jaeger, Prometheus, Grafana, and cloud observability platforms
backend-pino
High-performance structured JSON logging for Node.js. Use when building production APIs that need fast, structured logs for observability platforms (Datadog, ELK, CloudWatch). Provides request logging middleware, child loggers for context, and sensitive data redaction. Choose Pino over console.log for any production TypeScript backend.
prometheus-configuration
インフラストラクチャとアプリケーションの包括的なメトリクス収集、ストレージ、モニタリングのためのPrometheusをセットアップします。メトリクス収集の実装、モニタリングインフラストラクチャのセットアップ、アラートシステムの設定時に使用します。
grafana-dashboards
システムとアプリケーションメトリクスのリアルタイム可視化のための本番環境Grafanaダッシュボードを作成・管理します。モニタリングダッシュボードの構築、メトリクスの可視化、運用可観測性インターフェースの作成時に使用します。
feature-audit
Runtime behavior auditing through systematic log injection. Use when user wants to understand what code is doing at runtime, debug complex flows, or audit a process.
observability-instrumentation
Add business metrics using AWS EMF (Embedded Metric Format) to API endpoints. Focus on domain-specific metrics only - AWS AppRunner provides default SLO/SLA metrics. Use when implementing new endpoints, adding command handlers, or instrumenting business events.
opentelemetry
OpenTelemetry observability - use for distributed tracing, metrics, instrumentation, Sentry integration, and monitoring
sentry-monitor
Sentry error monitoring and user behavior tracking via CLI. Use when: (1) debugging user-reported issues, (2) checking recent errors/crashes, (3) tracing user actions before an error occurred, (4) searching issues by user email, (5) user asks "Sentryのログを確認して" or similar.
observability
Tracing with OpenTelemetry and structured logging with slog. Use when adding observability to services, handlers, or debugging production issues.
gatling-convert-from-jmeter
Guide for converting Apache JMeter tests to Gatling.
debugging-wizard
Use when investigating errors, analyzing stack traces, or finding root causes of unexpected behavior. Invoke for error investigation, troubleshooting, log analysis, root cause analysis. Українською: дебаг, налагодження, знайди помилку, виправи баг, стек трейс, логи, діагностика, аналіз помилок, breakpoint, усунення несправностей, трейс, розібратись з помилкою, крашнулось
k8s-namespace-troubleshooting
Use when a user reports a problem in a specific namespace, when investigating unhealthy workloads or pod failures, when checking namespace events and resource status, or when triaging application issues inside Kubernetes
otel-expert
Use when working with OpenTelemetry, telemetry, observability, traces, spans, metrics, logs, OTLP, semantic conventions, or instrumentation. Triggers on "what attributes should I use", "how do I configure the collector", "what's the semconv for X".
prd-to-issues
Break a PRD into independently-grabbable issue files using vertical slices (tracer bullets). Use when user wants to create issues from a PRD.
k8s-platform-operations
Use when performing cluster health checks, responding to incidents and alerts, planning and managing capacity, conducting maintenance operations, managing backups and recovery, or creating and following runbooks
ralph-init
Initialize a PRD (Product Requirements Document) for structured ralph-loop execution
logfire-observability
Full OpenClaw observability in Pydantic Logfire — agent traces, tool calls, metrics, and logs via OpenTelemetry
remote-operator-debug
Debug customer collectors via remote-operator CLI. Use when "collector logs", "customer kubectl", "remote operator", or need to run commands on customer Kubernetes clusters.
litestar-metrics
Add Litestar metrics with OpenTelemetry and Prometheus instrumentation, plugin or middleware wiring, exporter configuration, path grouping, labels, exemplars, and endpoint exclusion strategy. Use when implementing service-level monitoring, scrape endpoints, request metrics, or custom observability dimensions in Litestar. Do not use for log formatting, tracing-only concerns, or exception contract design.
