Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datase — from…
Automated LGTM + Alloy observability stack deployment using Docker Compose. Use when setting up Claude Code observability infrastructure locally.
Operate as a ruthless OCI observability and incident responder for Monitoring alarms, Logging, Events, Notifications, service health, metrics, runbooks, and IAM-scoped incident…
Intent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via category taxonomy; owns transport tuning,…
Generate comprehensive diagnostic bundles for OneNote Graph API issues with request tracing and token analysis.
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, and Java. Use when the user is building workflows, activities, or workers with a Temporal — from…
Use when adding regression evaluation, prompt and model versioning, token and cost telemetry, latency tracking, tracing, dashboards, or operational monitoring for OpenAI-backed AI…
OpenObserve is an open-source, cloud-native observability platform for logs, metrics, traces, and Real User Monitoring (RUM).
Implement audit logging for OpenRouter API calls. Use when building compliance trails, debugging production issues, or tracking model usage.
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, naming conventions, error handling, performance,…
Platform-agnostic OpenTelemetry reference — signal selection (traces/metrics/logs), span design, context propagation (W3C TraceContext), sampling strategies, and OTLP exporter…
Use when adding distributed tracing, debugging missing spans, fixing W3C traceparent propagation, configuring OTLP exporters (gRPC vs HTTP), choosing sampling strategies, setting…
Aggregates OpenTelemetry trace spans from Jaeger and Zipkin backends into unified flame graphs. Uses the OTLP gRPC exporter SDK to correlate distributed service calls across…
Query OCI metrics with MQL and create monitoring alarms via the Python SDK. Use when building dashboards, querying CPU/memory/network metrics, or creating alarms.
Expert guidance for configuring and deploying the OpenTelemetry Collector. Use when setting up a Collector pipeline, configuring receivers, exporters, or processors, deploying a…
Designs OpenTelemetry Collector pipeline configurations with receivers (otlp, prometheus, filelog), processors (batch, attributes, tail_sampling), and exporters (otlphttp, jaeger,…
OpenTelemetry Transformation Language (OTTL) expert. Use when writing or debugging OTTL expressions for any OpenTelemetry Collector component that supports OTTL (processors,…
Minimize PCI-DSS scope (engineering posture): use PSP client-side tokenization so the raw PAN never touches your servers (SAQ-A), reduce scope ruthlessly, log money operations for…
Run Lighthouse audits locally via CLI or Node API, parse and interpret reports, and set performance budgets.
Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to…
Optimize Perplexity costs through model routing, caching, token limits, and budget monitoring. Use when analyzing Perplexity billing, reducing API costs, or implementing budget…
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datase — from…
Generates onboarding code snippets for Phoenix tracing integrations and wires them into the project onboarding UI.
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datase — from…
Guide for the phoenix-otel TypeScript package — OTel registration, stack-based global provider management, and provider lifecycle.
OpenTelemetry instrumentation coverage auditor. Scans Node.js/Python/Go/Java source code to detect missing or misconfigured OTel instrumentation — HTTP handlers without spans,…
Este skill deve ser usado quando o usuário precisar consumir a API Pier Cloud (Lighthouse) para gerenciamento de custos em nuvem — incluindo autenticação JWT, listagem de…
Use when publishing or subscribing to Salesforce Platform Events from Apex, comparing Platform Events with Change Data Capture, or designing event-triggered error handling and…
Check if services are responding on given host:port pairs. Supports TCP and HTTP checks with configurable timeout. Use for service monitoring, health checks, and network debugging.
Portkey AI gateway — unified LLM API, load balancing, fallbacks, caching, guardrails, observability
Gerencia o ciclo de vida completo de processos background com suporte cross-platform (Windows taskkill + Unix killpg/SIGTERM).
Prometheus metrics for LLM/AI inference telemetry. Token throughput counters, KV-cache hit/miss rates, latency histograms, model queue depth gauges, and Grafana dashboard…
Builds custom Prometheus exporters using the prometheus_client Python SDK and Go client_golang library.
Reviews Prometheus instrumentation in Go code for proper metric types, labels, and patterns. Use when reviewing code with prometheus/client_golang metrics.
Validates and tests Prometheus alerting rules against historical metrics data using the Prometheus HTTP API /api/v1/query_range endpoint.
Observability patterns for Python backends. Use when adding logging, metrics, tracing, or debugging production issues.
Pyroscope is an open-source continuous profiling platform by Grafana Labs that helps identify CPU, memory, and I/O bottlenecks at the line-of-code level.
Use when writing or reviewing TypeScript/full-stack code. Encodes principles for type safety (branded types, discriminated unions, end-to-end types), real tests over mocks,…
Quickwit is a cloud-native search engine built in Rust for log management and distributed tracing. It offers sub-second search on cloud storage (S3, Azure Blob, GCS), an…
Quota tracking, threshold monitoring, graceful degradation for rate-limited APIs.
Upload files to Cloudflare R2, AWS S3, or any S3-compatible storage (like MinIO) and generate secure, time-limited presigned download links with configurable expiration, typically…
Guias de observabilidade para serviços em produção — logs, métricas, traces e resposta a incidentes. Use ao instrumentar código (logging estruturado, correlation/trace IDs,…
Monitor Replit deployments with health checks, uptime tracking, resource usage, and alerting. Use when setting up monitoring for Replit apps, building health dashboards, or…
Review code for logging patterns and suggest evlog adoption. Guides setup on Nuxt, Next.js, SvelteKit, Nitro, TanStack Start, React Router, NestJS, Express, Hono, Fastify, Elysia,…
Use when an ai-issue-solver batch run should execute unattended over night (or any long period) with full preflight checks, log rotation, dashboard refresh, and a final summary.
Runtime operational metrics with meters, timers, histograms, and moving averages. node-measured patterns for tracking request rates, execution durations, error rates, and EWMAs…
Monitor SAM.gov federal contract opportunities (and follow-on awards) by NAICS, PSC, agency, set-aside, and keyword — produces a daily pipeline report with pursue/no-pursue…
Review SAP Cloud ALM for SRE and operations governance: health monitoring configuration, alerting rule coverage, integration and exception monitoring, business process monitoring,…
Use TickerQ to add persistent cron and time-based job scheduling, retries, multi-node coordination, OpenTelemetry, and a live dashboard to .NET agent services.
Dictionary utilities for scientific Python — attribute-access dicts, conflict-aware merging, nested flattening, and pretty rendering.
System resource introspection + monitoring. `get_specs()` returns full hardware/OS/Python snapshot (CPU, memory, disk, network, GPU, OS, Python version) as a nested dict.
Full Sentry SDK setup for browser JavaScript. Use when asked to "add Sentry to a website", "install @sentry/browser", or configure error monitoring, tracing, session replay, or…
Integrate Sentry into CI/CD pipelines for automated release creation, source map uploads, and deploy notifications.
Analyze and resolve Sentry comments on GitHub Pull Requests. Use this when asked to review or fix issues identified by Sentry in PR comments.
Collect diagnostic information for Sentry troubleshooting and support tickets. Use when events are not appearing in Sentry, SDK initialization seems broken, DSN connectivity…
Debug and analyze {{PROJECT_NAME}} errors and exceptions. Use when investigating crashes, error patterns, performance issues, or understanding what went wrong in production.
Full Sentry SDK setup for .NET. Use when asked to "add Sentry to .NET", "install Sentry for C#", or configure error monitoring, tracing, profiling, logging, or crons for ASP.NET…
Capture your first test error with Sentry and verify it appears in the dashboard. Use when testing a new Sentry integration, verifying error capture works after install-auth, or…
Install and configure Sentry SDK authentication with DSN setup. Use when setting up Sentry error tracking, configuring DSN, or initializing Sentry in a Node.js or Python project.
Sentry error tracking i performance monitoring dla React + Supabase Edge Functions. Aktywuje się przy pracy z błędami, monitoringiem, captureException, error boundary, śledzeniem…