Upgrade Guidewire InsuranceSuite versions and migrate between environments. Use when planning version upgrades, handling breaking changes, or migrating from self-managed to Cloud.
Implement Replit reliability patterns including circuit breakers, idempotency, and graceful degradation.
Use when optimizing travel spend with Navan's policy engine, analyzing booking patterns for savings, and configuring the Navan Rewards program.
Configure Navan admin roles, travel policies, approval workflows, and department-level access controls.
Make your first Navan API call to retrieve trip and user data. Use when verifying a new Navan integration works end-to-end after auth setup.
Use when planning or executing a migration from SAP Concur or legacy TMC to Navan — data migration, user provisioning, policy recreation, and cutover planning.
Set up dev/staging/prod environment separation for Navan integrations without a sandbox API. Use when configuring multiple environments, building CI test pipelines, or setting up…
Use when setting up monitoring, logging, and alerting for Navan API integrations in production environments.
Use when handling Navan API changes in production — defensive coding patterns, schema validation, deprecation monitoring, and gradual rollout strategies for unversioned APIs.
Set up webhook listeners for real-time Navan event notifications. Use when you need to receive booking, expense, or travel disruption events from Navan.
ALWAYS USE when investigating incidents, checking system health, exploring services, validating hypotheses, or querying ANY observability backend (Prometheus/Mimir, Loki, Tempo,…
대상 프로젝트 런타임 관측 — Spring Actuator, Micrometer, logback JSON, Slack webhook. 로깅/모니터링/알림 설계 시 사용.
Query and analyze Claude Code observability data (metrics, logs, traces). Use when analyzing performance, costs, errors, tool usage, sessions, conversations, or subagents.
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting.
Application-side observability — structured logs, Prometheus metrics, OTel traces, signal correlation, head sampling, PII discipline, RED+USE.
Use when performing a deep observability audit or remediating missing structured logging, metrics, traces, or alerting rules
Fetch production observability signals from Sentry — error, exception, stack trace, regression, and alert data. Auto-loads on Sentry references.
Produces an architectural specification document mapping Gateway SSE events and OTEL spans to named dashboard widgets, a data flow diagram, and an MCP App config — ready to hand…
Making multi-agent workflows visible and debuggable for designers and developers.
Designs comprehensive observability strategies including SLI/SLO frameworks, alerting optimization, and dashboard generation.
Build production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and incident response workflows.
Use when building platform or application observability, defining SLOs, preparing telemetry backend artifacts, enforcing OpenTelemetry semantic conventions, creating alert…
Instrumentação com OpenTelemetry, logs estruturados e correlação por trace_id/span_id para achar causa raiz em microsserviços.
Observability guidelines for distributed systems using OpenTelemetry, tracing, metrics, and structured logging
Adds production observability to a service — structured logging, RED/USE metrics, OpenTelemetry distributed tracing, plus Prometheus/Grafana dashboards and actionable SLO-based…
Configure verbosity levels, live log streaming, JSONL file export, model I/O logging, and audit trails for monitoring agent execution.
Find unlogged Error branches in recently modified Gleam code and add wisp.log_* calls with string.inspect(err) context. Audits log levels, message format, and sensitive data leaks.
Production visibility through logs, metrics, traces, and alerting — the three pillars of observability
You are a monitoring and observability expert specializing in implementing comprehensive monitoring solutions.
You are an SLO (Service Level Objective) expert specializing in implementing reliability standards and error budget-based engineering practices.
Automated pattern recognition in Claude Code telemetry. Use when detecting failures, slowness, anomalies, trends, inefficiencies, conversation patterns, or tool sequences.
Observability: structured logging, metrics (RED/USE/four golden signals), distributed tracing (OpenTelemetry), correlation IDs, log aggregation, SLO/SLI.
Shannon-specific log reader for session, hook, and run-state diagnostics. ALWAYS use when the user says "session trace", "shannon doctor", "session log audit", "hooks fired log",…
Configure OpenTelemetry tracing, metrics, and structured logging for DAPR applications. Integrates with Azure Monitor, Jaeger, Prometheus, and other observability backends.
Observability and SRE expert. Use when setting up monitoring, logging, tracing, defining SLOs, or managing incidents.
Prometheus metrics and observability standards. Use when writing, generating, or reviewing code with metrics or instrumentation.
Design observability systems with metrics, logs, traces. TRIGGERS - Use when user needs help with observability-system related tasks.
Trigger: structured logging, tracing, telemetry, SLI metrics, SLO alerts, log formats. Scope: Performance metrics, error tracing, production telemetry.
Use when adding monitoring/alerting or when alerts are noisy/missing — instrument golden signals, make the system debuggable (metrics/logs/traces), and page humans only on…
Plan, implement, test, and diagnose observability for server-side Swift services, including Swift Logging, Swift Metrics, Swift Distributed Tracing, OpenTelemetry handoffs,…
Verify at Stage 6c that every metric, log, and trace promised in the design-spec is actually emitted by the shipped code. Runs on full and hotfix tracks only.
Forensic observability audit v1 (Gestalt-Popper). 18-phase deep analysis of whether you can SEE WHAT THE SYSTEM DOES IN PRODUCTION: structured logging coverage, log-level…
Monitor, observe, and report on infrastructure health, application metrics, and system observability.
Top-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates auth/runtime setup…
Optimize OneNote Graph API performance for large notebooks, image handling, and batch operations. Use when dealing with slow API responses, large notebooks, image uploads, or HTTP…
Migrate OneNote integrations across Graph SDK versions, auth deprecations, and API changes. Use when upgrading Graph SDK, migrating from app-only to delegated auth, or handling…
Implement change detection for OneNote using polling and delta queries (webhooks decommissioned June 2023).
Pydantic Logfire observability — OTEL GenAI traces, tool call spans, token metrics, distributed tracing
Diagnose and fix OpenEvidence common errors. Trigger: "openevidence error", "fix openevidence", "debug openevidence".
Create a minimal working OpenEvidence example. Trigger: "openevidence hello world", "openevidence example", "test openevidence".
Install and configure OpenEvidence SDK/API authentication. Use when setting up a new OpenEvidence integration.
Migration Deep Dive for OpenEvidence. Trigger: "openevidence migration deep dive".
Performance Tuning for OpenEvidence. Trigger: "openevidence performance tuning".
Set up OpenRouter API authentication and configure API keys. Use when starting a new OpenRouter integration, rotating keys, or troubleshooting auth issues.
Avoid common OpenRouter integration mistakes and gotchas. Use proactively when starting a new integration or reviewing existing code.
Optimize OpenRouter request latency and throughput. Use when building real-time applications, reducing TTFT, or scaling request volume.
Migrate to OpenRouter from direct provider APIs or upgrade between SDK/model versions. Triggers: 'openrouter migrate', 'openrouter upgrade', 'switch to openrouter', 'migrate from…
Search logs and traces, or run a live tail, when the user asks about current system behavior, incidents, errors, or recent runtime activity.
Diagnose and fix Oracle Cloud Infrastructure API errors with real error codes and proven fixes. Use when encountering OCI ServiceError exceptions, auth failures, SSL issues, or…
Track OCI spend with the Usage API and set up budget alerts. Use when monitoring Oracle Cloud costs, creating budgets, analyzing spend by compartment or service, or optimizing…