“observability”

Use when Pi needs to troubleshoot logs/metrics/traces or verify LGTM (Grafana/Loki/Mimir/Tempo) access in local k3s, cloud Kubernetes, or any generic K8s setup.

Logging and observability best practices — structured logging, log levels, correlation IDs, metrics, tracing, and alerting.

Investigates Google Cloud networking issues by analyzing GCP logs, metrics, and diagnostics.

Monitoring, error tracking, structured logging, alerting, health endpoints, backups, disaster recovery, status page, incident response, and auto-scaling.

Generate detailed functional observations for in-scope artifacts.

Capture and review Agent Skill observations, and create, run, diagnose, or iteratively improve Skill evaluations (evals) with the skill-up CLI.

Use when driving the live DPF portal through the browser — messaging a coworker, clicking through build gates, filling an admin form — or when establishing…

Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline →…

Use Langfuse for LLM observability and evaluation and look up Langfuse documentation.

Detonate malware samples in Cuckoo Sandbox to observe runtime behavior — process creation, file system and registry changes, network communications, and API…

Use when a project needs OpenTelemetry instrumentation for Fixter, when verifying an existing OTel setup points to Fixter, or when adding LLM observability.

Use proactively when the user wants help creating, observing, or managing Agent Teams teammates with claude-anyteam CLI backends.

Proves actions worked in reality — not just exit code 0, not just logs — by validating actual observable outcomes in the system

Use when instrumenting with trace/span/track, reviewing code for logging and observability patterns, converting console.log to wide events, adding structured…

Design the executable feedback loop for an intent — fastest check, highest-confidence check, manual fallback, observable shipped signal, and what shouldn't…

Install, configure, and maintain Hermes Cortex — the observability and knowledge layer for Hermes Agent (Ollama, mycortex, Langfuse, Cortex Dashboard, nginx…

AWS/GCP cloud infrastructure: Well-Architected, security, cost, observability.

Use when implementing any feature or bugfix in a Kotlin/Spring Boot service, covers layer conventions, idioms, testing, and observability

Expert skill for Datadog Observability & Security Platform

Use this skill for EverOS local-first Markdown memory service setup, HTTP memory and knowledge APIs, cascade/OME operations, and observability integration.

Use when the plausible consumer of an input is a human or system the agent cannot observe - support tickets, moderation queues, grant/partner applications…

Use the VirtualText vt CLI to monitor response time, observations, and sentiment.

CTO observability stack expertise - Prometheus metrics, Loki logs, Grafana dashboards.

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change.