The Agent Skills Directory

[SAFE]: The skill serves as a reference guide for monitoring and observability best practices using industry-standard tools like Prometheus, Grafana, OpenTelemetry, and k6.
[COMMAND_EXECUTION]: Provides instructions for running legitimate profiling and performance testing tools such as clinic.js, py-spy, pprof, and k6. These commands are standard for the stated purpose of application performance management.
[EXTERNAL_DOWNLOADS]: Recommends installing widely-used development and monitoring tools (e.g., clinic, py-spy, locust) from official package registries like npm and PyPI.
[PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety filters or override the agent's core behavioral constraints. It includes explicit 'MUST NOT DO' directives to avoid logging sensitive PII or credentials.
[DATA_EXFILTRATION]: No evidence of data exfiltration was found. Network operations described (e.g., OTLP exporters, Slack webhooks) are standard integrations for monitoring systems and use placeholder configurations.

monitoring-expert