The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard build commands such as ./mvnw clean verify or mvn clean verify to validate metrics registration and code changes.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates code refactoring based on user requests, which creates an attack surface for indirect injection. However, it provides robust guardrails by mandating 'CARDINALITY SAFETY' to prevent high-cardinality or sensitive data like UUIDs and emails from being used in metrics tags.
[NO_CODE]: The analyzed skill consists entirely of instructional markdown and configuration references; it does not contain any executable scripts or binaries.

182-java-observability-metrics-micrometer