The Agent Skills Directory

[COMMAND_EXECUTION]: Executes observe CLI commands to verify authentication status and perform data queries against telemetry datasets stored in Observe.
[COMMAND_EXECUTION]: Uses shell commands including curl, jq, and sort to programmatically fetch and identify the latest version of OpenTelemetry semantic conventions from official sources.
[EXTERNAL_DOWNLOADS]: Retrieves schema definitions and version metadata from the official OpenTelemetry GitHub repository (open-telemetry/semantic-conventions) to validate conformance.
[PROMPT_INJECTION]: Processes telemetry data (such as span names and attributes) which serves as an ingestion point for untrusted data. While this presents an indirect prompt injection surface, the risk is mitigated by the skill's diagnostic focus and the agent's internal safety constraints.

opentelemetry-validation