The Agent Skills Directory

[COMMAND_EXECUTION]: The skill explicitly instructs the agent to perform operational actions such as rolling back deployments, applying patches, restarting services, or modifying configurations. These actions are aligned with the skill's primary purpose of providing immediate triage for active breakage.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources, such as crash reports, error logs, and failing service statuses.
Ingestion points: The agent processes details about a 'broken build', 'failing service', or 'production issue' provided during invocation or discovery.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the processed logs/data are defined in the skill body.
Capability inventory: The agent is empowered to modify system state through rollbacks, patches, and configuration changes.
Sanitization: The skill does not define specific sanitization or validation logic for the input data, relying on the agent's internal reasoning and the 'minimum viable fix' constraint to mitigate risks.

cure-wounds