The Agent Skills Directory

[SAFE]: The skill provides structured guidance and templates for designing alert systems within CRM and Slack environments. It does not attempt to access sensitive system files or establish unauthorized network connections.
[COMMAND_EXECUTION]: The skill includes a local utility script scripts/check-output.py that validates generated markdown files. The script is used by the agent to verify that all required sections (Context, Metrics, etc.) are present in the final deliverable. This is a benign support script with a narrow, defined purpose.
[INDIRECT_PROMPT_INJECTION]: The skill is intended to process external data sources such as buying signals and CRM pipeline changes. While this creates a surface for potential indirect instructions, the skill uses structured output templates and explicit quality check criteria to mitigate the risk of the agent following instructions embedded in the processed data.

proactive-alerts