The Agent Skills Directory

[SAFE]: The skill consists of instructional text providing business decision playbooks. No executable code, obfuscation, or unauthorized network activity was identified.
[PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection via the agent's memory interaction.
Ingestion points: Reads from MEMORY.md and USER.md (SKILL.md).
Boundary markers: None identified; context is used directly from memory files.
Capability inventory: Writes decision logs to memory/YYYY-MM-DD.md and updates MEMORY.md (SKILL.md).
Sanitization: No specific sanitization logic is present for data retrieved from memory files.

decision-playbook