The Agent Skills Directory

[SAFE]: The skill is a purely instructional resource providing definitions and marketing applications for various psychological principles and mental models. It contains no executable scripts, external dependencies, or network operations.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read context from specific local files such as .agents/marketing-strategy.md and .agents/marketing-learnings.md.
Ingestion points: Reads from .agents/marketing-learnings.md, .agents/marketing-strategy.md, .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md.
Boundary markers: None specified in the instructions.
Capability inventory: No file writing, network operations, or subprocess execution capabilities are present in the skill.
Sanitization: No specific sanitization or validation of the content of these files is requested. While this creates a potential surface for indirect prompt injection if the content of these files is untrusted, the lack of dangerous tools or capabilities mitigates the risk.

marketing-psychology