The Agent Skills Directory

[SAFE]: The skill's logic is entirely contained within instructions for persona-based analysis and text generation. It does not attempt to access sensitive system files, hardcode credentials, or establish unauthorized network connections.
[PROMPT_INJECTION]: The skill is designed to ingest and process user narratives concerning business and execution dilemmas. This creates a surface for indirect prompt injection, where a user might attempt to influence the agent's internal diagnostic logic. However, the risk is minimized as the skill does not possess capabilities to execute code or exfiltrate data.
Ingestion points: User descriptions of business, products, or career situations in SKILL.md.
Boundary markers: None; the skill lacks explicit delimiters for user content.
Capability inventory: Persona-driven response generation and local file access for retrieving case study examples.
Sanitization: None; the system relies on standard model behavioral constraints.

ludamo-lianmai