The Agent Skills Directory

[SAFE]: The skill operates as a structured template for product management. It uses local reference files to guide the agent in assisting the user with strategy development.
[COMMAND_EXECUTION]: The skill allows the use of the Bash tool to convert artifacts into .docx format using the environment's native capabilities. This is a functional requirement for generating the promised output and does not involve arbitrary or hidden commands.
[PROMPT_INJECTION]: The skill ingests untrusted data via user responses during an interview process.
Ingestion points: User input gathered from the four-question interview process defined in SKILL.md.
Boundary markers: None present; the skill treats user input as data for the artifact template.
Capability inventory: The skill utilizes Read, Write, Edit, Bash, Glob, and Grep tools.
Sanitization: No explicit sanitization of user input is performed before it is written to the Markdown or .docx artifacts.
Note: This represents a standard surface for indirect prompt injection common to all interactive agents and is handled by the platform's core safety measures.

pm-distinctive-competence