The Agent Skills Directory

[SAFE]: The skill operates exclusively within the local file system using the workspace/sessions/ directory to store and retrieve data. It does not access sensitive system paths or credentials.
[DATA_EXFILTRATION]: There are no network operations, API calls, or remote data transmissions present in the instructions. Data remains confined to the user's workspace.
[COMMAND_EXECUTION]: No shell commands, subprocesses, or executable scripts are invoked. The logic is entirely contained within the AI agent's instructional context.
[PROMPT_INJECTION]: The 'Domain Expert Boards' provide personality frameworks and business philosophies based on historical figures. These instructions guide the agent's reasoning process without attempting to override core safety protocols or system constraints.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files (02-niches.md, 05-offer.md). While these files contain external data, they are part of a trusted multi-step workflow where data is generated and consumed within the same business context.

sk-skills