The Agent Skills Directory

[SAFE]: The skill is a set of guidelines for architectural and problem-space analysis. It does not contain executable code, remote scripts, or commands that could compromise system security.
[SAFE]: Documented file system interactions are limited to maintaining session context within a local project directory (.oh/). This is a standard functional requirement for maintaining state between different AI agent tasks.
[SAFE]: No evidence of prompt injection or instructions to bypass safety filters was found. The skill actually encourages the agent to adhere to constraints and avoid making assumptions.

problem-space